{"type": "FeatureCollection", "features": [{"id": "10.1016/j.envpol.2021.118128", "type": "Feature", "geometry": null, "properties": {"updated": "2026-05-23T16:16:00Z", "type": "Journal Article", "created": "2021-09-09", "title": "Diagnosis of cadmium contamination in urban and suburban soils using visible-to-near-infrared spectroscopy", "description": "Previous studies have mostly focused on using visible-to-near-infrared spectral technique to quantitatively estimate soil cadmium (Cd) content, whereas little attention has been paid to identifying soil Cd contamination from a perspective of spectral classification. Here, we developed a framework to compare the potential of two spectral transformations (i.e., raw reflectance and continuum removal [CR]), three optimization strategies (i.e., full-spectrum, Boruta feature selection, and synthetic minority over-sampling technique [SMOTE]), and three classification algorithms (i.e., partial least squares discriminant analysis, random forest [RF], and support vector machine) for diagnosing soil Cd contamination. A total of 536 soil samples were collected from urban and suburban areas located in Wuhan City, China. Specifically, Boruta and SMOTE strategies were aimed at selecting the most informative predictors and obtaining balanced training datasets, respectively. Results indicated that soils contaminated by Cd induced decrease in spectral reflectance magnitude. Classification models developed after Boruta and SMOTE strategies out-performed to those from full-spectrum. A diagnose model combining CR preprocessing, SMOTE strategy, and RF algorithm achieved the highest validation accuracy for soil Cd (Kappa = 0.74). This study provides a theoretical reference for rapid identification of and monitoring of soil Cd contamination in urban and suburban areas.", "keywords": ["DIFFUSE-REFLECTANCE SPECTROSCOPY", "HUMAN HEALTH", "PREDICTION", "POTENTIALLY TOXIC ELEMENTS", "Boruta algorithm", "01 natural sciences", "Visible-to-near-infrared spectroscopy", "NIR SPECTROSCOPY", "Soil", "ORGANIC-CARBON", "Machine learning", "11. Sustainability", "Soil Pollutants", "Least-Squares Analysis", "0105 earth and related environmental sciences", "Spectroscopy", " Near-Infrared", "RANDOM FOREST", "Urban and suburban soil Cd contamination", "04 agricultural and veterinary sciences", "15. Life on land", "QUANTITATIVE-ANALYSIS", "6. Clean water", "RIVER DELTA", "13. Climate action", "Earth and Environmental Sciences", "Synthetic minority over-sampling technique", "0401 agriculture", " forestry", " and fisheries", "HEAVY-METAL CONCENTRATIONS", "Cadmium"]}, "links": [{"href": "https://doi.org/10.1016/j.envpol.2021.118128"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Environmental%20Pollution", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.1016/j.envpol.2021.118128", "name": "item", "description": "10.1016/j.envpol.2021.118128", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.1016/j.envpol.2021.118128"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2021-12-01T00:00:00Z"}}, {"id": "10.1016/j.jag.2022.103101", "type": "Feature", "geometry": null, "properties": {"updated": "2026-05-23T16:16:23Z", "type": "Journal Article", "created": "2022-11-10", "title": "Forest foliage fuel load estimation from multi-sensor spatiotemporal features", "description": "Foliage fuel is the most flammable component in crown fires. Spatiotemporal dynamics of foliage fuel load (FFL) are important for fire managers to assess fire risk. Here, we integrated optical data from the Landsat 8 Operational Land Imager (OLI) with synthetic aperture radar (SAR) data from Sentinel-1 to estimate FFL. We first reconstructed seamless time series from the Landsat 8 and Sentinel-1 imagery by accounting for unequal time intervals between image observations and outliers. We then extracted temporal features that are proxies of the intra- and inter-annual dynamics from these time series. In addition, we derived spatial features from the imagery that quantify spatial context and therefore used varying window sizes. The random forest regression was implemented to assess the importance of the spatiotemporal features, reduce errors, and derive robust FFL estimates. The satellite estimates were validated against 96 field measurements from Pinus yunnanensis forests in the Liangshan Yi Autonomous Prefecture, Sichuan Province, China. Both the spatiotemporal features of SAR and optical data importantly contributed to FFL estimation. When only optical data was used, the model achieved a R2 of 0.75 (relative Root Mean Squared Error (rRMSE)\u00a0=\u00a025.3\u00a0%), while when only SAR data was used the R2 was 0.76 (rRMSE\u00a0=\u00a025.6\u00a0%). However, when optical and SAR data were combined, the R2 increased to 0.81 (rRMSE\u00a0=\u00a023.2\u00a0%). We also found that temporal features were more important predictors of FFL than features that captured spatial context. We demonstrated our FFL mapping method by a case study in the Chinese Sichuan Province, in relation to the occurrence of a fire. Our method needs additional validation over different tree species and forest types, yet has potential for mapping forest fuel loads and fire risk.", "keywords": ["Landsat 8", "Physical geography", "04 agricultural and veterinary sciences", "15. Life on land", "Fire risk", "01 natural sciences", "GB3-5030", "Spatiotemporal features", "Environmental sciences", "Forest foliage fuel load", "Sentinel-1", "0401 agriculture", " forestry", " and fisheries", "GE1-350", "SDG 14 - Life Below Water", "Random forest", "0105 earth and related environmental sciences"]}, "links": [{"href": "https://doi.org/10.1016/j.jag.2022.103101"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/International%20Journal%20of%20Applied%20Earth%20Observation%20and%20Geoinformation", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.1016/j.jag.2022.103101", "name": "item", "description": "10.1016/j.jag.2022.103101", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.1016/j.jag.2022.103101"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2022-12-01T00:00:00Z"}}, {"id": "10.21203/rs.3.rs-5128244/v2", "type": "Feature", "geometry": null, "properties": {"updated": "2026-05-23T16:19:49Z", "type": "Journal Article", "created": "2025-07-14", "title": "Spatiotemporal prediction of soil organic carbon density in Europe (2000\u20132022) using earth observation and machine learning", "description": "<p>This article describes a comprehensive framework for soil organic carbon density (SOCD, kg/m3) modeling and mapping, based on spatiotemporal random forest (RF) and quantile regression forests (QRF). A total of 45,616 SOCD observations and various Earth observation (EO) feature layers were used to produce 30 m SOCD maps for the EU at four-year intervals (2000\uffe2\uff80\uff932022) and four soil depth intervals (0\uffe2\uff80\uff9320 cm, 20\uffe2\uff80\uff9350 cm, 50\uffe2\uff80\uff93100 cm, and 100\uffe2\uff80\uff93200 cm). Per-pixel 95% probability prediction intervals (PIs) and extrapolation risk probabilities are also provided. Model evaluation indicates good overall accuracy (R2 = 0.63 and CCC = 0.76 for hold-out independent tests). Prediction accuracy varies by land cover, depth interval and year of prediction with the worst accuracy for shrubland and deeper soils 100\uffe2\uff80\uff93200 cm. The PI validation confirmed effective uncertainty estimation, though with reduced accuracy for higher SOCD values. Shapley analysis identified soil depth as the most influential feature, followed by vegetation, long-term bioclimate, and topographic features. While pixel-level uncertainty is substantial, spatial aggregation reduces uncertainty by approximately 66%. Detecting SOCD changes remains challenging but offers a baseline for future improvements. Maps, based primarily on topsoil data from cropland, grassland, and woodland, are best suited for applications related to these land covers and depths. We recommend that users interpret the maps in conjunction with local knowledge and consider the accompanying uncertainty and extrapolation risk layers. All data and code are available under an open license at https://doi.org/10.5281/zenodo.13754343 and https://github.com/AI4SoilHealth/SoilHealthDataCube/.</p", "keywords": ["Model interpretability", "Earth observation", "Time series", "QH301-705.5", "Uncertainty", "R", "Soil organic carbon density", "Soil Science", "Data transformation", "Spatial aggregation", "Machine learning", "Medicine", "Shapley value", "Biology (General)", "Random forest"]}, "links": [{"href": "https://doi.org/10.21203/rs.3.rs-5128244/v2"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/PeerJ", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.21203/rs.3.rs-5128244/v2", "name": "item", "description": "10.21203/rs.3.rs-5128244/v2", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.21203/rs.3.rs-5128244/v2"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2025-05-01T00:00:00Z"}}, {"id": "10.1016/j.geoderma.2021.115656", "type": "Feature", "geometry": null, "properties": {"updated": "2026-05-23T16:16:19Z", "type": "Journal Article", "created": "2021-12-15", "title": "A framework for determining the total salt content of soil profiles using time-series Sentinel-2 images and a random forest-temporal convolution network", "description": "Soil salinization causes a deterioration in soil health and threatens crop growth. Rapid identification of salinization in farmlands is of great significance to improve soil functions and to maintain sustainable land management. As salt moves in soil profiles during plowing and irrigation, the commonly used protocol for measuring and monitoring salt content in topsoil does not provide a thorough assessment. In order to quantify and comprehensively evaluate the salt content in deep soil, this study developed a novel framework for monitoring total salt content in the soil profile to a depth of 1 m by combining information from time-series satellite images and machine learning. The field experiments were conducted in Alar, Southern Xinjiang, with a total of 120 soil samples and 582 measurements of EM38-MK2 apparent electrical conductivity in 2019 and 2020 to quantify the vertical variation in the salt content. A total of 42 covariates derived from time-series Sentinel-2 images, including 20 salinity indices, 10 soil indices, and 12 vegetation indices were used for modeling salinity in the soil profile. From the total covariates, 22 were selected using the Random Forest. Soil salinity which was modeled using a Temporal Convolution Network in 2019 and 2020 and forecast for 2021. The model effectively revealed the spatial and temporal variability of the salt content in the soil profile with R<sup>2</sup> of 0.71 and 0.65 for 2019 and 2020, respectively. The proposed new framework provides an effective method to estimate the salt content in the soil profile for precision agriculture in arid and semi-arid regions.", "keywords": ["2. Zero hunger", "Soil salinity", "Random Forest", "13. Climate action", "Time-series images", "Soil profile", "0401 agriculture", " forestry", " and fisheries", "04 agricultural and veterinary sciences", "15. Life on land", "6. Clean water", "Temporal Convolution Network"]}, "links": [{"href": "https://doi.org/10.1016/j.geoderma.2021.115656"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Geoderma", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.1016/j.geoderma.2021.115656", "name": "item", "description": "10.1016/j.geoderma.2021.115656", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.1016/j.geoderma.2021.115656"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2022-03-01T00:00:00Z"}}, {"id": "10.1016/j.geodrs.2024.e00801", "type": "Feature", "geometry": null, "properties": {"updated": "2026-05-23T16:16:20Z", "type": "Journal Article", "created": "2024-04-20", "title": "National-scale digital soil mapping performances are related to covariates and sampling density: Lessons from France", "description": "Accurate soil property and class predictions through spatial modelling necessitate a thoughtful selection of explanatory variables and sample size, as their choice greatly impacts model performance. Within the framework of Global Soil Nutrient and Nutrient Budgets maps (GSNmap), the FAO Global Soil Partnership (GSP) launched a country-driven digital soil mapping (DSM) approach. The GSP asked the countries if they could implement the DSM prediction of ten soil properties, using their national point data and a set of widely available covariates (GSP_Cov). In this study, we examined the effect of including additional national-based covariates and soil observations on the performance of the prediction models using mainland France as a pilot. The learning soil dataset was based on a systematic 16-to-16\u202fkm grid. For a subset of soil properties, we also assessed using repeated k-fold cross-validation the effect of adding to this dataset many other irregularly spread measurements. The GSP_Cov included common widely available covariates that represented information about terrain, climate, and organisms. The second set of covariates consisted of the GSP_Cov, extended to extra covariates available at a national level, such as previously existing soil maps, geological maps, remote sensing products and others. Random Forest approach in combination with the Boruta selection method was employed for mapping ten soil properties: soil organic carbon (SOC), pH (water), total nitrogen (N), available phosphorus (P), available potassium (K), cation exchange capacity (CEC), bulk density (BD), and texture (clay, silt, and sand). The results revealed noteworthy enhancements in prediction performance for more than half of the properties, although, for some of them, the improvements were negligible. The most significant improvements were obtained for pH, CEC and texture, where geological variables and a previous pH map significantly contributed to the increase in accuracy. Adding numerous points (around 25,000) to the learning dataset improved the performance of soil particle-size fractions predictions. By broadening the spectrum of covariates and better covering the feature and geographical spaces considered in soil prediction models, this research underscores the importance of implementing a more diverse range of covariates at a national scale and of densifying soil information to enlarge the feature and geographical spaces of multidimensional soil/covariates combinations. This information should be taken into account in national and continental digital soil mapping endeavours.", "keywords": ["2. Zero hunger", "Soil", "Digital soil mapping", "13. Climate action", "[SDU.STU] Sciences of the Universe [physics]/Earth Sciences", "[SDU.STU]Sciences of the Universe [physics]/Earth Sciences", "Spatial sampling", "[SDV.SA.SDS]Life Sciences [q-bio]/Agricultural sciences/Soil study", "15. Life on land", "[SDV.SA.SDS] Life Sciences [q-bio]/Agricultural sciences/Soil study", "Covariates", "Modelling", "Random forest"], "contacts": [{"organization": "Suleymanov, Azamat, Richer-De-Forges, Anne C, Saby, Nicolas P. A., Arrouays, Dominique, Martin, Manuel P, Bispo, Antonio,", "roles": ["creator"]}]}, "links": [{"href": "https://doi.org/10.1016/j.geodrs.2024.e00801"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Geoderma%20Regional", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.1016/j.geodrs.2024.e00801", "name": "item", "description": "10.1016/j.geodrs.2024.e00801", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.1016/j.geodrs.2024.e00801"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2024-06-01T00:00:00Z"}}, {"id": "10.1016/j.scitotenv.2023.168249", "type": "Feature", "geometry": null, "properties": {"updated": "2026-05-23T16:16:42Z", "type": "Journal Article", "created": "2023-10-31", "title": "An advanced global soil erodibility (K) assessment including the effects of saturated hydraulic conductivity", "description": "USLE-type models are widely used to estimate average annual soil loss at large scales, with the erodibility factor (K) being the sole component that accounts for soil's susceptibility to erosion. The factor includes the information on permeability in the equation, however, most definitions of the K factor consider the soil hydrological influence only very crudely and indirectly. Thus, the direct impact of surface runoff infiltration and drainage on soil erosion is largely neglected. The objective of this study is to incorporate soil hydraulic properties in the K factor map by merging available global-scale measured saturated hydraulic conductivity (Ksat) data with soil texture and organic carbon information into a modified K factor. To achieve this, the Wischmeier and Smith (1978) soil texture- and permeability-based equation (KWischmeier factor) was modified to include Ksat, called Kksat factor. Using the Random Forest machine learning algorithm, the KWischmeier factor and the Kksat factor were each correlated with soil and remote sensing covariates for spatial extrapolation of two independent K factor maps at 1\u00a0km spatial resolution. We noted a clear decrease in the mean value of the Kksat factor (0.023\u00a0t\u00a0ha\u00a0h\u00a0ha-1\u00a0MJ-1\u00a0mm-1) compared to the mean value of the KWischmeier factor (0.027\u00a0t\u00a0ha\u00a0h\u00a0ha-1\u00a0MJ-1\u00a0mm-1). The reduction in Kksat factor values was most pronounced in tropical regions reflecting the difference in soil properties (e.g., clay and iron), whereas other climate regions showed relatively minor changes in comparison to the KWischmeier factor as well as to the recent global modeling of Borrelli et al. (2017) (KGloSEM factor maps). As many studies discussed an overall overestimation of (R)USLE based erosion rates compared to measurements, this reduction in the K factor might improve modeled erosion rates in the right direction. The Kksat marks an important initial step in integrating hydraulic properties into the K factor of USLE-type models and can prove their significance in future studies.", "keywords": ["K factor; Random Forest; Soil hydraulic properties; Soil texture; Tropical regions; USLE", "15. Life on land", "6. Clean water"]}, "links": [{"href": "https://doi.org/10.1016/j.scitotenv.2023.168249"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Science%20of%20The%20Total%20Environment", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.1016/j.scitotenv.2023.168249", "name": "item", "description": "10.1016/j.scitotenv.2023.168249", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.1016/j.scitotenv.2023.168249"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2024-01-01T00:00:00Z"}}, {"id": "10.3390/plants11152070", "type": "Feature", "geometry": null, "properties": {"updated": "2026-05-23T16:20:47Z", "type": "Journal Article", "created": "2022-08-09", "title": "Identification of Soil Properties Associated with the Incidence of Banana Wilt Using Supervised Methods", "description": "<?xml version='1.0' encoding='UTF-8'?><article><p>Over the last few decades, a growing incidence of Banana Wilt (BW) has been detected in the banana-producing areas of the central zone of Venezuela. This disease is thought to be caused by a fungal\u2013bacterial complex, coupled with the influence of specific soil properties. However, until now, there was no consensus on the soil characteristics associated with a high incidence of BW. The objective of this study was to identify the soil properties potentially associated with BW incidence, using supervised methods. The soil samples associated with banana plant lots in Venezuela, showing low (n = 29) and high (n = 49) incidence of BW, were collected during two consecutive years (2016 and 2017). On those soils, sixteen soil variables, including the percentage of sand, silt and clay, pH, electrical conductivity, organic matter, available contents of K, Na, Mg, Ca, Mn, Fe, Zn, Cu, S and P, were determined. The Wilcoxon test identified the occurrence of significant differences in the soil variables between the two groups of BW incidence. In addition, Orthogonal Least Squares Discriminant Analysis (OPLS-DA) and the Random Forest (RF) algorithm was applied to find soil variables capable of distinguishing banana lots showing high or low BW incidence. The OPLS-DA model showed a proper fitting of the data (R2Y: 0.61, p value &lt; 0.01), and exhibited good predictive power (Q2: 0.50, p value &lt; 0.01). The analysis of the Receiver Operating Characteristics (ROC) curves by RF revealed that the combination of Zn, Fe, Ca, K, Mn and Clay was able to accurately differentiate 84.1% of the banana lots with a sensitivity of 89.80% and a specificity of 72.40%. So far, this is the first study that identifies these six soil variables as possible new indicators associated with BW incidence in soils of lacustrine origin in Venezuela.</p></article>", "keywords": ["calcium; clay; iron; machine learning; random forest; zinc", "0301 basic medicine", "2. Zero hunger", "0303 health sciences", "calcium", "Iron", "zinc", "Botany", "clay", "15. Life on land", "Article", "Zinc", "03 medical and health sciences", "iron", "machine learning", "QK1-989", "Machine learning", "Clay", "Calcium", "random forest", "Random forest"]}, "links": [{"href": "http://www.mdpi.com/2223-7747/11/15/2070/pdf"}, {"href": "https://www.mdpi.com/2223-7747/11/15/2070/pdf"}, {"href": "https://doi.org/10.3390/plants11152070"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Plants", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.3390/plants11152070", "name": "item", "description": "10.3390/plants11152070", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.3390/plants11152070"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2022-08-08T00:00:00Z"}}, {"id": "10.1016/j.still.2020.104672", "type": "Feature", "geometry": null, "properties": {"updated": "2026-05-23T16:17:07Z", "type": "Journal Article", "created": "2020-05-15", "title": "Can pedotransfer functions based on environmental variables improve soil total nutrient mapping at a regional scale?", "description": "Abstract   Numerous pedotransfer functions (PTFs) have been developed to predict the soil properties of interest from other soil properties and, less commonly, from environmental variables. However, only a few PTFs have been developed to predict soil nutrients using environmental variables and to extrapolate them to characterize spatial soil variations at a regional scale. In this study, we attempted to develop PTFs for the total nitrogen (TN), total phosphorus (TP) and total potassium (TK) concentrations in three typical pedo-climatic areas of China (Fujian Province, Jiangsu Province and Qilian Mountains) with diverse climate, terrain and soil types. A series of linear PTFs were developed to quantify the effect of terrain and climate on the predictive relations between the soil nutrients and other measured soil properties and environmental variables. In addition, digital soil mapping (DSM) based on the random forest (RF) technique was performed to test the hypothesis that the best-fit PTFs could be extrapolated, based on soil maps and environmental variables, to describe regional soil variations in the soil nutrients. The root mean square errors (RMSEs) of the best-fit PTFs for TN, TP and TK ranged from 0.21 to 0.79 g kg\u22121, 0.20 to 0.58 g kg\u22121, and 3.68 to 5.00 g kg\u22121, respectively. Different RMSEs were produced by DSM, namely 0.37-1.89 g kg\u22121, 0.19\u22120.56 g kg\u22121 and 3.79-4.83 g kg\u22121 for TN, TP and TK, respectively. PTFs provided a sound basis for database compilation if the soil properties were highly correlated. However, the extrapolation of best-fit PTFs to regional scales yielded greater errors than those produced by DSM. The comparison results reveal the limitations of PTFs and suggest that their performance could be improved by using environmental covariates or by fitting data in areas with relatively homogeneous soil landscapes. The DSM techniques may provide satisfactory alternatives to predict soil data at both regional and plot scales.", "keywords": ["Digital soil mapping", "Total phosphorus", "Total potassium", "0401 agriculture", " forestry", " and fisheries", "04 agricultural and veterinary sciences", "Total nitrogen", "15. Life on land", "Regression analysis", "01 natural sciences", "Random forest", "0105 earth and related environmental sciences"]}, "links": [{"href": "https://doi.org/10.1016/j.still.2020.104672"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Soil%20and%20Tillage%20Research", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.1016/j.still.2020.104672", "name": "item", "description": "10.1016/j.still.2020.104672", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.1016/j.still.2020.104672"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2020-08-01T00:00:00Z"}}, {"id": "10.5194/gmd-10-1945-2017", "type": "Feature", "geometry": null, "properties": {"updated": "2026-05-23T16:21:32Z", "type": "Journal Article", "created": "2017-05-17", "title": "A non-linear Granger-causality framework to investigate climate\u2013vegetation dynamics", "description": "<p>Abstract. Satellite Earth observation has led to the creation of global climate data records of many important environmental and climatic variables. These come in the form of multivariate time series with different spatial and temporal resolutions. Data of this kind provide new means to further unravel the influence of climate on vegetation dynamics. However, as advocated in this article, commonly used statistical methods are often too simplistic to represent complex climate\uffe2\uff80\uff93vegetation relationships due to linearity assumptions. Therefore, as an extension of linear Granger-causality analysis, we present a novel non-linear framework consisting of several components, such as data collection from various databases, time series decomposition techniques, feature construction methods, and predictive modelling by means of random forests. Experimental results on global data sets indicate that, with this framework, it is possible to detect non-linear patterns that are much less visible with traditional Granger-causality methods. In addition, we discuss extensive experimental results that highlight the importance of considering non-linear aspects of climate\uffe2\uff80\uff93vegetation dynamics.                     </p>", "keywords": ["QE1-996.5", "0207 environmental engineering", "TIME-SERIES", "Geology", "02 engineering and technology", "15. Life on land", "SOIL-MOISTURE", "SAMPLE TESTS", "SURFACE-TEMPERATURE", "01 natural sciences", "RANDOM FORESTS", "CARBON-DIOXIDE", "NDVI DATA", "13. Climate action", "Earth and Environmental Sciences", "PRECIPITATION", "GLOBAL TERRESTRIAL ECOSYSTEMS", "SDG 13 - Climate Action", "SATELLITE", "0105 earth and related environmental sciences"]}, "links": [{"href": "https://gmd.copernicus.org/articles/10/1945/2017/gmd-10-1945-2017.pdf"}, {"href": "https://doi.org/10.5194/gmd-10-1945-2017"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Geoscientific%20Model%20Development", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.5194/gmd-10-1945-2017", "name": "item", "description": "10.5194/gmd-10-1945-2017", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.5194/gmd-10-1945-2017"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2017-05-17T00:00:00Z"}}, {"id": "10.1038/s41598-020-60366-y", "type": "Feature", "geometry": null, "properties": {"updated": "2026-05-23T16:17:37Z", "type": "Journal Article", "created": "2020-02-25", "title": "Engineering Meteorological Features to Select Stress Tolerant Hybrids in Maize", "description": "Abstract<p>In this study we used meteorological parameters and predictive modelling interpreted by model explanation to develop stress metrics that indicate the presence of drought and heat stress at the specific environment. We started from the extreme temperature and precipitation indices, modified some of them and introduced additional drought indices relevant to the analysis. Based on maize\uffe2\uff80\uff99s sensitivity to stress, the growing season was divided into four stages. The features were calculated throughout the growing season and split in two groups, one for the drought and the other for heat stress. Generated meteorological features were combined with soil features and fed to random forest regression model for the yield prediction. Model explanation gave us the contribution of features to yield decrease, from which we estimated total amount of stress at the environments, which represents new environmental index. Using this index we ranked the environments according to the level of stress. More than 2400 hybrids were tested across the environments where they were grown and based on the yield stability they were marked as either tolerant or susceptible to heat, drought or combined heat and drought stress. Presented methodology and results were produced within the Syngenta Crop Challenge 2019.</p", "keywords": ["0301 basic medicine", "2. Zero hunger", "0303 health sciences", "Genotype", "Acclimatization", "environmental index", "15. Life on land", "maize", "Models", " Biological", "Zea mays", "Article", "Crop Production", "6. Clean water", "model explanation", "Plant Leaves", "03 medical and health sciences", "Meteorology", "13. Climate action", "drought and heat stress", "Hybridization", " Genetic", "Heat-Shock Response", "random forest regressor"]}, "links": [{"href": "https://www.nature.com/articles/s41598-020-60366-y.pdf"}, {"href": "https://doi.org/10.1038/s41598-020-60366-y"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Scientific%20Reports", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.1038/s41598-020-60366-y", "name": "item", "description": "10.1038/s41598-020-60366-y", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.1038/s41598-020-60366-y"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2020-02-25T00:00:00Z"}}, {"id": "10.5061/dryad.0cfxpnw4m", "type": "Feature", "geometry": null, "properties": {"updated": "2026-05-23T16:21:07Z", "type": "Dataset", "title": "Data from: Decipher soil organic carbon dynamics and driving forces across China using machine learning", "description": "unspecifiedPlease see the ReadMe  file.", "keywords": ["2. Zero hunger", "Driving Forces", "13. Climate action", "Machine learning", "cross validation", "FOS: Earth and related environmental sciences", "SOC", "spatiotemporal dynamics", "15. Life on land", "random forest"], "contacts": [{"organization": "Li, Huiwen, Wu, Yiping, Liu, Shuguang, Xiao, Jingfeng, Zhao, Wenzhi, Chen, Ji, Alexandrov, Georgii, Cao, Yue,", "roles": ["creator"]}]}, "links": [{"href": "https://doi.org/10.5061/dryad.0cfxpnw4m"}, {"rel": "self", "type": "application/geo+json", "title": "10.5061/dryad.0cfxpnw4m", "name": "item", "description": "10.5061/dryad.0cfxpnw4m", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.5061/dryad.0cfxpnw4m"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2022-04-23T00:00:00Z"}}, {"id": "10.3390/rs13224615", "type": "Feature", "geometry": null, "properties": {"updated": "2026-05-23T16:20:50Z", "type": "Journal Article", "created": "2021-11-17", "title": "Spatiotemporal Prediction and Mapping of Heavy Metals at Regional Scale Using Regression Methods and Landsat 7", "description": "<?xml version='1.0' encoding='UTF-8'?><article><p>Soil contamination by heavy metals is of particular concern, due to the direct negative impact on crop yield, food quality and human health. Although the conventional approach to monitor heavy metals relies on field sampling and lab analysis, the proliferation in the use of portable spectrometers has reduced the cost and time of investigation. However, discrepancies in spectral data from different spectrometers increase the modeling time and undermine the model accuracy for spatial mapping. This study, therefore, took advantage of the readily accessible Landsat 7 data to predict and map the spatiotemporal distribution of ten heavy metals (i.e., Sb, Pb, Ni, Mn, Hg, Cu, Cr, Co, Cd and As) over a 640 km2 area in Belgium. The Land Use/Cover Area Frame Survey (LUCAS) database of a region in north-eastern Belgium was used to retrieve variation in heavy metals concentrations over time and space, using the Landsat 7 imagery for four single dates in 2009, 2013, 2016 and 2020. Three regression methods, namely, partial least squares regression (PLSR), random forest (RF) and support vector machine (SVM) were used to model and predict the heavy metal concentrations for 2009. By comparing these models unbiasedly, the best model was selected for predicting and mapping the heavy metal distributions for 2013, 2016 and 2020. RF turned out to be the optimal model for 2009 with a coefficient of determination of prediction (R2P) and residual prediction deviation of prediction (RPDP) ranging from 0.62 to 0.92, and 1.23 to 2.79, respectively. The measured heavy metal distributions along the river floodplains, at the highlands and in the lowlands, were generally high, compared to their RF spatiotemporal predictions, which decreased over time. Increasing moisture contents in the floodplains adjacent to the river channels and the lowlands were the primary contributors to the reduction in the satellite reflectance spectra. However, topsoil erosion from rainfall, snowmelt as well as wind into the lowlands could have influenced the reduction in heavy metal spatiotemporal predicted values over time in the highlands. The spatiotemporal prediction maps produced for the heavy metals for the four different years revealed a good spatial similarity and consistency with the measured maps for 2009, which indicates their stability over the years.</p></article>", "keywords": ["PROVINCE", "Landsat 7", "analysis", "Science", "random forest (RF)", "MOISTURE", "01 natural sciences", "NIR SPECTROSCOPY", "spatiotemporal analysis", "AGRICULTURAL SOILS", "spatiotemporal", "0105 earth and related environmental sciences", "2. Zero hunger", "RANGE", "Q", "04 agricultural and veterinary sciences", "15. Life on land", "6. Clean water", "3. Good health", "MULTIVARIATE", "TOPSOILS", "13. Climate action", "Earth and Environmental Sciences", "soil heavy metal; Landsat 7; partial least squares regression (PLSR); random forest (RF); support vector machine (SVM); spatiotemporal analysis", "0401 agriculture", " forestry", " and fisheries", "support vector machine (SVM)", "soil heavy metal", "partial least squares regression (PLSR)"]}, "links": [{"href": "http://www.mdpi.com/2072-4292/13/22/4615/pdf"}, {"href": "https://www.mdpi.com/2072-4292/13/22/4615/pdf"}, {"href": "https://doi.org/10.3390/rs13224615"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Remote%20Sensing", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.3390/rs13224615", "name": "item", "description": "10.3390/rs13224615", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.3390/rs13224615"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2021-11-16T00:00:00Z"}}, {"id": "10.3168/jds.2019-16575", "type": "Feature", "geometry": null, "properties": {"updated": "2026-05-23T16:20:27Z", "type": "Journal Article", "created": "2019-08-22", "title": "Using machine learning to estimate herbage production and nutrient uptake on Irish dairy farms", "description": "Nutrient management on grazed grasslands is of critical importance to maintain productivity levels, as grass is the cheapest feed for ruminants and underpins these meat and milk production systems. Many attempts have been made to model the relationships between controllable (crop and soil fertility management) and noncontrollable influencing factors (weather, soil drainage) and nutrient/productivity levels. However, to the best of our knowledge not much research has been performed on modeling the interconnections between the influencing factors on one hand and nutrient uptake/herbage production on the other hand, by using data-driven modeling techniques. Our paper proposes to use predictive clustering trees (PCT) learned for building models on data from dairy farms in the Republic of Ireland. The PCT models show good accuracy in estimating herbage production and nutrient uptake. They are also interpretable and are found to embody knowledge that is in accordance with existing theoretical understanding of the task at hand. Moreover, if we combine more PCT into an ensemble of PCT (random forest of PCT), we can achieve improved accuracy of the estimates. In practical terms, the number of grazings, which is related proportionally with soil drainage class, is one of the most important factors that moderates the herbage production potential and nutrient uptake. Furthermore, we found the nutrient (N, P, and K) uptake and herbage nutrient concentration to be conservative in fields that had medium yield potential (11 t of dry matter per hectare on average), whereas nutrient uptake was more variable and potentially limiting in fields that had higher and lower herbage production. Our models also show that phosphorus is the most limiting nutrient for herbage production across the fields on these Irish dairy farms, followed by nitrogen and potassium.", "keywords": ["2. Zero hunger", "nutrient uptake", "Nutrients", "04 agricultural and veterinary sciences", "15. Life on land", "Poaceae", "Animal Feed", "Diet", "Machine Learning", "herbage production", "Dairying", "Milk", "nutrient uptake", " herbage production", " predictive clustering trees", " random forest", "predictive clustering trees", "Animals", "Lactation", "0401 agriculture", " forestry", " and fisheries", "Cattle", "Female", "Ireland", "random forest"]}, "links": [{"href": "https://doi.org/10.3168/jds.2019-16575"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Journal%20of%20Dairy%20Science", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.3168/jds.2019-16575", "name": "item", "description": "10.3168/jds.2019-16575", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.3168/jds.2019-16575"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2019-11-01T00:00:00Z"}}, {"id": "10.3390/rs16091510", "type": "Feature", "geometry": null, "properties": {"updated": "2026-05-23T16:20:50Z", "type": "Journal Article", "created": "2024-04-25", "title": "Remote Quantification of Soil Organic Carbon: Role of Topography in the Intra-Field Distribution", "description": "<?xml version='1.0' encoding='UTF-8'?><article><p>Soil organic carbon (SOC) measurements are an indicator of soil health and an important parameter for the study of land-atmosphere carbon fluxes. Field sampling provides precise measurements at the sample location but entails high costs and cannot provide detailed maps unless the sampling density is very high. Remote sensing offers the possibility to quantify SOC over large areas in a cost-effective way. As a result, numerous studies have sought to quantify SOC using Earth observation data with a focus on inter-field or regional distributions. This study took a different angle and aimed to map the spatial distribution of SOC at the intra-field scale, since this distribution provides important insights into the biophysiochemical processes involved in the retention of SOC. Instead of solely using spectral measurements to quantify SOC, topographic and spectral features act as predictor variables. The necessary data on study fields in South-East England was acquired through a detailed SOC sampling campaign, including a LiDAR survey flight. Multi-spectral Sentinel-2 data of the study fields were acquired for the exact day of the sampling campaign, and for an interval of 18 months before and after this date. Random Forest (RF) and Support Vector Regression (SVR) models were trained and tested on the spectral and topographical data of the fields to predict the observed SOC values. Five different sets of model predictors were assessed, by using independently and in combination, single and multidate spectral data, and topographical features for the SOC sampling points. Both, RF and SVR models performed best when trained on multi-temporal Sentinel-2 data together with topographic features, achieving validation root-mean-square errors (RMSEs) of 0.29% and 0.23% SOC, respectively. These RMSEs are competitive when compared with those found in the literature for similar models. The topographic wetness index (TWI) exhibited the highest permutation importance for virtually all models. Given that farming practices within each field are the same, this result suggests an important role of soil moisture in SOC retention. Contrary to findings in dryer climates or in studies encompassing larger areas, TWI was negatively related to SOC levels in the study fields, suggesting a different role of soil wetness in the SOC storage in climates characterized by excess rainfall and poorly drained soils.</p></article>", "keywords": ["2. Zero hunger", "Science", "Q", "04 agricultural and veterinary sciences", "15. Life on land", "01 natural sciences", "soil organic carbon", "topographic wetness index", "13. Climate action", "0401 agriculture", " forestry", " and fisheries", "support vector machine", "Sentinel-2", "random forest", "0105 earth and related environmental sciences"]}, "links": [{"href": "https://www.mdpi.com/2072-4292/16/9/1510/pdf"}, {"href": "https://doi.org/10.3390/rs16091510"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Remote%20Sensing", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.3390/rs16091510", "name": "item", "description": "10.3390/rs16091510", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.3390/rs16091510"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2024-04-25T00:00:00Z"}}, {"id": "10.3390/rs13163272", "type": "Feature", "geometry": null, "properties": {"updated": "2026-05-23T16:20:49Z", "type": "Journal Article", "created": "2021-08-19", "title": "UAV-Based Land Cover Classification for Hoverfly (Diptera: Syrphidae) Habitat Condition Assessment: A Case Study on Mt. Stara Planina (Serbia)", "description": "<?xml version='1.0' encoding='UTF-8'?><article><p>Habitat degradation, mostly caused by human impact, is one of the key drivers of biodiversity loss. This is a global problem, causing a decline in the number of pollinators, such as hoverflies. In the process of digitalizing ecological studies in Serbia, remote-sensing-based land cover classification has become a key component for both current and future research. Object-based land cover classification, using machine learning algorithms of very high resolution (VHR) imagery acquired by an unmanned aerial vehicle (UAV) was carried out in three different study sites on Mt. Stara Planina, Eastern Serbia. UAV land cover classified maps with seven land cover classes (trees, shrubs, meadows, road, water, agricultural land, and forest patches) were studied. Moreover, three different classification algorithms\u2014support vector machine (SVM), random forest (RF), and k-NN (k-nearest neighbors)\u2014were compared. This study shows that the random forest classifier performs better with respect to the other classifiers in all three study sites, with overall accuracy values ranging from 0.87 to 0.96. The overall results are robust to changes in labeling ground truth subsets. The obtained UAV land cover classified maps were compared with the Map of the Natural Vegetation of Europe (EPNV) and used to quantify habitat degradation and assess hoverfly species richness. It was concluded that the percentage of habitat degradation is primarily caused by anthropogenic pressure, thus affecting the richness of hoverfly species in the study sites. In order to enable research reproducibility, the datasets used in this study are made available in a public repository.</p></article>", "keywords": ["<i>Map of the Natural Vegetation of Europe</i>", "Orfeo ToolBox", "unmanned aerial vehicle; object-based image analysis; Orfeo ToolBox; QGIS; random forest; hoverfly; Map of the Natural Vegetation of Europe", "Science", "Q", "0211 other engineering and technologies", "Unmanned aerial vehicle", "02 engineering and technology", "15. Life on land", "01 natural sciences", "Object-based image analysis", "Map of the Natural Vegetation of Europe", "13. Climate action", "unmanned aerial vehicle;\u00a0object-based image analysis;\u00a0Orfeo ToolBox;\u00a0QGIS;\u00a0random forest;\u00a0hoverfly;\u00a0Map of the Natural Vegetation of Europe", "unmanned aerial vehicle", "object-based image analysis", "Hoverfly", "QGIS", "random forest", "Random forest", "hoverfly", "0105 earth and related environmental sciences"]}, "links": [{"href": "http://www.mdpi.com/2072-4292/13/16/3272/pdf"}, {"href": "https://doi.org/10.3390/rs13163272"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Remote%20Sensing", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.3390/rs13163272", "name": "item", "description": "10.3390/rs13163272", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.3390/rs13163272"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2021-08-18T00:00:00Z"}}, {"id": "2987379657", "type": "Feature", "geometry": null, "properties": {"updated": "2026-05-23T16:25:31Z", "type": "Journal Article", "created": "2019-11-07", "title": "Deriving Field Scale Soil Moisture from Satellite Observations and Ground Measurements in a Hilly Agricultural Region", "description": "<?xml version='1.0' encoding='UTF-8'?><article><p>Agricultural and hydrological applications could greatly benefit from soil moisture (SM) information at sub-field resolution and (sub-) daily revisit time. However, current operational satellite missions provide soil moisture information at either lower spatial or temporal resolution. Here, we downscale coarse resolution (25\u201336 km) satellite SM products with quasi-daily resolution to the field scale (30 m) using the random forest (RF) machine learning algorithm. RF models are trained with remotely sensed SM and ancillary variables on soil texture, topography, and vegetation cover against SM measured in the field. The approach is developed and tested in an agricultural catchment equipped with a high-density network of low-cost SM sensors. Our results show a strong consistency between the downscaled and observed SM spatio-temporal patterns. We found that topography has higher predictive power for downscaling than soil texture, due to the hilly landscape of the study area. Furthermore, including a proxy of vegetation cover results in considerable improvements of the performance. Increasing the training set size leads to significant gain in the model skill and expanding the training set is likely to further enhance the accuracy. When only limited in-situ measurements are available as training data, increasing the number of sensor locations should be favored over expanding the duration of the measurements for improved downscaling performance. In this regard, we show the potential of low-cost sensors as a practical and cost-effective solution for gathering the necessary observations. Overall, our findings highlight the suitability of using ground measurements in conjunction with machine learning to derive high spatially resolved SM maps from coarse-scale satellite products.</p></article>", "keywords": ["advanced scatterometer (ascat)", "2. Zero hunger", "soil moisture; downscaling; advanced scatterometer (ASCAT); soil moisture active passive (SMAP); random forest; low-cost sensor", "soil moisture active passive (smap)", "Science", "Q", "downscaling", "soil moisture", "15. Life on land", "01 natural sciences", "random forest", "low-cost sensor", "0105 earth and related environmental sciences"]}, "links": [{"href": "http://www.mdpi.com/2072-4292/11/22/2596/pdf"}, {"href": "https://www.mdpi.com/2072-4292/11/22/2596/pdf"}, {"href": "https://doi.org/2987379657"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Remote%20Sensing", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "2987379657", "name": "item", "description": "2987379657", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/2987379657"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2019-11-06T00:00:00Z"}}, {"id": "10.3390/rs11111350", "type": "Feature", "geometry": null, "properties": {"updated": "2026-05-23T16:20:48Z", "type": "Journal Article", "created": "2019-06-06", "title": "Spectral Response Analysis: An Indirect and Non-Destructive Methodology for the Chlorophyll Quantification of Biocrusts", "description": "<?xml version='1.0' encoding='UTF-8'?><article><p>Chlorophyll a concentration (Chla) is a well-proven proxy of biocrust development, photosynthetic organisms\u2019 status, and recovery monitoring after environmental disturbances. However, laboratory methods for the analysis of chlorophyll require destructive sampling and are expensive and time consuming. Indirect estimation of chlorophyll a by means of soil surface reflectance analysis has been demonstrated to be an accurate, cheap, and quick alternative for chlorophyll retrieval information, especially in plants. However, its application to biocrusts has yet to be harnessed. In this study we evaluated the potential of soil surface reflectance measurements for non-destructive Chla quantification over a range of biocrust types and soils. Our results revealed that from the different spectral transformation methods and techniques, the first derivative of the reflectance and the continuum removal were the most accurate for Chla retrieval. Normalized difference values in the red-edge region and common broadband indexes (e.g., normalized difference vegetation index (NDVI)) were also sensitive to changes in Chla. However, such approaches should be carefully adapted to each specific biocrust type. On the other hand, the combination of spectral measurements with non-linear random forest (RF) models provided very good fits (R2 &gt; 0.94) with a mean root mean square error (RMSE) of about 6.5 \u00b5g/g soil, and alleviated the need for a specific calibration for each crust type, opening a wide range of opportunities to advance our knowledge of biocrust responses to ongoing global change and degradation processes from anthropogenic disturbance.</p></article>", "keywords": ["chlorophyll quantification", "remote sensing", "hyperspectral", "13. Climate action", "Science", "Q", "Biocrusts; biological soil crust; chlorophyll quantification; hyperspectral; random forest; remote sensing", "0401 agriculture", " forestry", " and fisheries", "04 agricultural and veterinary sciences", "15. Life on land", "random forest", "Biocrusts", "biological soil crust"]}, "links": [{"href": "http://www.mdpi.com/2072-4292/11/11/1350/pdf"}, {"href": "https://www.mdpi.com/2072-4292/11/11/1350/pdf"}, {"href": "https://doi.org/10.3390/rs11111350"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Remote%20Sensing", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.3390/rs11111350", "name": "item", "description": "10.3390/rs11111350", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.3390/rs11111350"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2019-06-05T00:00:00Z"}}, {"id": "10.3390/rs11222596", "type": "Feature", "geometry": null, "properties": {"updated": "2026-05-23T16:20:48Z", "type": "Journal Article", "created": "2019-11-07", "title": "Deriving Field Scale Soil Moisture from Satellite Observations and Ground Measurements in a Hilly Agricultural Region", "description": "<?xml version='1.0' encoding='UTF-8'?><article><p>Agricultural and hydrological applications could greatly benefit from soil moisture (SM) information at sub-field resolution and (sub-) daily revisit time. However, current operational satellite missions provide soil moisture information at either lower spatial or temporal resolution. Here, we downscale coarse resolution (25\u201336 km) satellite SM products with quasi-daily resolution to the field scale (30 m) using the random forest (RF) machine learning algorithm. RF models are trained with remotely sensed SM and ancillary variables on soil texture, topography, and vegetation cover against SM measured in the field. The approach is developed and tested in an agricultural catchment equipped with a high-density network of low-cost SM sensors. Our results show a strong consistency between the downscaled and observed SM spatio-temporal patterns. We found that topography has higher predictive power for downscaling than soil texture, due to the hilly landscape of the study area. Furthermore, including a proxy of vegetation cover results in considerable improvements of the performance. Increasing the training set size leads to significant gain in the model skill and expanding the training set is likely to further enhance the accuracy. When only limited in-situ measurements are available as training data, increasing the number of sensor locations should be favored over expanding the duration of the measurements for improved downscaling performance. In this regard, we show the potential of low-cost sensors as a practical and cost-effective solution for gathering the necessary observations. Overall, our findings highlight the suitability of using ground measurements in conjunction with machine learning to derive high spatially resolved SM maps from coarse-scale satellite products.</p></article>", "keywords": ["advanced scatterometer (ascat)", "2. Zero hunger", "soil moisture; downscaling; advanced scatterometer (ASCAT); soil moisture active passive (SMAP); random forest; low-cost sensor", "soil moisture active passive (smap)", "Science", "Q", "downscaling", "soil moisture", "15. Life on land", "01 natural sciences", "random forest", "low-cost sensor", "0105 earth and related environmental sciences"]}, "links": [{"href": "http://www.mdpi.com/2072-4292/11/22/2596/pdf"}, {"href": "https://www.mdpi.com/2072-4292/11/22/2596/pdf"}, {"href": "https://doi.org/10.3390/rs11222596"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Remote%20Sensing", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.3390/rs11222596", "name": "item", "description": "10.3390/rs11222596", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.3390/rs11222596"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2019-11-06T00:00:00Z"}}, {"id": "10.3390/rs13163181", "type": "Feature", "geometry": null, "properties": {"updated": "2026-05-23T16:20:49Z", "type": "Journal Article", "created": "2021-08-11", "title": "Retrieving Crop Albedo Based on Radar Sentinel-1 and Random Forest Approach", "description": "<?xml version='1.0' encoding='UTF-8'?><article><p>Monitoring agricultural crops is of paramount importance for preserving water resources and increasing water efficiency over semi-arid areas. This can be achieved by modelling the water resources all along the growing season through the coupled water\u2013surface energy balance. Surface albedo is a key land surface variable to constrain the surface radiation budget and hence the coupled water\u2013surface energy balance. In order to capture the hydric status changes over the growing season, optical remote sensing becomes impractical due to cloud cover in some periods, especially over irrigated winter crops in semi-arid regions. To fill the gap, this paper aims to generate cloudless surface albedo product from Sentinel-1 data that offers a source of high spatio-temporal resolution images. This can help to better capture the vegetation development along the growth season through the surface radiation budget. Random Forest (RF) algorithm was implemented using Sentinel-1 backscatters as input. The approach was tested over an irrigated semi-arid zone in Morocco, which is known by its heterogeneity in term of soil conditions and crop types. The obtained results are evaluated against Landsat-derived albedo with quasi-concurrent Landsat/Sentinel-1 overpasses (up to one day offset), while a further validation was investigated using in situ field scale albedo data. The best model-hyperparameters selection was dependent on two validation approaches (K-fold cross-validation \u2018k = 10\u2019, and holdout). The more robust and accurate model parameters are those that represent the best statistical metrics (root mean square error \u2018RMSE\u2019, bias and correlation coefficient \u2018R\u2019). Coefficient values ranging from 0.70 to 0.79 and a RMSE value between 0.0002 and 0.00048 were obtained comparing Landsat and predicted albedo by RF method. The relative error ratio equals 4.5, which is acceptable to predict surface albedo.</p></article>", "keywords": ["[SDE] Environmental Sciences", "crop vegetation", "550", "Science", "Q", "500", "surface albedo", "04 agricultural and veterinary sciences", "15. Life on land", "01 natural sciences", "6. Clean water", "13. Climate action", "[SDE]Environmental Sciences", "Sentinel-1", "0401 agriculture", " forestry", " and fisheries", "Landsat", "random forest", "0105 earth and related environmental sciences"]}, "links": [{"href": "http://www.mdpi.com/2072-4292/13/16/3181/pdf"}, {"href": "https://www.mdpi.com/2072-4292/13/16/3181/pdf"}, {"href": "https://doi.org/10.3390/rs13163181"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Remote%20Sensing", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.3390/rs13163181", "name": "item", "description": "10.3390/rs13163181", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.3390/rs13163181"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2021-08-11T00:00:00Z"}}, {"id": "10.3390/rs13234893", "type": "Feature", "geometry": null, "properties": {"updated": "2026-05-23T16:20:50Z", "type": "Journal Article", "created": "2021-12-06", "title": "In Situ Observation-Constrained Global Surface Soil Moisture Using Random Forest Model", "description": "<p>The inherent biases of different long-term gridded surface soil moisture (SSM) products, unconstrained by the in situ observations, implies different spatio-temporal patterns. In this study, the Random Forest (RF) model was trained to predict SSM from relevant land surface feature variables (i.e., land surface temperature, vegetation indices, soil texture, and geographical information) and precipitation, based on the in situ soil moisture data of the International Soil Moisture Network (ISMN.). The results of the RF model show an RMSE of 0.05 m3 m\uffe2\uff88\uff923 and a correlation coefficient of 0.9. The calculated impurity-based feature importance indicates that the Antecedent Precipitation Index affects most of the predicted soil moisture. The geographical coordinates also significantly influence the prediction (i.e., RMSE was reduced to 0.03 m3 m\uffe2\uff88\uff923 after considering geographical coordinates), followed by land surface temperature, vegetation indices, and soil texture. The spatio-temporal pattern of RF predicted SSM was compared with the European Space Agency Climate Change Initiative (ESA-CCI) soil moisture product, using both time-longitude and latitude diagrams. The results indicate that the RF SSM captures the spatial distribution and the daily, seasonal, and annual variabilities globally.</p>", "keywords": ["feature importance", "Science", "0207 environmental engineering", "02 engineering and technology", "01 natural sciences", "antecedent precipitation index", "SDG 13 - Climate Action", "Global scale", "Antecedent precipitation index; Feature importance; Global scale; In situ constrained; Random forest; Soil moisture", "soil moisture; random forest; global scale; in situ constrained; feature importance; antecedent precipitation index", "SDG 15 - Life on Land", "0105 earth and related environmental sciences", "Antecedent precipitation index", "Q", "In situ constrained", "15. Life on land", "Feature importance", "13. Climate action", "ITC-ISI-JOURNAL-ARTICLE", "global scale", "Soil moisture", "soil moisture", "ITC-GOLD", "in situ constrained", "random forest", "Random forest"]}, "links": [{"href": "http://www.mdpi.com/2072-4292/13/23/4893/pdf"}, {"href": "https://www.iris.unina.it/bitstream/11588/938135/1/2021_Ljie_Zeng_et_al_remotesensing.pdf"}, {"href": "https://www.mdpi.com/2072-4292/13/23/4893/pdf"}, {"href": "https://doi.org/10.3390/rs13234893"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Remote%20Sensing", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.3390/rs13234893", "name": "item", "description": "10.3390/rs13234893", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.3390/rs13234893"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2021-12-02T00:00:00Z"}}, {"id": "10.3390/rs14030541", "type": "Feature", "geometry": null, "properties": {"updated": "2026-05-23T16:20:50Z", "type": "Journal Article", "created": "2022-01-24", "title": "Designing a European-Wide Crop Type Mapping Approach Based on Machine Learning Algorithms Using LUCAS Field Survey and Sentinel-2 Data", "description": "<?xml version='1.0' encoding='UTF-8'?><article><p>One of the most challenging aspects of obtaining detailed and accurate land-use and land-cover (LULC) maps is the availability of representative field data for training and validation. In this manuscript, we evaluate the use of the Eurostat Land Use and Coverage Area frame Survey (LUCAS) 2018 data to generate a detailed LULC map with 19 crop type classes and two broad categories for woodland and shrubland, and grassland. The field data were used in combination with Copernicus Sentinel-2 (S2) satellite data covering Europe. First, spatially and temporally consistent S2 image composites of (1) spectral reflectances, (2) a selection of spectral indices, and (3) several bio-geophysical indicators were created for the year 2018. From the large number of features, the most important were selected for classification using two machine-learning algorithms (support vector machine and random forest). Results indicated that the 19 crop type classes and the two broad categories could be classified with an overall accuracy (OA) of 77.6%, using independent data for validation. Our analysis of three methods to select optimum training data showed that by selecting the most spectrally different pixels for training data, the best OA could be achieved, and this already using only 11% of the total training data. Comparing our results to a similar study using Sentinel-1 (S1) data indicated that S2 can achieve slightly better results, although the spatial coverage was slightly reduced due to gaps in S2 data. Further analysis is ongoing to leverage synergies between optical and microwave data.</p></article>", "keywords": ["LUCAS 2018", "crop type classification", "crop type classification; random forest; support vector machine; LUCAS 2018", "Science", "Q", "0211 other engineering and technologies", "0401 agriculture", " forestry", " and fisheries", "support vector machine", "04 agricultural and veterinary sciences", "02 engineering and technology", "15. Life on land", "random forest"]}, "links": [{"href": "http://www.mdpi.com/2072-4292/14/3/541/pdf"}, {"href": "https://www.mdpi.com/2072-4292/14/3/541/pdf"}, {"href": "https://doi.org/10.3390/rs14030541"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Remote%20Sensing", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.3390/rs14030541", "name": "item", "description": "10.3390/rs14030541", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.3390/rs14030541"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2022-01-23T00:00:00Z"}}, {"id": "10.3390/rs14061384", "type": "Feature", "geometry": null, "properties": {"updated": "2026-05-23T16:20:50Z", "type": "Journal Article", "created": "2022-03-14", "title": "Development of Prediction Models for Estimating Key Rice Growth Variables Using Visible and NIR Images from Unmanned Aerial Systems", "description": "<?xml version='1.0' encoding='UTF-8'?><article><p>The rapid and accurate acquisition of rice growth variables using unmanned aerial system (UAS) is useful for assessing rice growth and variable fertilization in precision agriculture. In this study, rice plant height (PH), leaf area index (LAI), aboveground biomass (AGB), and nitrogen nutrient index (NNI) were obtained for different growth periods in field experiments with different nitrogen (N) treatments from 2019\u20132020. Known spectral indices derived from the visible and NIR images and key rice growth variables measured in the field at different growth periods were used to build a prediction model using the random forest (RF) algorithm. The results showed that the different N fertilizer applications resulted in significant differences in rice growth variables; the correlation coefficients of PH and LAI with visible-near infrared (V-NIR) images at different growth periods were larger than those with visible (V) images while the reverse was true for AGB and NNI. RF models for estimating key rice growth variables were established using V-NIR images and V images, and the results were validated with an R2 value greater than 0.8 for all growth stages. The accuracy of the RF model established from V images was slightly higher than that established from V-NIR images. The RF models were further tested using V images from 2019: R2 values of 0.75, 0.75, 0.72, and 0.68 and RMSE values of 11.68, 1.58, 3.74, and 0.13 were achieved for PH, LAI, AGB, and NNI, respectively, demonstrating that RGB UAS achieved the same performance as multispectral UAS for monitoring rice growth.</p></article>", "keywords": ["2. Zero hunger", "digital imagery", "rice growth variables; unmanned aerial system; multispectral imagery; digital imagery; random forest model", "Science", "random forest model", "Q", "0401 agriculture", " forestry", " and fisheries", "rice growth variables", "04 agricultural and veterinary sciences", "15. Life on land", "multispectral imagery", "unmanned aerial system"], "contacts": [{"organization": "Zhengchao Qiu, Fei Ma, Zhenwang Li, Xuebin Xu, Changwen Du,", "roles": ["creator"]}]}, "links": [{"href": "http://www.mdpi.com/2072-4292/14/6/1384/pdf"}, {"href": "https://doi.org/10.3390/rs14061384"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Remote%20Sensing", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.3390/rs14061384", "name": "item", "description": "10.3390/rs14061384", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.3390/rs14061384"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2022-03-13T00:00:00Z"}}, {"id": "10.3389/fmicb.2019.02904", "type": "Feature", "geometry": null, "properties": {"updated": "2026-05-23T16:20:31Z", "type": "Journal Article", "created": "2020-01-09", "title": "Fungal Traits Important for Soil Aggregation", "description": "Soil structure, the complex arrangement of soil into aggregates and pore spaces, is a key feature of soils and soil biota. Among them, filamentous saprobic fungi have well-documented effects on soil aggregation. However, it is unclear what properties, or traits, determine the overall positive effect of fungi on soil aggregation. To achieve progress, it would be helpful to systematically investigate a broad suite of fungal species for their trait expression and the relation of these traits to soil aggregation. Here, we apply a trait-based approach to a set of 15 traits measured under standardized conditions on 31 fungal strains including Ascomycota, Basidiomycota, and Mucoromycota, all isolated from the same soil. We find large differences among these fungi in their ability to aggregate soil, including neutral to positive effects, and we document large differences in trait expression among strains. We identify biomass density, i.e., the density with which a mycelium grows (positive effects), leucine aminopeptidase activity (negative effects) and phylogeny as important factors explaining differences in soil aggregate formation (SAF) among fungal strains; importantly, growth rate was not among the important traits. Our results point to a typical suite of traits characterizing fungi that are good soil aggregators, and our findings illustrate the power of employing a trait-based approach to unravel biological mechanisms underpinning soil aggregation. Such an approach could now be extended also to other soil biota groups. In an applied context of restoration and agriculture, such trait information can inform management, for example to prioritize practices that favor the expression of more desirable fungal traits.", "keywords": ["saprobic fungi", "0301 basic medicine", "2. Zero hunger", "ddc:500", "570", "0303 health sciences", "Saprobic fungi", "500 Naturwissenschaften und Mathematik::570 Biowissenschaften; Biologie::570 Biowissenschaften; Biologie", "15. Life on land", "Traits", "leucine amino peptidases", "Microbiology", "QR1-502", "soil aggregation", "03 medical and health sciences", "traits", "biomass density", "Soil aggregation", "Biomass density", "Leucine amino peptidases", "Institut f\u00fcr Biochemie und Biologie", "random forest", "Random forest"]}, "links": [{"href": "https://doi.org/10.3389/fmicb.2019.02904"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Frontiers%20in%20Microbiology", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.3389/fmicb.2019.02904", "name": "item", "description": "10.3389/fmicb.2019.02904", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.3389/fmicb.2019.02904"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2020-01-09T00:00:00Z"}}, {"id": "10.3390/f12070902", "type": "Feature", "geometry": null, "properties": {"updated": "2026-05-23T16:20:40Z", "type": "Journal Article", "created": "2021-07-12", "title": "Aboveground Biomass Estimation in Short Rotation Forest Plantations in Northern Greece Using ESA\u2019s Sentinel Medium-High Resolution Multispectral and Radar Imaging Missions", "description": "<p>Plantations of fast-growing forest species such as black locust (Robinia Pseudoacacia) can contribute to energy transformation, mitigate industrial pollution, and restore degraded, marginal land. In this study, the synergistic use of Sentinel-2 and Sentinel-1 time series data is explored for modeling aboveground biomass (AGB) in black locust short-rotation plantations in northeastern Greece. Optimal modeling dates and EO sensor data are also identified through the analysis. Random forest (RF) models were originally developed using monthly Sentinel-2 spectral indices, while, progressively, monthly Sentinel-1 bands were incorporated in the statistical analysis. The highest accuracy was observed for the models generated using Sentinel-2 August composites (R2 = 0.52). The inclusion of Sentinel-1 bands in the spectral indices\uffe2\uff80\uff99 models had a negligible effect on modeling accuracy during the leaf-on period. The correlation and comparative performance of the spectral indices in terms of pairwise correlation with AGB varied among the phenophases of the forest plantations. Overall, the field-measured AGB in the forest plantations plots presented a higher correlation with the optical Sentinel-2 images. The synergy of Sentinel-1 and Sentinel-2 data proved to be a non-efficient approach for improving forest biomass RF models throughout the year within the geographical and environmental context of our study.</p>", "keywords": ["random forests", "13. Climate action", "optical", "AGB", "0211 other engineering and technologies", "spectral indices", "0401 agriculture", " forestry", " and fisheries", "04 agricultural and veterinary sciences", "02 engineering and technology", "seasonal", "15. Life on land", "optical", " SAR", " spectral indices", " AGB", " seasonal", " random forests", "SAR"]}, "links": [{"href": "http://www.mdpi.com/1999-4907/12/7/902/pdf"}, {"href": "https://www.mdpi.com/1999-4907/12/7/902/pdf"}, {"href": "https://doi.org/10.3390/f12070902"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Forests", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.3390/f12070902", "name": "item", "description": "10.3390/f12070902", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.3390/f12070902"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2021-07-11T00:00:00Z"}}, {"id": "10.3390/rs11080913", "type": "Feature", "geometry": null, "properties": {"updated": "2026-05-23T16:20:48Z", "type": "Journal Article", "created": "2019-04-15", "title": "Multispectral Contrast of Archaeological Features: A Quantitative Evaluation", "description": "<p>This study provides an evaluation of spectral responses of hollow ways in Upper Mesopotamia. Hollow ways were used for the transportation of animals, carts, and other moving agents for centuries. The aim is to show how the success of spectral indices varies in describing topologically simple features even in a seemingly homogeneous geographic unit. The variation is further highlighted under the changing precipitation regime. The methodology begins with an exploration of the relationship between the date of a multispectral scene and the visibility of hollow ways. The next step is to evaluate the impact of rainfall levels on numerous indices and to quantify spectral contrast. The contrast between a hollow way and its background is evaluated with Welch\uffe2\uff80\uff99s t-test and the association between precipitation regime and spectral responses of hollow ways are investigated with Correspondence Analysis and Fisher\uffe2\uff80\uff99s test. Results highlight an intrinsic relationship between the precipitation regime and the ways in which archaeological features reflects and/or emits electromagnetic energy. Next, the categorization of spectral indices based on different rainfall levels can be used as a guidance in future studies. Finally, the study suggests contrast becomes an even more fruitful concept as one moves from the spatial domain to the spectral domain.</p>", "keywords": ["Random Forests", "Lidar", "satellite remote sensing", "Science", "Q", "0211 other engineering and technologies", "Effectiveness of data fusion", "06 humanities and the arts", "02 engineering and technology", "Data fusion", "910", "15. Life on land", "archaeology of roads", "precipitation regime", "Imaging spectroscopy", "Precipitation regime", "spectral contrast", "Hollow ways", "Natura 2000 habitat", "13. Climate action", "Satellite remote sensing", "Upper Mesopotamia", "0601 history and archaeology", "Spectral contrast", "hollow ways"]}, "links": [{"href": "http://www.mdpi.com/2072-4292/11/8/913/pdf"}, {"href": "https://iris.cnr.it/bitstream/20.500.14243/390208/1/prod_402195-doc_199283.pdf"}, {"href": "http://dro.dur.ac.uk/27994/1/27994.pdf"}, {"href": "http://dro.dur.ac.uk/27994/2/27994.pdf"}, {"href": "https://www.mdpi.com/2072-4292/11/8/913/pdf"}, {"href": "https://doi.org/10.3390/rs11080913"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Remote%20Sensing", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.3390/rs11080913", "name": "item", "description": "10.3390/rs11080913", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.3390/rs11080913"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2019-04-15T00:00:00Z"}}, {"id": "10.3390/land10010063", "type": "Feature", "geometry": null, "properties": {"updated": "2026-05-23T16:20:43Z", "type": "Journal Article", "created": "2021-01-13", "title": "Evaluation of a Micro-Electro Mechanical Systems Spectral Sensor for Soil Properties Estimation", "description": "<p>Soil properties estimation with the use of reflectance spectroscopy has met major advances over the last decades. Their non-destructive nature and their high accuracy capacity enabled a breakthrough in the efficiency of performing soil analysis against conventional laboratory techniques. As the need for rapid, low cost, and accurate soil properties\uffe2\uff80\uff99 estimations increases, micro electro mechanical systems (MEMS) have been introduced and are becoming applicable for informed decision making in various domains. This work presents the assessment of a MEMS sensor (1750\uffe2\uff80\uff932150 nm) in estimating clay and soil organic carbon (SOC) contents. The sensor was first tested under various experimental setups (different working distances and light intensities) through its similarity assessment (Spectral Angle Mapper) to the measurements of a spectroradiometer of the full 350\uffe2\uff80\uff932500 nm range that was used as reference. MEMS performance was evaluated over spectra measured from 102 samples in laboratory conditions. Models\uffe2\uff80\uff99 calibrations were performed using random forest (RF) and partial least squares regression (PLSR). The results provide insights that MEMS could be employed for soil properties estimation, since the RF model demonstrated solid performance over both clay (R2 = 0.85) and SOC (R2 = 0.80). These findings pave the way for supporting daily agriculture applications and land related policies through the exploration of a wider set of soil properties.</p>", "keywords": ["2. Zero hunger", "S", "Agriculture", "clay", "NIR", "04 agricultural and veterinary sciences", "15. Life on land", "SWIR", "soil organic carbon", "MEMS", "machine learning", "clay; soil organic carbon; MEMS; soil spectroscopy; NIR; random forest; machine learning; SWIR", "0401 agriculture", " forestry", " and fisheries", "random forest", "soil spectroscopy"]}, "links": [{"href": "http://www.mdpi.com/2073-445X/10/1/63/pdf"}, {"href": "https://www.mdpi.com/2073-445X/10/1/63/pdf"}, {"href": "https://doi.org/10.3390/land10010063"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Land", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.3390/land10010063", "name": "item", "description": "10.3390/land10010063", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.3390/land10010063"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2021-01-13T00:00:00Z"}}, {"id": "10.3390/land11050651", "type": "Feature", "geometry": null, "properties": {"updated": "2026-05-23T16:20:43Z", "type": "Journal Article", "created": "2022-04-29", "title": "Anthropogenic and Lightning Fire Incidence and Burned Area in Europe", "description": "<?xml version='1.0' encoding='UTF-8'?><article><p>Fires can have an anthropogenic or natural origin. The most frequent natural fire cause is lightning. Since anthropogenic and lightning fires have different climatic and socio-economic drivers, it is important to distinguish between these different fire causes. We developed random forest models that predict the fraction of anthropogenic and lightning fire incidences, and their burned area, at the level of the Nomenclature des Unit\u00e9s Territoriales Statistiques level 3 (NUTS3) for Europe. The models were calibrated using the centered log-ratio of fire incidence and burned area reference data from the European Forest Fire Information System. After a correlation analysis, the population density, fractional human land impact, elevation and burned area coefficient of variation\u2014a measure of interannual variability in burned area\u2014were selected as predictor variables in the models. After parameter tuning and running the models with several train-validate compositions, we found that the vast majority of fires and burned area in Europe has an anthropogenic cause, while lightning plays a significant role in the remote northern regions of Scandinavia. Combining our results with burned area data from the Moderate Resolution Imaging Spectroradiometer, we estimated that 96.5 \u00b1 0.9% of the burned area in Europe has an anthropogenic cause. Our spatially explicit fire cause attribution model demonstrates the spatial variability between anthropogenic and lightning fires and their burned area over Europe and could be used to improve predictive fire models by accounting for fire cause.</p></article>", "keywords": ["Europe", "S", "13. Climate action", "random forest model", "11. Sustainability", "ignition", "fire cause; burned area; ignition; random forest model; Europe", "Agriculture", "15. Life on land", "01 natural sciences", "burned area", "fire cause", "0105 earth and related environmental sciences"]}, "links": [{"href": "http://www.mdpi.com/2073-445X/11/5/651/pdf"}, {"href": "https://www.mdpi.com/2073-445X/11/5/651/pdf"}, {"href": "https://doi.org/10.3390/land11050651"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Land", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.3390/land11050651", "name": "item", "description": "10.3390/land11050651", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.3390/land11050651"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2022-04-28T00:00:00Z"}}, {"id": "10.5281/zenodo.8091863", "type": "Feature", "geometry": null, "properties": {"updated": "2026-05-23T16:23:23Z", "type": "Journal Article", "created": "2022-01-23", "title": "Designing a European-Wide Crop Type Mapping Approach Based on Machine Learning Algorithms Using LUCAS Field Survey and Sentinel-2 Data", "description": "<?xml version='1.0' encoding='UTF-8'?><article><p>One of the most challenging aspects of obtaining detailed and accurate land-use and land-cover (LULC) maps is the availability of representative field data for training and validation. In this manuscript, we evaluate the use of the Eurostat Land Use and Coverage Area frame Survey (LUCAS) 2018 data to generate a detailed LULC map with 19 crop type classes and two broad categories for woodland and shrubland, and grassland. The field data were used in combination with Copernicus Sentinel-2 (S2) satellite data covering Europe. First, spatially and temporally consistent S2 image composites of (1) spectral reflectances, (2) a selection of spectral indices, and (3) several bio-geophysical indicators were created for the year 2018. From the large number of features, the most important were selected for classification using two machine-learning algorithms (support vector machine and random forest). Results indicated that the 19 crop type classes and the two broad categories could be classified with an overall accuracy (OA) of 77.6%, using independent data for validation. Our analysis of three methods to select optimum training data showed that by selecting the most spectrally different pixels for training data, the best OA could be achieved, and this already using only 11% of the total training data. Comparing our results to a similar study using Sentinel-1 (S1) data indicated that S2 can achieve slightly better results, although the spatial coverage was slightly reduced due to gaps in S2 data. Further analysis is ongoing to leverage synergies between optical and microwave data.</p></article>", "keywords": ["LUCAS 2018", "crop type classification", "crop type classification; random forest; support vector machine; LUCAS 2018", "Science", "Q", "0211 other engineering and technologies", "0401 agriculture", " forestry", " and fisheries", "support vector machine", "04 agricultural and veterinary sciences", "02 engineering and technology", "15. Life on land", "random forest"]}, "links": [{"href": "http://www.mdpi.com/2072-4292/14/3/541/pdf"}, {"href": "https://www.mdpi.com/2072-4292/14/3/541/pdf"}, {"href": "https://doi.org/10.5281/zenodo.8091863"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Remote%20Sensing", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.5281/zenodo.8091863", "name": "item", "description": "10.5281/zenodo.8091863", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.5281/zenodo.8091863"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2022-01-23T00:00:00Z"}}, {"id": "10.3390/w14081188", "type": "Feature", "geometry": null, "properties": {"updated": "2026-05-23T16:20:54Z", "type": "Journal Article", "created": "2022-04-10", "title": "Estimating Yield from NDVI, Weather Data, and Soil Water Depletion for Sugar Beet and Potato in Northern Belgium", "description": "<?xml version='1.0' encoding='UTF-8'?><article><p>Crop-yield models based on vegetation indices such as the normalized difference vegetation index (NDVI) have been developed to monitor crop yield at higher spatial and temporal resolutions compared to agricultural statistical data. We evaluated the model performance of NDVI-based random forest models for sugar beet and potato farm yields in northern Belgium during 2016\u20132018. We also evaluated whether weather variables and root-zone soil water depletion during the growing season improved the model performance. The NDVI integral did not explain early and late potato yield variability and only partly explained sugar-beet yield variability. The NDVI series of early and late potato crops were not sensitive enough to yield affecting weather and soil water conditions. We found that water-saturated conditions early in the growing season and elevated temperatures late in the growing season explained a large part of the sugar-beet and late-potato yield variability. The NDVI integral in combination with monthly precipitation, maximum temperature, and root-zone soil water depletion during the growing season explained farm-scale sugar beet (R2 = 0.84, MSE = 48.8) and late potato (R2 = 0.56, MSE = 57.3) yield variability well from 2016 to 2018 in northern Belgium.</p></article>", "keywords": ["AquaCrop-OSPy", "STRESS", "root-zone soil water depletion; AquaCrop-OSPy; sugar beet; potato; crop yield; NDVI; Belgium; weather impact; random forest", "NDVI", "Environmental Sciences & Ecology", "root-zone soil water depletion", "01 natural sciences", "Belgium", "INDEX", "0105 earth and related environmental sciences", "2. Zero hunger", "Science & Technology", "PRODUCTIVITY", "CROP", "sugar beet", "weather impact", "04 agricultural and veterinary sciences", "crop yield", "WINTER-WHEAT", "15. Life on land", "MODEL", "Physical Sciences", "Water Resources", "potato", "0401 agriculture", " forestry", " and fisheries", "Life Sciences & Biomedicine", "Environmental Sciences", "random forest"]}, "links": [{"href": "http://www.mdpi.com/2073-4441/14/8/1188/pdf"}, {"href": "https://www.mdpi.com/2073-4441/14/8/1188/pdf"}, {"href": "https://doi.org/10.3390/w14081188"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Water", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.3390/w14081188", "name": "item", "description": "10.3390/w14081188", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.3390/w14081188"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2022-04-08T00:00:00Z"}}, {"id": "10.5194/isprs-archives-XLIII-B2-2020-659-2020", "type": "Feature", "geometry": null, "properties": {"updated": "2026-05-23T16:21:35Z", "type": "Journal Article", "created": "2020-08-12", "title": "CLASSIFICATION OF UAV-BASED PHOTOGRAMMETRIC POINT CLOUDS OF RIVERINE SPECIES USING MACHINE LEARNING ALGORITHMS: A CASE STUDY IN THE PALANCIA RIVER, SPAIN", "description": "<p>Abstract. The management of riverine areas is fundamental due to their great environmental importance. The fast changes that occur in these areas due to river mechanics and human pressure makes it necessary to obtain data with high temporal and spatial resolution. This study proposes a workflow to map riverine species using Unmanned Aerial Vehicle (UAV) imagery. Based on RGB point clouds, our work derived simple geometric and spectral metrics to classify an area of the public hydraulic domain of the river Palancia (Spain) in five different classes: Tamarix gallica L. (French tamarisk), Pinus halepensis Miller (Aleppo pine), Arundo donax L. (giant reed), other riverine species and ground. A total of six Machine Learning (ML) methods were evaluated: Decision Trees, Extra Trees, Multilayer Perceptron, K-Nearest Neighbors, Random Forest and Ridge. The method chosen to carry out the classification was Random Forest, which obtained a mean score cross-validation close to 0.8. Subsequently, an object-based reclassification was done to improve this result, obtaining an overall accuracy of 83.6%, and individually a producer\uffe2\uff80\uff99s accuracy of 73.8% for giant reed, 87.7% for Aleppo pine, 82.8% for French tamarisk, 93.5% for ground and 80.1% for other riverine species. Results were promising, proving the feasibility of using this cost-effective method for periodic monitoring of riverine species. In addition, the proposed workflow is easily transferable to other tasks beyond riverine species classification (e.g., green areas detection, land cover classification) opening new opportunities in the use of UAVs equipped with consumer cameras for environmental applications.                     </p>", "keywords": ["Technology", "Point cloud classification", " UAV", " Structure from Motion", " Random forest", " Riverine species", "T", "UAV", "0211 other engineering and technologies", "02 engineering and technology", "15. Life on land", "Engineering (General). Civil engineering (General)", "01 natural sciences", "Structure from Motion", "TA1501-1820", "13. Climate action", "INGENIERIA CARTOGRAFICA", " GEODESIA Y FOTOGRAMETRIA", "Applied optics. Photonics", "Riverine species", "TA1-2040", "Point cloud classification", "Random forest", "0105 earth and related environmental sciences"]}, "links": [{"href": "https://isprs-archives.copernicus.org/articles/XLIII-B2-2020/659/2020/isprs-archives-XLIII-B2-2020-659-2020.pdf"}, {"href": "https://doi.org/10.5194/isprs-archives-XLIII-B2-2020-659-2020"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/The%20International%20Archives%20of%20the%20Photogrammetry%2C%20Remote%20Sensing%20and%20Spatial%20Information%20Sciences", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.5194/isprs-archives-XLIII-B2-2020-659-2020", "name": "item", "description": "10.5194/isprs-archives-XLIII-B2-2020-659-2020", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.5194/isprs-archives-XLIII-B2-2020-659-2020"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2020-08-12T00:00:00Z"}}, {"id": "10.5281/zenodo.14012785", "type": "Feature", "geometry": null, "properties": {"updated": "2026-05-23T16:22:09Z", "type": "Dataset", "title": "SERENA EJPSOIL IT TUS SOC Loss SOC", "description": "Open AccessThe data are derived from the calculation of indicators based on a standard methodology established as\u00a0part of the EJP Soil SERENA\u00a0programme. Please keep in mind that:       It is the result of a modelling exercise and does not necessarily reflect reality.     Despite the efforts made to provide reliable data, the results\u00a0may contain inconsistencies,\u00a0depending\u00a0in particular on\u00a0the raw data\u00a0available\u00a0and level of accuracy of the techniques chosen\u00a0and\u00a0their prior knowledge\u00a0.     It is necessary to consider how the results have been obtained\u00a0in order to\u00a0decide on their\u00a0relevance\u00a0in relation to the intended\u00a0purpose\u00a0of reuse.     These results are interesting from a scientific point of view, but their use\u00a0for environmental\u00a0management and policy issues should be done keeping the previous aspects in mind and\u00a0complementing when\u00a0necessary\u00a0the provided results with the best available data.      ==> Finally, it is the responsibility of the users of this information to decide whether it is appropriate to use these data and whether the data meet their needs. The authors of this resource can in no way be held responsible for the results obtained from the use of this data.", "keywords": ["EJP Soil", "Random Forest", "Italy", "Tuscany", "Soil Organic Carbon (SOC)", "SOC loss", "Topsoil", "SERENA", "Grant n 862695", "Digital Soil Mapping"]}, "links": [{"href": "https://doi.org/10.5281/zenodo.14012785"}, {"rel": "self", "type": "application/geo+json", "title": "10.5281/zenodo.14012785", "name": "item", "description": "10.5281/zenodo.14012785", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.5281/zenodo.14012785"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2024-10-31T00:00:00Z"}}, {"id": "10261/278582", "type": "Feature", "geometry": null, "properties": {"updated": "2026-05-24T16:23:48Z", "type": "Journal Article", "created": "2022-08-09", "title": "Identification of Soil Properties Associated with the Incidence of Banana Wilt Using Supervised Methods", "description": "<?xml version='1.0' encoding='UTF-8'?><article><p>Over the last few decades, a growing incidence of Banana Wilt (BW) has been detected in the banana-producing areas of the central zone of Venezuela. This disease is thought to be caused by a fungal\u2013bacterial complex, coupled with the influence of specific soil properties. However, until now, there was no consensus on the soil characteristics associated with a high incidence of BW. The objective of this study was to identify the soil properties potentially associated with BW incidence, using supervised methods. The soil samples associated with banana plant lots in Venezuela, showing low (n = 29) and high (n = 49) incidence of BW, were collected during two consecutive years (2016 and 2017). On those soils, sixteen soil variables, including the percentage of sand, silt and clay, pH, electrical conductivity, organic matter, available contents of K, Na, Mg, Ca, Mn, Fe, Zn, Cu, S and P, were determined. The Wilcoxon test identified the occurrence of significant differences in the soil variables between the two groups of BW incidence. In addition, Orthogonal Least Squares Discriminant Analysis (OPLS-DA) and the Random Forest (RF) algorithm was applied to find soil variables capable of distinguishing banana lots showing high or low BW incidence. The OPLS-DA model showed a proper fitting of the data (R2Y: 0.61, p value &lt; 0.01), and exhibited good predictive power (Q2: 0.50, p value &lt; 0.01). The analysis of the Receiver Operating Characteristics (ROC) curves by RF revealed that the combination of Zn, Fe, Ca, K, Mn and Clay was able to accurately differentiate 84.1% of the banana lots with a sensitivity of 89.80% and a specificity of 72.40%. So far, this is the first study that identifies these six soil variables as possible new indicators associated with BW incidence in soils of lacustrine origin in Venezuela.</p></article>", "keywords": ["calcium; clay; iron; machine learning; random forest; zinc", "0301 basic medicine", "2. Zero hunger", "0303 health sciences", "calcium", "Iron", "zinc", "Botany", "clay", "15. Life on land", "Article", "Zinc", "03 medical and health sciences", "iron", "machine learning", "QK1-989", "Machine learning", "Clay", "Calcium", "random forest", "Random forest"]}, "links": [{"href": "http://www.mdpi.com/2223-7747/11/15/2070/pdf"}, {"href": "https://www.mdpi.com/2223-7747/11/15/2070/pdf"}, {"href": "https://doi.org/10261/278582"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Plants", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10261/278582", "name": "item", "description": "10261/278582", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10261/278582"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2022-08-08T00:00:00Z"}}, {"id": "1871.1/505fa0c0-6587-48f4-a8b1-4f1ad19d6bb8", "type": "Feature", "geometry": null, "properties": {"updated": "2026-05-23T16:24:50Z", "type": "Journal Article", "created": "2022-11-10", "title": "Forest foliage fuel load estimation from multi-sensor spatiotemporal features", "description": "Foliage fuel is the most flammable component in crown fires. Spatiotemporal dynamics of foliage fuel load (FFL) are important for fire managers to assess fire risk. Here, we integrated optical data from the Landsat 8 Operational Land Imager (OLI) with synthetic aperture radar (SAR) data from Sentinel-1 to estimate FFL. We first reconstructed seamless time series from the Landsat 8 and Sentinel-1 imagery by accounting for unequal time intervals between image observations and outliers. We then extracted temporal features that are proxies of the intra- and inter-annual dynamics from these time series. In addition, we derived spatial features from the imagery that quantify spatial context and therefore used varying window sizes. The random forest regression was implemented to assess the importance of the spatiotemporal features, reduce errors, and derive robust FFL estimates. The satellite estimates were validated against 96 field measurements from Pinus yunnanensis forests in the Liangshan Yi Autonomous Prefecture, Sichuan Province, China. Both the spatiotemporal features of SAR and optical data importantly contributed to FFL estimation. When only optical data was used, the model achieved a R2 of 0.75 (relative Root Mean Squared Error (rRMSE)\u00a0=\u00a025.3\u00a0%), while when only SAR data was used the R2 was 0.76 (rRMSE\u00a0=\u00a025.6\u00a0%). However, when optical and SAR data were combined, the R2 increased to 0.81 (rRMSE\u00a0=\u00a023.2\u00a0%). We also found that temporal features were more important predictors of FFL than features that captured spatial context. We demonstrated our FFL mapping method by a case study in the Chinese Sichuan Province, in relation to the occurrence of a fire. Our method needs additional validation over different tree species and forest types, yet has potential for mapping forest fuel loads and fire risk.", "keywords": ["Landsat 8", "Physical geography", "04 agricultural and veterinary sciences", "15. Life on land", "Fire risk", "01 natural sciences", "GB3-5030", "Spatiotemporal features", "Environmental sciences", "Forest foliage fuel load", "Sentinel-1", "0401 agriculture", " forestry", " and fisheries", "GE1-350", "SDG 14 - Life Below Water", "Random forest", "0105 earth and related environmental sciences"]}, "links": [{"href": "https://doi.org/1871.1/505fa0c0-6587-48f4-a8b1-4f1ad19d6bb8"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/International%20Journal%20of%20Applied%20Earth%20Observation%20and%20Geoinformation", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "1871.1/505fa0c0-6587-48f4-a8b1-4f1ad19d6bb8", "name": "item", "description": "1871.1/505fa0c0-6587-48f4-a8b1-4f1ad19d6bb8", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/1871.1/505fa0c0-6587-48f4-a8b1-4f1ad19d6bb8"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2022-12-01T00:00:00Z"}}, {"id": "10.5281/zenodo.5597222", "type": "Feature", "geometry": null, "properties": {"updated": "2026-05-23T16:23:05Z", "type": "Report", "title": "Accuracy assessment of early- and late-season crop classification using optical and SAR imagery", "description": "<em>Reliable early-season crop classification provides necessary input for storage planning, logistics optimization, sales forecasting and setting adequate government policies. The objective of this research was to evaluate crop classification models at different points in time using SAR (Synthetic Aperture Radar) and optical satellite images. SAR and optical images used in the study came from ESA's Sentinel-1 and Sentinel-2 satellites, respectively. A total of 7 cloud-free Sentinel-2 and 50 Sentinel-1 images were used to obtain the time-series necessary for seasonal crop classification. For the classifier training purpose ground truth was collected through the conducted data collection campaign, which consisted of information about the location and crop type for over 1400 parcels of 5 most important crops on the plains of Vojvodina in northern Serbia, where the study was conducted. These are: maize, wheat, soybeans, sugar beet and sunflower, which represented labels for classification. Pixel-based Random Forest (RF) algorithm proved to be a very good solution for the classification problem of the large scale datasets. The final labeled dataset was used for training and testing of RF classifier in different classification scenarios. Early-season crop classification was performed at the end of May, when the crops of interest reached the desired growth stage, while the late-season crop classification was performed at the end of August. Fusion of SAR and optical images gave the overall accuracy of 75.93% for early-season crop classification, while the late-season crop classification accuracy was 89.75%. Using individual sources, accuracies were 68.23% and 75.29%, for SAR and optical images, while the late-season accuracies were 88.37% and 88.88%, respectively. In order to achieve more accurate classification results, various vegetation indices can be integrated in further research.</em>", "keywords": ["2. Zero hunger", "Classification", " Random Forest", " Sentinel-1", " Sentinel-2", "15. Life on land"], "contacts": [{"organization": "Branislav Pejak, Milos Pandzic, Predrag Lugonja, Oskar Marko,", "roles": ["creator"]}]}, "links": [{"href": "https://doi.org/10.5281/zenodo.5597222"}, {"rel": "self", "type": "application/geo+json", "title": "10.5281/zenodo.5597222", "name": "item", "description": "10.5281/zenodo.5597222", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.5281/zenodo.5597222"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2019-03-21T00:00:00Z"}}, {"id": "10.5281/zenodo.5597223", "type": "Feature", "geometry": null, "properties": {"license": "Open Access", "updated": "2026-05-24T16:22:41Z", "type": "Report", "title": "Accuracy assessment of early- and late-season crop classification using optical and SAR imagery", "description": "<em>Reliable early-season crop classification provides necessary input for storage planning, logistics optimization, sales forecasting and setting adequate government policies. The objective of this research was to evaluate crop classification models at different points in time using SAR (Synthetic Aperture Radar) and optical satellite images. SAR and optical images used in the study came from ESA's Sentinel-1 and Sentinel-2 satellites, respectively. A total of 7 cloud-free Sentinel-2 and 50 Sentinel-1 images were used to obtain the time-series necessary for seasonal crop classification. For the classifier training purpose ground truth was collected through the conducted data collection campaign, which consisted of information about the location and crop type for over 1400 parcels of 5 most important crops on the plains of Vojvodina in northern Serbia, where the study was conducted. These are: maize, wheat, soybeans, sugar beet and sunflower, which represented labels for classification. Pixel-based Random Forest (RF) algorithm proved to be a very good solution for the classification problem of the large scale datasets. The final labeled dataset was used for training and testing of RF classifier in different classification scenarios. Early-season crop classification was performed at the end of May, when the crops of interest reached the desired growth stage, while the late-season crop classification was performed at the end of August. Fusion of SAR and optical images gave the overall accuracy of 75.93% for early-season crop classification, while the late-season crop classification accuracy was 89.75%. Using individual sources, accuracies were 68.23% and 75.29%, for SAR and optical images, while the late-season accuracies were 88.37% and 88.88%, respectively. In order to achieve more accurate classification results, various vegetation indices can be integrated in further research.</em>", "keywords": ["2. Zero hunger", "Classification", " Random Forest", " Sentinel-1", " Sentinel-2", "15. Life on land"], "contacts": [{"organization": "Pejak, Branislav, Pandzic, Milos, Lugonja, Predrag, Marko, Oskar,", "roles": ["creator"]}]}, "links": [{"href": "https://doi.org/10.5281/zenodo.5597223"}, {"rel": "self", "type": "application/geo+json", "title": "10.5281/zenodo.5597223", "name": "item", "description": "10.5281/zenodo.5597223", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.5281/zenodo.5597223"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2019-03-21T00:00:00Z"}}, {"id": "10.5281/zenodo.5770286", "type": "Feature", "geometry": null, "properties": {"updated": "2026-05-23T16:23:06Z", "type": "Journal Article", "created": "2021-08-18", "title": "UAV-Based Land Cover Classification for Hoverfly (Diptera: Syrphidae) Habitat Condition Assessment: A Case Study on Mt. Stara Planina (Serbia)", "description": "<?xml version='1.0' encoding='UTF-8'?><article><p>Habitat degradation, mostly caused by human impact, is one of the key drivers of biodiversity loss. This is a global problem, causing a decline in the number of pollinators, such as hoverflies. In the process of digitalizing ecological studies in Serbia, remote-sensing-based land cover classification has become a key component for both current and future research. Object-based land cover classification, using machine learning algorithms of very high resolution (VHR) imagery acquired by an unmanned aerial vehicle (UAV) was carried out in three different study sites on Mt. Stara Planina, Eastern Serbia. UAV land cover classified maps with seven land cover classes (trees, shrubs, meadows, road, water, agricultural land, and forest patches) were studied. Moreover, three different classification algorithms\u2014support vector machine (SVM), random forest (RF), and k-NN (k-nearest neighbors)\u2014were compared. This study shows that the random forest classifier performs better with respect to the other classifiers in all three study sites, with overall accuracy values ranging from 0.87 to 0.96. The overall results are robust to changes in labeling ground truth subsets. The obtained UAV land cover classified maps were compared with the Map of the Natural Vegetation of Europe (EPNV) and used to quantify habitat degradation and assess hoverfly species richness. It was concluded that the percentage of habitat degradation is primarily caused by anthropogenic pressure, thus affecting the richness of hoverfly species in the study sites. In order to enable research reproducibility, the datasets used in this study are made available in a public repository.</p></article>", "keywords": ["<i>Map of the Natural Vegetation of Europe</i>", "Orfeo ToolBox", "unmanned aerial vehicle; object-based image analysis; Orfeo ToolBox; QGIS; random forest; hoverfly; Map of the Natural Vegetation of Europe", "Science", "Q", "0211 other engineering and technologies", "Unmanned aerial vehicle", "02 engineering and technology", "15. Life on land", "01 natural sciences", "Object-based image analysis", "Map of the Natural Vegetation of Europe", "13. Climate action", "unmanned aerial vehicle", "object-based image analysis", "Hoverfly", "QGIS", "random forest", "Random forest", "hoverfly", "0105 earth and related environmental sciences"]}, "links": [{"href": "http://www.mdpi.com/2072-4292/13/16/3272/pdf"}, {"href": "https://doi.org/10.5281/zenodo.5770286"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Remote%20Sensing", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.5281/zenodo.5770286", "name": "item", "description": "10.5281/zenodo.5770286", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.5281/zenodo.5770286"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2021-08-18T00:00:00Z"}}, {"id": "10.5281/zenodo.6119920", "type": "Feature", "geometry": null, "properties": {"license": "Open Access", "updated": "2026-05-24T16:22:43Z", "type": "Report", "title": "Machine learning applied to the classification of riverine species using UAV-based photogrammetric point clouds", "description": "Open AccessCite as: Carbonell-Rivera, J. P., Estornell, J., Ruiz, L. A., Torralba, J., Crespo-Peremarch, P., 2021. Machine learning applied to the classification of riverine species using UAV-based photogrammetric point clouds. First International Conference on Smart Geoinformatics Applications (ICSGA), pp. 33-36, 24-25 Feb., online.", "keywords": ["13. Climate action", "Point cloud classification", " UAV-DAP", " Random Forest", " Riverine species", "15. Life on land"], "contacts": [{"organization": "Carbonell Rivera Juan Pedro, Estornell Javier, Ruiz Luis A, Torralba Perez Jesus, Crespo Peremarch Pablo,", "roles": ["creator"]}]}, "links": [{"href": "https://doi.org/10.5281/zenodo.6119920"}, {"rel": "self", "type": "application/geo+json", "title": "10.5281/zenodo.6119920", "name": "item", "description": "10.5281/zenodo.6119920", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.5281/zenodo.6119920"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2021-01-01T00:00:00Z"}}, {"id": "10.5281/zenodo.6397568", "type": "Feature", "geometry": null, "properties": {"updated": "2026-05-23T16:23:07Z", "type": "Dataset", "title": "Maps of soil organic carbon stocks in Brazil", "description": "Open AccessThis database was created by Gustavo Vieira Veloso and Lucas Carvalho Gomes 04/06/2022. <br> Contact: gustavo.v.veloso@gmail.com and lucascarvalhogomes15@hotmail.com Maps of soil organic carbon (SOC) stocks in Brazil of the article: 'Modeling and mapping soil organic carbon stocks in Brazil' (doi: 10.1016/j.geoderma.2019.01.007) The dataset is composed of five folders of SOC stocks maps at the standard depths (0\u20135, 5\u201315, 15\u201330, 30\u201360, and 60\u2013100 cm). The maps are in Geotif format (EPSG 102015) with a spatial resolution of approximately 1 km and include the mean SOC stocks, standard deviation (SD), coefficient of variation (CV), 0.05 and 0.95 quantiles. The maps are free to use and please cite also the article:<br> Gomes, L.C., Faria, R.M., de Souza, E., Veloso, G.V., Schaefer, C.E.G., &amp; Fernandes Filho, E.I. (2019). Modeling and mapping soil organic carbon stocks in Brazil. Geoderma, 340, 337-350.", "keywords": ["2. Zero hunger", "Random Forests", "Spatial prediction", "Soil carbon stock", "Machine learning", "15. Life on land"]}, "links": [{"href": "https://doi.org/10.5281/zenodo.6397568"}, {"rel": "self", "type": "application/geo+json", "title": "10.5281/zenodo.6397568", "name": "item", "description": "10.5281/zenodo.6397568", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.5281/zenodo.6397568"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2022-01-01T00:00:00Z"}}, {"id": "10.5281/zenodo.8092682", "type": "Feature", "geometry": null, "properties": {"updated": "2026-05-23T16:23:24Z", "type": "Journal Article", "created": "2021-12-15", "title": "A framework for determining the total salt content of soil profiles using time-series Sentinel-2 images and a random forest-temporal convolution network", "description": "Soil salinization causes a deterioration in soil health and threatens crop growth. Rapid identification of salinization in farmlands is of great significance to improve soil functions and to maintain sustainable land management. As salt moves in soil profiles during plowing and irrigation, the commonly used protocol for measuring and monitoring salt content in topsoil does not provide a thorough assessment. In order to quantify and comprehensively evaluate the salt content in deep soil, this study developed a novel framework for monitoring total salt content in the soil profile to a depth of 1 m by combining information from time-series satellite images and machine learning. The field experiments were conducted in Alar, Southern Xinjiang, with a total of 120 soil samples and 582 measurements of EM38-MK2 apparent electrical conductivity in 2019 and 2020 to quantify the vertical variation in the salt content. A total of 42 covariates derived from time-series Sentinel-2 images, including 20 salinity indices, 10 soil indices, and 12 vegetation indices were used for modeling salinity in the soil profile. From the total covariates, 22 were selected using the Random Forest. Soil salinity which was modeled using a Temporal Convolution Network in 2019 and 2020 and forecast for 2021. The model effectively revealed the spatial and temporal variability of the salt content in the soil profile with R<sup>2</sup> of 0.71 and 0.65 for 2019 and 2020, respectively. The proposed new framework provides an effective method to estimate the salt content in the soil profile for precision agriculture in arid and semi-arid regions.", "keywords": ["2. Zero hunger", "Soil salinity", "Random Forest", "13. Climate action", "Time-series images", "Soil profile", "0401 agriculture", " forestry", " and fisheries", "04 agricultural and veterinary sciences", "15. Life on land", "6. Clean water", "Temporal Convolution Network"]}, "links": [{"href": "https://doi.org/10.5281/zenodo.8092682"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Geoderma", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.5281/zenodo.8092682", "name": "item", "description": "10.5281/zenodo.8092682", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.5281/zenodo.8092682"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2022-03-01T00:00:00Z"}}, {"id": "10.5281/zenodo.8092713", "type": "Feature", "geometry": null, "properties": {"updated": "2026-05-23T16:23:24Z", "type": "Journal Article", "created": "2022-03-13", "title": "Development of Prediction Models for Estimating Key Rice Growth Variables Using Visible and NIR Images from Unmanned Aerial Systems", "description": "<?xml version='1.0' encoding='UTF-8'?><article><p>The rapid and accurate acquisition of rice growth variables using unmanned aerial system (UAS) is useful for assessing rice growth and variable fertilization in precision agriculture. In this study, rice plant height (PH), leaf area index (LAI), aboveground biomass (AGB), and nitrogen nutrient index (NNI) were obtained for different growth periods in field experiments with different nitrogen (N) treatments from 2019\u20132020. Known spectral indices derived from the visible and NIR images and key rice growth variables measured in the field at different growth periods were used to build a prediction model using the random forest (RF) algorithm. The results showed that the different N fertilizer applications resulted in significant differences in rice growth variables; the correlation coefficients of PH and LAI with visible-near infrared (V-NIR) images at different growth periods were larger than those with visible (V) images while the reverse was true for AGB and NNI. RF models for estimating key rice growth variables were established using V-NIR images and V images, and the results were validated with an R2 value greater than 0.8 for all growth stages. The accuracy of the RF model established from V images was slightly higher than that established from V-NIR images. The RF models were further tested using V images from 2019: R2 values of 0.75, 0.75, 0.72, and 0.68 and RMSE values of 11.68, 1.58, 3.74, and 0.13 were achieved for PH, LAI, AGB, and NNI, respectively, demonstrating that RGB UAS achieved the same performance as multispectral UAS for monitoring rice growth.</p></article>", "keywords": ["2. Zero hunger", "digital imagery", "rice growth variables; unmanned aerial system; multispectral imagery; digital imagery; random forest model", "Science", "random forest model", "Q", "0401 agriculture", " forestry", " and fisheries", "rice growth variables", "04 agricultural and veterinary sciences", "15. Life on land", "multispectral imagery", "unmanned aerial system"], "contacts": [{"organization": "Zhengchao Qiu, Fei Ma, Zhenwang Li, Xuebin Xu, Changwen Du,", "roles": ["creator"]}]}, "links": [{"href": "http://www.mdpi.com/2072-4292/14/6/1384/pdf"}, {"href": "https://doi.org/10.5281/zenodo.8092713"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Remote%20Sensing", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.5281/zenodo.8092713", "name": "item", "description": "10.5281/zenodo.8092713", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.5281/zenodo.8092713"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2022-03-13T00:00:00Z"}}, {"id": "10.57745/3QFT2T", "type": "Feature", "geometry": null, "properties": {"updated": "2026-05-23T16:23:52Z", "type": "Dataset", "title": "French maps for the Global Soil Nutrient and Nutrient Budget Map (GSNmap)", "description": "This set of maps presents digital maps of soil properties on agricultural lands in France within the FAO framework \u201cGlobal Soil Nutrient and Nutrient Budgets maps\u201d. The spatial predictions of ten soil properties, namely Total N, available P, CEC, pH (water), Clay, Silt, Sand, Soil Organic Carbon, Bulk density and available K were generated with a 250 m spatial resolution. Random forest machine learning approach in combination with environmental variables was used for spatial distribution assessment of properties. Additionally, uncertainty maps expressed as the standard deviation of spatial predictions were produced. All maps are provided in a raster geotiff format. the identifier of the spatial reference system (srid) is 4326.", "keywords": ["Earth and Environmental Science", "bulk density", "cation exchange capacity", "available phosphorus content", "Agriculture", " Forestry", " Horticulture", " Aquaculture", "sand", "cropland", "potassium content", "cation-exchange capacity", "Agriculture", " Forestry", " Horticulture", "2. Zero hunger", "silt", "Agricultural Sciences", "pH", "nutrient", "EAR soil sciences", "soil property", "Life Sciences", "clay", "15. Life on land", "6. Clean water", "soil organic carbon", "13. Climate action", "Earth and Environmental Sciences", "digital soil mapping", "Agriculture", " Forestry", " Horticulture", " Aquaculture and Veterinary Medicine", "Environmental Research", "Natural Sciences", "random forest", "Geosciences", "nitrogen content"], "contacts": [{"organization": "Suleymanov, Azamat, Saby, Nicolas, Bispo, Antonio,", "roles": ["creator"]}]}, "links": [{"href": "https://doi.org/10.57745/3QFT2T"}, {"rel": "self", "type": "application/geo+json", "title": "10.57745/3QFT2T", "name": "item", "description": "10.57745/3QFT2T", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.57745/3QFT2T"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2023-01-01T00:00:00Z"}}, {"id": "10.7910/DVN/U5DAEP", "type": "Feature", "geometry": null, "properties": {"updated": "2026-05-23T16:24:09Z", "type": "Dataset", "title": "An Available Water Capacity Pedotransfer Function using Random Forest - 2020 Cornell Soil Health Model", "description": "Open AccessDataset was compiled from 7,232 samples run through the Cornell Soil Health Laboratory between 2015-2019. Dataset contains texture data (sand, silt, and clay), wet aggregate stability (WAS), soil organic matter (SOM), 4-day soil respiration (Resp), active carbon (AC; this is also referred to as permanganate oxidizable carbon-POxC within the scientific literature), and modified morgan extractable K, Mg, Fe, and Mn in ppm. The dataset also includes field capacity, permanent wilting point, and available water capacity (AWC), which was measured on disturbed soil samples (&lt; 2 mm) that were equilibrated after initial saturation to pressures of -10 kPa and -1500 kPa on porous ceramic pressure plates in pressure chambers (Soil Moisture Equipment Corp., Goleta, CA). Columns include: RowNumber, sand, silt, clay, WAS, SOM, Resp, AC, K, Mg, Fe, Mn, and AWC.", "keywords": ["AWC", "Random Forest", "Soil Health Indicator", "Available Water Capacity", "Agricultural Sciences", "Permanent Wilting Point", "Field Capacity"], "contacts": [{"organization": "Amsili, Joseph, van Es, Harold, Schindelbeck, Robert,", "roles": ["creator"]}]}, "links": [{"href": "https://doi.org/10.7910/DVN/U5DAEP"}, {"rel": "self", "type": "application/geo+json", "title": "10.7910/DVN/U5DAEP", "name": "item", "description": "10.7910/DVN/U5DAEP", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.7910/DVN/U5DAEP"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2022-01-01T00:00:00Z"}}, {"id": "10835/7551", "type": "Feature", "geometry": null, "properties": {"updated": "2026-05-23T16:24:31Z", "type": "Journal Article", "created": "2019-06-06", "title": "Spectral Response Analysis: An Indirect and Non-Destructive Methodology for the Chlorophyll Quantification of Biocrusts", "description": "<?xml version='1.0' encoding='UTF-8'?><article><p>Chlorophyll a concentration (Chla) is a well-proven proxy of biocrust development, photosynthetic organisms\u2019 status, and recovery monitoring after environmental disturbances. However, laboratory methods for the analysis of chlorophyll require destructive sampling and are expensive and time consuming. Indirect estimation of chlorophyll a by means of soil surface reflectance analysis has been demonstrated to be an accurate, cheap, and quick alternative for chlorophyll retrieval information, especially in plants. However, its application to biocrusts has yet to be harnessed. In this study we evaluated the potential of soil surface reflectance measurements for non-destructive Chla quantification over a range of biocrust types and soils. Our results revealed that from the different spectral transformation methods and techniques, the first derivative of the reflectance and the continuum removal were the most accurate for Chla retrieval. Normalized difference values in the red-edge region and common broadband indexes (e.g., normalized difference vegetation index (NDVI)) were also sensitive to changes in Chla. However, such approaches should be carefully adapted to each specific biocrust type. On the other hand, the combination of spectral measurements with non-linear random forest (RF) models provided very good fits (R2 &gt; 0.94) with a mean root mean square error (RMSE) of about 6.5 \u00b5g/g soil, and alleviated the need for a specific calibration for each crust type, opening a wide range of opportunities to advance our knowledge of biocrust responses to ongoing global change and degradation processes from anthropogenic disturbance.</p></article>", "keywords": ["chlorophyll quantification", "remote sensing", "hyperspectral", "13. Climate action", "Science", "Q", "Biocrusts; biological soil crust; chlorophyll quantification; hyperspectral; random forest; remote sensing", "0401 agriculture", " forestry", " and fisheries", "04 agricultural and veterinary sciences", "15. Life on land", "random forest", "Biocrusts", "biological soil crust"]}, "links": [{"href": "http://www.mdpi.com/2072-4292/11/11/1350/pdf"}, {"href": "https://www.mdpi.com/2072-4292/11/11/1350/pdf"}, {"href": "https://doi.org/10835/7551"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Remote%20Sensing", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10835/7551", "name": "item", "description": "10835/7551", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10835/7551"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2019-06-05T00:00:00Z"}}, {"id": "11019/1960", "type": "Feature", "geometry": null, "properties": {"updated": "2026-05-23T16:24:32Z", "type": "Journal Article", "created": "2019-08-22", "title": "Using machine learning to estimate herbage production and nutrient uptake on Irish dairy farms", "description": "Nutrient management on grazed grasslands is of critical importance to maintain productivity levels, as grass is the cheapest feed for ruminants and underpins these meat and milk production systems. Many attempts have been made to model the relationships between controllable (crop and soil fertility management) and noncontrollable influencing factors (weather, soil drainage) and nutrient/productivity levels. However, to the best of our knowledge not much research has been performed on modeling the interconnections between the influencing factors on one hand and nutrient uptake/herbage production on the other hand, by using data-driven modeling techniques. Our paper proposes to use predictive clustering trees (PCT) learned for building models on data from dairy farms in the Republic of Ireland. The PCT models show good accuracy in estimating herbage production and nutrient uptake. They are also interpretable and are found to embody knowledge that is in accordance with existing theoretical understanding of the task at hand. Moreover, if we combine more PCT into an ensemble of PCT (random forest of PCT), we can achieve improved accuracy of the estimates. In practical terms, the number of grazings, which is related proportionally with soil drainage class, is one of the most important factors that moderates the herbage production potential and nutrient uptake. Furthermore, we found the nutrient (N, P, and K) uptake and herbage nutrient concentration to be conservative in fields that had medium yield potential (11 t of dry matter per hectare on average), whereas nutrient uptake was more variable and potentially limiting in fields that had higher and lower herbage production. Our models also show that phosphorus is the most limiting nutrient for herbage production across the fields on these Irish dairy farms, followed by nitrogen and potassium.", "keywords": ["2. Zero hunger", "nutrient uptake", "Nutrients", "04 agricultural and veterinary sciences", "15. Life on land", "Poaceae", "Animal Feed", "Diet", "Machine Learning", "herbage production", "Dairying", "Milk", "predictive clustering trees", "Animals", "Lactation", "0401 agriculture", " forestry", " and fisheries", "Cattle", "Female", "Ireland", "random forest"]}, "links": [{"href": "https://doi.org/11019/1960"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Journal%20of%20Dairy%20Science", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "11019/1960", "name": "item", "description": "11019/1960", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/11019/1960"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2019-11-01T00:00:00Z"}}, {"id": "11588/938135", "type": "Feature", "geometry": null, "properties": {"updated": "2026-05-23T16:24:42Z", "type": "Journal Article", "created": "2021-12-06", "title": "In Situ Observation-Constrained Global Surface Soil Moisture Using Random Forest Model", "description": "<?xml version='1.0' encoding='UTF-8'?><article><p>The inherent biases of different long-term gridded surface soil moisture (SSM) products, unconstrained by the in situ observations, implies different spatio-temporal patterns. In this study, the Random Forest (RF) model was trained to predict SSM from relevant land surface feature variables (i.e., land surface temperature, vegetation indices, soil texture, and geographical information) and precipitation, based on the in situ soil moisture data of the International Soil Moisture Network (ISMN.). The results of the RF model show an RMSE of 0.05 m3 m\u22123 and a correlation coefficient of 0.9. The calculated impurity-based feature importance indicates that the Antecedent Precipitation Index affects most of the predicted soil moisture. The geographical coordinates also significantly influence the prediction (i.e., RMSE was reduced to 0.03 m3 m\u22123 after considering geographical coordinates), followed by land surface temperature, vegetation indices, and soil texture. The spatio-temporal pattern of RF predicted SSM was compared with the European Space Agency Climate Change Initiative (ESA-CCI) soil moisture product, using both time-longitude and latitude diagrams. The results indicate that the RF SSM captures the spatial distribution and the daily, seasonal, and annual variabilities globally.</p></article>", "keywords": ["feature importance", "Antecedent precipitation index", "Science", "Q", "0207 environmental engineering", "In situ constrained", "02 engineering and technology", "15. Life on land", "01 natural sciences", "Feature importance", "antecedent precipitation index", "13. Climate action", "ITC-ISI-JOURNAL-ARTICLE", "global scale", "Global scale", "Antecedent precipitation index; Feature importance; Global scale; In situ constrained; Random forest; Soil moisture", "Soil moisture", "soil moisture", "ITC-GOLD", "in situ constrained", "soil moisture; random forest; global scale; in situ constrained; feature importance; antecedent precipitation index", "random forest", "Random forest", "0105 earth and related environmental sciences"]}, "links": [{"href": "http://www.mdpi.com/2072-4292/13/23/4893/pdf"}, {"href": "https://www.iris.unina.it/bitstream/11588/938135/1/2021_Ljie_Zeng_et_al_remotesensing.pdf"}, {"href": "https://www.mdpi.com/2072-4292/13/23/4893/pdf"}, {"href": "https://doi.org/11588/938135"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Remote%20Sensing", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "11588/938135", "name": "item", "description": "11588/938135", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/11588/938135"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2021-12-02T00:00:00Z"}}, {"id": "11590/469727", "type": "Feature", "geometry": null, "properties": {"updated": "2026-05-23T16:24:42Z", "type": "Journal Article", "created": "2023-10-31", "title": "An advanced global soil erodibility (K) assessment including the effects of saturated hydraulic conductivity", "description": "USLE-type models are widely used to estimate average annual soil loss at large scales, with the erodibility factor (K) being the sole component that accounts for soil's susceptibility to erosion. The factor includes the information on permeability in the equation, however, most definitions of the K factor consider the soil hydrological influence only very crudely and indirectly. Thus, the direct impact of surface runoff infiltration and drainage on soil erosion is largely neglected. The objective of this study is to incorporate soil hydraulic properties in the K factor map by merging available global-scale measured saturated hydraulic conductivity (Ksat) data with soil texture and organic carbon information into a modified K factor. To achieve this, the Wischmeier and Smith (1978) soil texture- and permeability-based equation (KWischmeier factor) was modified to include Ksat, called Kksat factor. Using the Random Forest machine learning algorithm, the KWischmeier factor and the Kksat factor were each correlated with soil and remote sensing covariates for spatial extrapolation of two independent K factor maps at 1\u00a0km spatial resolution. We noted a clear decrease in the mean value of the Kksat factor (0.023\u00a0t\u00a0ha\u00a0h\u00a0ha-1\u00a0MJ-1\u00a0mm-1) compared to the mean value of the KWischmeier factor (0.027\u00a0t\u00a0ha\u00a0h\u00a0ha-1\u00a0MJ-1\u00a0mm-1). The reduction in Kksat factor values was most pronounced in tropical regions reflecting the difference in soil properties (e.g., clay and iron), whereas other climate regions showed relatively minor changes in comparison to the KWischmeier factor as well as to the recent global modeling of Borrelli et al. (2017) (KGloSEM factor maps). As many studies discussed an overall overestimation of (R)USLE based erosion rates compared to measurements, this reduction in the K factor might improve modeled erosion rates in the right direction. The Kksat marks an important initial step in integrating hydraulic properties into the K factor of USLE-type models and can prove their significance in future studies.", "keywords": ["K factor; Random Forest; Soil hydraulic properties; Soil texture; Tropical regions; USLE", "15. Life on land", "6. Clean water"]}, "links": [{"href": "https://doi.org/11590/469727"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Science%20of%20The%20Total%20Environment", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "11590/469727", "name": "item", "description": "11590/469727", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/11590/469727"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2024-01-01T00:00:00Z"}}, {"id": "1854/LU-01GM39MMFY2YP4FTDY102R50HB", "type": "Feature", "geometry": null, "properties": {"updated": "2026-05-23T16:24:48Z", "type": "Journal Article", "created": "2021-11-17", "title": "Spatiotemporal Prediction and Mapping of Heavy Metals at Regional Scale Using Regression Methods and Landsat 7", "description": "<?xml version='1.0' encoding='UTF-8'?><article><p>Soil contamination by heavy metals is of particular concern, due to the direct negative impact on crop yield, food quality and human health. Although the conventional approach to monitor heavy metals relies on field sampling and lab analysis, the proliferation in the use of portable spectrometers has reduced the cost and time of investigation. However, discrepancies in spectral data from different spectrometers increase the modeling time and undermine the model accuracy for spatial mapping. This study, therefore, took advantage of the readily accessible Landsat 7 data to predict and map the spatiotemporal distribution of ten heavy metals (i.e., Sb, Pb, Ni, Mn, Hg, Cu, Cr, Co, Cd and As) over a 640 km2 area in Belgium. The Land Use/Cover Area Frame Survey (LUCAS) database of a region in north-eastern Belgium was used to retrieve variation in heavy metals concentrations over time and space, using the Landsat 7 imagery for four single dates in 2009, 2013, 2016 and 2020. Three regression methods, namely, partial least squares regression (PLSR), random forest (RF) and support vector machine (SVM) were used to model and predict the heavy metal concentrations for 2009. By comparing these models unbiasedly, the best model was selected for predicting and mapping the heavy metal distributions for 2013, 2016 and 2020. RF turned out to be the optimal model for 2009 with a coefficient of determination of prediction (R2P) and residual prediction deviation of prediction (RPDP) ranging from 0.62 to 0.92, and 1.23 to 2.79, respectively. The measured heavy metal distributions along the river floodplains, at the highlands and in the lowlands, were generally high, compared to their RF spatiotemporal predictions, which decreased over time. Increasing moisture contents in the floodplains adjacent to the river channels and the lowlands were the primary contributors to the reduction in the satellite reflectance spectra. However, topsoil erosion from rainfall, snowmelt as well as wind into the lowlands could have influenced the reduction in heavy metal spatiotemporal predicted values over time in the highlands. The spatiotemporal prediction maps produced for the heavy metals for the four different years revealed a good spatial similarity and consistency with the measured maps for 2009, which indicates their stability over the years.</p></article>", "keywords": ["Technology", "PROVINCE", "Landsat 7", "analysis", "Science", "Environmental Sciences & Ecology", "random forest (RF)", "MOISTURE", "01 natural sciences", "NIR SPECTROSCOPY", "0203 Classical Physics", "Remote Sensing", "0909 Geomatic Engineering", "spatiotemporal analysis", "AGRICULTURAL SOILS", "Geosciences", " Multidisciplinary", "Imaging Science & Photographic Technology", "spatiotemporal", "0105 earth and related environmental sciences", "2. Zero hunger", "Science & Technology", "RANGE", "Q", "Geology", "04 agricultural and veterinary sciences", "15. Life on land", "6. Clean water", "3. Good health", "MULTIVARIATE", "TOPSOILS", "13. Climate action", "Earth and Environmental Sciences", "Physical Sciences", "soil heavy metal; Landsat 7; partial least squares regression (PLSR); random forest (RF); support vector machine (SVM); spatiotemporal analysis", "0401 agriculture", " forestry", " and fisheries", "support vector machine (SVM)", "4013 Geomatic engineering", "0406 Physical Geography and Environmental Geoscience", "soil heavy metal", "partial least squares regression (PLSR)", "Life Sciences & Biomedicine", "3701 Atmospheric sciences", "Environmental Sciences", "3709 Physical geography and environmental geoscience"]}, "links": [{"href": "http://www.mdpi.com/2072-4292/13/22/4615/pdf"}, {"href": "https://www.mdpi.com/2072-4292/13/22/4615/pdf"}, {"href": "https://doi.org/1854/LU-01GM39MMFY2YP4FTDY102R50HB"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Remote%20Sensing", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "1854/LU-01GM39MMFY2YP4FTDY102R50HB", "name": "item", "description": "1854/LU-01GM39MMFY2YP4FTDY102R50HB", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/1854/LU-01GM39MMFY2YP4FTDY102R50HB"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2021-11-16T00:00:00Z"}}, {"id": "1854/LU-8720112", "type": "Feature", "geometry": null, "properties": {"updated": "2026-05-23T16:24:49Z", "type": "Journal Article", "created": "2021-09-09", "title": "Diagnosis of cadmium contamination in urban and suburban soils using visible-to-near-infrared spectroscopy", "description": "Previous studies have mostly focused on using visible-to-near-infrared spectral technique to quantitatively estimate soil cadmium (Cd) content, whereas little attention has been paid to identifying soil Cd contamination from a perspective of spectral classification. Here, we developed a framework to compare the potential of two spectral transformations (i.e., raw reflectance and continuum removal [CR]), three optimization strategies (i.e., full-spectrum, Boruta feature selection, and synthetic minority over-sampling technique [SMOTE]), and three classification algorithms (i.e., partial least squares discriminant analysis, random forest [RF], and support vector machine) for diagnosing soil Cd contamination. A total of 536 soil samples were collected from urban and suburban areas located in Wuhan City, China. Specifically, Boruta and SMOTE strategies were aimed at selecting the most informative predictors and obtaining balanced training datasets, respectively. Results indicated that soils contaminated by Cd induced decrease in spectral reflectance magnitude. Classification models developed after Boruta and SMOTE strategies out-performed to those from full-spectrum. A diagnose model combining CR preprocessing, SMOTE strategy, and RF algorithm achieved the highest validation accuracy for soil Cd (Kappa = 0.74). This study provides a theoretical reference for rapid identification of and monitoring of soil Cd contamination in urban and suburban areas.", "keywords": ["DIFFUSE-REFLECTANCE SPECTROSCOPY", "HUMAN HEALTH", "PREDICTION", "POTENTIALLY TOXIC ELEMENTS", "Boruta algorithm", "01 natural sciences", "Visible-to-near-infrared spectroscopy", "NIR SPECTROSCOPY", "Soil", "ORGANIC-CARBON", "Machine learning", "11. Sustainability", "Soil Pollutants", "Least-Squares Analysis", "0105 earth and related environmental sciences", "Spectroscopy", " Near-Infrared", "RANDOM FOREST", "Urban and suburban soil Cd contamination", "04 agricultural and veterinary sciences", "15. Life on land", "QUANTITATIVE-ANALYSIS", "6. Clean water", "RIVER DELTA", "13. Climate action", "Earth and Environmental Sciences", "Synthetic minority over-sampling technique", "0401 agriculture", " forestry", " and fisheries", "HEAVY-METAL CONCENTRATIONS", "Cadmium"]}, "links": [{"href": "https://doi.org/1854/LU-8720112"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Environmental%20Pollution", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "1854/LU-8720112", "name": "item", "description": "1854/LU-8720112", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/1854/LU-8720112"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2021-12-01T00:00:00Z"}}, {"id": "1871.1/3a1c0c1b-eb65-499f-a442-7d44fe86fcbf", "type": "Feature", "geometry": null, "properties": {"updated": "2026-05-23T16:24:50Z", "type": "Journal Article", "created": "2022-04-28", "title": "Anthropogenic and Lightning Fire Incidence and Burned Area in Europe", "description": "<?xml version='1.0' encoding='UTF-8'?><article><p>Fires can have an anthropogenic or natural origin. The most frequent natural fire cause is lightning. Since anthropogenic and lightning fires have different climatic and socio-economic drivers, it is important to distinguish between these different fire causes. We developed random forest models that predict the fraction of anthropogenic and lightning fire incidences, and their burned area, at the level of the Nomenclature des Unit\u00e9s Territoriales Statistiques level 3 (NUTS3) for Europe. The models were calibrated using the centered log-ratio of fire incidence and burned area reference data from the European Forest Fire Information System. After a correlation analysis, the population density, fractional human land impact, elevation and burned area coefficient of variation\u2014a measure of interannual variability in burned area\u2014were selected as predictor variables in the models. After parameter tuning and running the models with several train-validate compositions, we found that the vast majority of fires and burned area in Europe has an anthropogenic cause, while lightning plays a significant role in the remote northern regions of Scandinavia. Combining our results with burned area data from the Moderate Resolution Imaging Spectroradiometer, we estimated that 96.5 \u00b1 0.9% of the burned area in Europe has an anthropogenic cause. Our spatially explicit fire cause attribution model demonstrates the spatial variability between anthropogenic and lightning fires and their burned area over Europe and could be used to improve predictive fire models by accounting for fire cause.</p></article>", "keywords": ["Europe", "S", "13. Climate action", "random forest model", "11. Sustainability", "ignition", "fire cause; burned area; ignition; random forest model; Europe", "Agriculture", "15. Life on land", "01 natural sciences", "burned area", "fire cause", "0105 earth and related environmental sciences"]}, "links": [{"href": "http://www.mdpi.com/2073-445X/11/5/651/pdf"}, {"href": "https://www.mdpi.com/2073-445X/11/5/651/pdf"}, {"href": "https://doi.org/1871.1/3a1c0c1b-eb65-499f-a442-7d44fe86fcbf"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Land", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "1871.1/3a1c0c1b-eb65-499f-a442-7d44fe86fcbf", "name": "item", "description": "1871.1/3a1c0c1b-eb65-499f-a442-7d44fe86fcbf", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/1871.1/3a1c0c1b-eb65-499f-a442-7d44fe86fcbf"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2022-04-28T00:00:00Z"}}, {"id": "2954192991", "type": "Feature", "geometry": null, "properties": {"updated": "2026-05-23T16:25:30Z", "type": "Journal Article", "created": "2019-06-06", "title": "Spectral Response Analysis: An Indirect and Non-Destructive Methodology for the Chlorophyll Quantification of Biocrusts", "description": "<?xml version='1.0' encoding='UTF-8'?><article><p>Chlorophyll a concentration (Chla) is a well-proven proxy of biocrust development, photosynthetic organisms\u2019 status, and recovery monitoring after environmental disturbances. However, laboratory methods for the analysis of chlorophyll require destructive sampling and are expensive and time consuming. Indirect estimation of chlorophyll a by means of soil surface reflectance analysis has been demonstrated to be an accurate, cheap, and quick alternative for chlorophyll retrieval information, especially in plants. However, its application to biocrusts has yet to be harnessed. In this study we evaluated the potential of soil surface reflectance measurements for non-destructive Chla quantification over a range of biocrust types and soils. Our results revealed that from the different spectral transformation methods and techniques, the first derivative of the reflectance and the continuum removal were the most accurate for Chla retrieval. Normalized difference values in the red-edge region and common broadband indexes (e.g., normalized difference vegetation index (NDVI)) were also sensitive to changes in Chla. However, such approaches should be carefully adapted to each specific biocrust type. On the other hand, the combination of spectral measurements with non-linear random forest (RF) models provided very good fits (R2 &gt; 0.94) with a mean root mean square error (RMSE) of about 6.5 \u00b5g/g soil, and alleviated the need for a specific calibration for each crust type, opening a wide range of opportunities to advance our knowledge of biocrust responses to ongoing global change and degradation processes from anthropogenic disturbance.</p></article>", "keywords": ["chlorophyll quantification", "remote sensing", "hyperspectral", "13. Climate action", "Science", "Q", "Biocrusts; biological soil crust; chlorophyll quantification; hyperspectral; random forest; remote sensing", "0401 agriculture", " forestry", " and fisheries", "04 agricultural and veterinary sciences", "15. Life on land", "random forest", "Biocrusts", "biological soil crust"]}, "links": [{"href": "http://www.mdpi.com/2072-4292/11/11/1350/pdf"}, {"href": "https://www.mdpi.com/2072-4292/11/11/1350/pdf"}, {"href": "https://doi.org/2954192991"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Remote%20Sensing", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "2954192991", "name": "item", "description": "2954192991", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/2954192991"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2019-06-05T00:00:00Z"}}], "links": [{"rel": "self", "type": "application/geo+json", "title": "This document as GeoJSON", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items?keywords=RANDOM+FOREST&f=json", "hreflang": "en-US"}, {"rel": "alternate", "type": "text/html", "title": "This document as HTML", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items?keywords=RANDOM+FOREST&f=html", "hreflang": "en-US"}, {"rel": "collection", "type": "application/json", "title": "Collection URL", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main", "hreflang": "en-US"}, {"type": "application/geo+json", "rel": "first", "title": "items (first)", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items?keywords=RANDOM+FOREST&", "hreflang": "en-US"}, {"rel": "next", "type": "application/geo+json", "title": "items (next)", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items?keywords=RANDOM+FOREST&offset=50", "hreflang": "en-US"}], "numberMatched": 56, "numberReturned": 50, "distributedFeatures": [], "timeStamp": "2026-05-25T07:21:21.448897Z"}