{"type": "FeatureCollection", "features": [{"id": "10.5281/zenodo.8089699", "type": "Feature", "geometry": null, "properties": {"updated": "2026-10-06T16:21:37Z", "type": "Journal Article", "created": "2019-11-28", "title": "High-resolution and three-dimensional mapping of soil texture of China", "description": "The lack of detailed three-dimensional soil texture information largely restricts many applications in agriculture, hydrology, climate, ecology and environment. This study predicted 90 m resolution spatial variations of sand, silt and clay contents at a national extent across China and at multiple depths 0\u20135, 5\u201315, 15\u201330, 30\u201360, 60\u2013100 and 100\u2013200 cm. We used 4579 soil profiles collected from a national soil series inventory conducted recently and currently available environmental covariates. The covariates characterized environmental factors including climate, parent materials, terrain, vegetation and soil conditions. We constructed random forest models and employed a parallel computing strategy for the predictions of soil texture fractions based on its relationship with the environmental factors. Quantile regression forest was used to estimate the uncertainty of the predictions. Results showed that the predicted maps were much more accurate and detailed than the conventional linkage maps and the SoilGrids250m product, and could well represent spatial variation of soil texture across China. The relative accuracy improvement was around 245\u2013370% relative to the linkage maps and 83\u2013112% relative to the SoilGrids250m product with regard to the R2, and it was around 24\u201326% and 14\u201319% respectively with regard to the RMSE. The wide range between 5% lower and 95% upper prediction limits may suggest that there was a substantial room to improve current predictions. Besides, we found that climate and terrain factors are major controllers for spatial patterns of soil texture in China. The heat and water-driven physical and chemical weathering and wind-driven erosion processes primarily shape the pattern of clay content. The terrain, wind and water-driven deposition, erosion and transportation sorting processes of soil particles primarily shape the pattern of silt. The findings provide clues for modeling future soil evolution and for national soil security management under the background of global and regional environmental changes.", "keywords": ["2. Zero hunger", "Digital soil mapping", "13. Climate action", "Large extent", "Machine learning", "Environmental factors", "Uncertainty", "0401 agriculture", " forestry", " and fisheries", "04 agricultural and veterinary sciences", "15. Life on land", "01 natural sciences", "0105 earth and related environmental sciences"]}, "links": [{"href": "https://doi.org/10.5281/zenodo.8089699"}, {"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.8089699", "name": "item", "description": "10.5281/zenodo.8089699", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.5281/zenodo.8089699"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2020-03-01T00:00:00Z"}}, {"id": "1ff103b563b961b09e0d6df12278052e", "type": "Feature", "geometry": null, "properties": {"updated": "2026-10-06T16:22:48Z", "type": "Report", "title": "DISSEC-ML \u02f8 towards distributed and secured machine learning in the personal cloud", "description": "Open AccessLes initiatives comme le Blue Button et les nouvelles r\u00e9glementations comme le RGPD europ\u00e9en visent \u00e0 permettre aux individus de r\u00e9cup\u00e9rer leurs donn\u00e9es personnelles aupr\u00e8s des entreprises ou des organismes qui les ont recueillies. Parall\u00e8lement, des plateformes, qu'on appelle Personal Data Management System (PDMS), Personal Information Management System (PIMS) ou Cloud Personnel se d\u00e9veloppent rapidement et permettent aux utilisateurs de regrouper tout leur patrimoine num\u00e9rique. Le paradigme PDMS promet d'ouvrir la voie \u00e0 de nouveaux usages innovants d\u00e9velopp\u00e9s autour des donn\u00e9es personnelles, et de r\u00e9aliser notamment des calculs distribu\u00e9s sur un grand nombre de PDMS (e.g., classification automatique, recommandations, \u00e9tudes participatives). De tels exemples n\u00e9cessitent souvent la formation d'un mod\u00e8le d'intelligence artificielle (IA) bas\u00e9 sur un grand volume de donn\u00e9es des utilisateurs, soulevant \u00e9galement d'importants d\u00e9fis au niveau de la protection de la vie priv\u00e9e et de la performance d'un tel calcul. Ainsi, l'organisation d'un calcul distribu\u00e9 s\u00e9curis\u00e9 et efficace entre un grand nombre de PDMS peut s'av\u00e9rer complexe, surtout en pr\u00e9sence d'un nombre potentiellement important de n\u0153uds corrompus. Cette th\u00e8se CIFRE est r\u00e9alis\u00e9e avec la soci\u00e9t\u00e9 Cozy Cloud qui propose une solution libre de cloud personnel, Cozy. L'objectif est de fournir une \u00e9tude approfondie de ce probl\u00e8me nouveau et crucial et de proposer des solutions appropri\u00e9es pour entra\u00eener efficacement un mod\u00e8le d'IA (e.g., un r\u00e9seau neuronal profond) dans un syst\u00e8me totalement distribu\u00e9 tout en offrant de solides garanties de s\u00e9curit\u00e9 aux n\u0153uds participants. Les r\u00e9sultats, sous forme de protocoles et d'algorithmes d'ex\u00e9cution distribu\u00e9s, s\u00e9curis\u00e9s et fiables seront appliqu\u00e9s \u00e0 des cas pratiques fournis par la soci\u00e9t\u00e9 Cozy Cloud.", "keywords": ["Machine Learning", "Cloud personnel", "Personal data", "Privacy", "Calcul distribu\u00e9", "Personal Cloud", "Data leakage", "[INFO.INFO-DC] Computer Science [cs]/Distributed", " Parallel", " and Cluster Computing [cs.DC]", "Apprentissage automatique", "Distributed computations", "Fuite de donn\u00e9es", "Confidentialit\u00e9", "Donn\u00e9es personnelles"], "contacts": [{"organization": "Mirval, Julien", "roles": ["creator"]}]}, "links": [{"href": "https://doi.org/1ff103b563b961b09e0d6df12278052e"}, {"rel": "self", "type": "application/geo+json", "title": "1ff103b563b961b09e0d6df12278052e", "name": "item", "description": "1ff103b563b961b09e0d6df12278052e", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/1ff103b563b961b09e0d6df12278052e"}, {"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": "10.5281/zenodo.7948400", "type": "Feature", "geometry": null, "properties": {"updated": "2026-10-06T16:21:36Z", "type": "Report", "title": "Farm management information systems as tools for revealing management zones inside the fields", "description": "INTRODUCTION and OBJECTIVES: There is a huge need to increase the productivity in agriculture to feed the world\u2019s growing population. However, this increase needs to be achieved in a sustainable way, without jeopardising the ecosystem and environment. Innovations in AgTech are accelerating this process and providing adequate solutions for optimisation of on-field decision-making, but they are often isolated and inaccessible to the farmers. The objective of our work was to design a comprehensive farm management system that takes scientific achievements and enables farmers to use them in their daily operations. MATERIAL and METHOD: In order to digitally transform the Serbian agriculture, we designed AgroSense farm management information system. It was launched in 2017 and has since gathered more than 20,000 users, whose total area equals one fourth of all farmland in Serbia. The platform has a number of modules for weather forecast, historical weather records, digital field books, satellite image processing etc., while the newest addition is the drone image processing module. This module allows 3rd party drone services to scan the fields and upload the data to the platform, after which, the images are processed and analysed. The analysis is directed towards zone management delineation, which is the first step in application of precision agriculture technologies. Zones are detected within the field as areas with homogeneous soil and elevation properties. This is done by applying k-means, an unsupervised machine learning model for clusterisation of data, i.e. pixels in this case. This algorithm minimises the intra-class variance (variance of pixels within the zone) and maximises the inter-class variance (variance between pixels from different classes. This zone delineation can be done on a pixel-level if the objective of zone delineation is e.g. choosing the right locations for soil sampling, or on the level of the tractor swath if the goal is e.g. the variable-rate application of fertiliser. The number of zones and the swath width are variable parameters, left to the user to choose, according to the size of the field, type of the equipment and other factors. RESULTS and CONCLUSIONS: The resulting platform was deployed in 2021 and tested on a number of users. It yielded excellent results and served for optimising the route and sampling location of unmanned ground vehicles (UGVs), characterisation of fields and variable application of fertiliser. Future work includes development of other algorithms for more complex image recognition tasks, such as row detection, leaf area assessment and disease/weed mapping.", "keywords": ["2. Zero hunger", "13. Climate action", "15. Life on land", "drones; precision agriculture; image processing; machine learning"], "contacts": [{"organization": "Marko, Oskar, Brdar, Sanja, Pani\u0107, Marko, Mini\u0107, Vladan, Pejak, Branislav, Crnojevi\u0107, Vladimir,", "roles": ["creator"]}]}, "links": [{"href": "https://doi.org/10.5281/zenodo.7948400"}, {"rel": "self", "type": "application/geo+json", "title": "10.5281/zenodo.7948400", "name": "item", "description": "10.5281/zenodo.7948400", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.5281/zenodo.7948400"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2022-06-16T00:00:00Z"}}, {"id": "10.3390/land11091397", "type": "Feature", "geometry": null, "properties": {"updated": "2026-10-06T16:19:40Z", "type": "Journal Article", "created": "2022-08-26", "title": "Evaluation of Accuracy Enhancement in European-Wide Crop Type Mapping by Combining Optical and Microwave Time Series", "description": "<?xml version='1.0' encoding='UTF-8'?><article><p>This investigation evaluates the potential of combining Copernicus Sentinel-1 (S1) and Sentinel-2 (S2) satellite data in producing a detailed Land Use and Land Cover (LULC) map with 19 crop type classes and 2 broader categories containing Woodland/Shrubland and Grassland over 28 Member States of Europe (EU-28). The Eurostat Land Use and Coverage Area Frame Survey (LUCAS) 2018 dataset is employed as ground truth for model training and validation. Monthly and yearly optical features from S2 spectral reflectance and spectral indices, alongside decadal (10-days) composites from an S1 microwave sensor, are extracted for the EU-28 territory for 2018 using Google Earth Engine (GEE). Five different feature sets using a mixture of indicators were created as input training data. A Random Forest (RF) machine learning algorithm was applied to classify these feature sets, and the generated classification models were compared using an identical validation dataset. Results show that S1 and S2 yearly features together are able to provide a full coverage map less dependent on cloud effects and having appropriate overall accuracy (OA). Based on this feature set, the 21 classes could be classified with an OA of 78.3% using the independent validation data set. The OA increases to 82.7% by grouping 21 classes into 8 broader categories. The comparison with similar studies using individual S1 and S2 data indicates that combining S1 and S2 time series can attain slightly better results while enhancing spatial coverage.</p></article>", "keywords": ["LUCAS 2018", "S", "0211 other engineering and technologies", "Agriculture", "04 agricultural and veterinary sciences", "02 engineering and technology", "15. Life on land", "crop type classification", "machine learning", "13. Climate action", "Sentinel-1", "0401 agriculture", " forestry", " and fisheries", "Sentinel-2", "time series", "Google Earth Engine"]}, "links": [{"href": "https://www.mdpi.com/2073-445X/11/9/1397/pdf"}, {"href": "https://doi.org/10.3390/land11091397"}, {"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/land11091397", "name": "item", "description": "10.3390/land11091397", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.3390/land11091397"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2022-08-25T00:00:00Z"}}, {"id": "10.1016/j.envpol.2021.118128", "type": "Feature", "geometry": null, "properties": {"updated": "2026-10-06T16:16:02Z", "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": "10.1002/cli2.19", "type": "Feature", "geometry": null, "properties": {"updated": "2026-10-06T16:14:29Z", "type": "Journal Article", "created": "2021-10-21", "title": "An alert system for Seasonal Fire probability forecast for South American Protected Areas", "description": "Abstract<p>Timely spatially explicit warning of areas with high fire occurrence probability is an important component of strategic plans to prevent and monitor fires within South American (SA) Protected Areas (PAs). In this study, we present a five\uffe2\uff80\uff90level alert system, which combines both climatological and anthropogenic factors, the two main drivers of fires in SA. The alert levels are: High Alert, Alert, Attention, Observation and Low Probability. The trend in the number of active fires over the past three years and the accumulated number of active fires over the same period were used as indicators of intensification of human use of fire in that region, possibly associated with ongoing land use/land cover change (LULCC). An ensemble of temperature and precipitation gridded output from the GloSea5 Seasonal Forecast System was used to indicate an enhanced probability of hot and dry weather conditions that combined with LULCC favour fire occurrences. Alerts from this system were first issued in August 2020, for the period ranging from August to October (ASO) 2020. Overall, 50% of all fires observed during the ASO 2017\uffe2\uff80\uff932019 period and 40% of the ASO 2020 fires occurred in only 29 PAs were all categorized in the top two alert levels. In categories mapped as High Alert level, 34% of the PAs experienced an increase in fires compared with the 2017\uffe2\uff80\uff932019 reference period, and 81% of the High Alert false alarm registered fire occurrence above the median. Initial feedback from stakeholders indicates that these alerts were used to inform resource management in some PAs. We expect that these forecasts can provide continuous information aiming at changing societal perceptions of fire use and consequently subsidize strategic planning and mitigatory actions, focusing on timely responses to a disaster risk management strategy. Further research must focus on the model improvement and knowledge translation to stakeholders.</p>", "keywords": ["0106 biological sciences", "Atmospheric Science", "Land cover", "Flood Risk", "Precipitation", "01 natural sciences", "Environmental science", "Impact of Climate Change on Forest Wildfires", "Global Flood Risk Assessment and Management", "Meteorology", "Engineering", "Machine learning", "False alarm", "Civil engineering", "0105 earth and related environmental sciences", "Climatology", "Global and Planetary Change", "Tropical Cyclone Intensity and Climate Change", "Geography", "Warning system", "Geology", "FOS: Earth and related environmental sciences", "15. Life on land", "Computer science", "Earth and Planetary Sciences", "13. Climate action", "Environmental Science", "Physical Sciences", "Land use", "Telecommunications", "FOS: Civil engineering"]}, "links": [{"href": "https://rmets.onlinelibrary.wiley.com/doi/pdf/10.1002/cli2.19"}, {"href": "https://doi.org/10.1002/cli2.19"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Climate%20Resilience%20and%20Sustainability", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.1002/cli2.19", "name": "item", "description": "10.1002/cli2.19", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.1002/cli2.19"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2021-10-20T00:00:00Z"}}, {"id": "10.1007/s00466-018-1540-6", "type": "Feature", "geometry": null, "properties": {"updated": "2026-10-06T16:14:52Z", "type": "Journal Article", "created": "2018-01-10", "title": "Toward transient finite element simulation of thermal deformation of machine tools in real-time", "description": "Finite element models without simplifying assumptions can accurately describe the spatial and temporal distribution of heat in machine tools as well as the resulting deformation. In principle, this allows to correct for displacements of the Tool Centre Point and enables high precision manufacturing. However, the computational cost of FEM models and restriction to generic algorithms in commercial tools like ANSYS prevents their operational use since simulations have to run faster than real-time. For the case where heat diffusion is slow compared to machine movement, we introduce a tailored implicit-explicit multi-rate time stepping method of higher order based on spectral deferred corrections. Using the open-source FEM library DUNE, we show that fully coupled simulations of the temperature field are possible in real-time for a machine consisting of a stock sliding up and down on rails attached to a stand.", "keywords": ["FOS: Computer and information sciences", "Machine tool", "Numerical Analysis (math.NA)", "Systems and Control (eess.SY)", "Electrical Engineering and Systems Science - Systems and Control", "Real-time simulation", "Computational Engineering", " Finance", " and Science (cs.CE)", "Numerical time-stepping", "Spectral deferred corrections", "FOS: Mathematics", "FOS: Electrical engineering", " electronic engineering", " information engineering", "Thermal error", "Mathematics - Numerical Analysis", "Computer Science - Computational Engineering", " Finance", " and Science"]}, "links": [{"href": "https://eprints.whiterose.ac.uk/125537/1/paper.pdf"}, {"href": "https://doi.org/10.1007/s00466-018-1540-6"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Computational%20Mechanics", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.1007/s00466-018-1540-6", "name": "item", "description": "10.1007/s00466-018-1540-6", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.1007/s00466-018-1540-6"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2018-01-10T00:00:00Z"}}, {"id": "10.1007/s00226-022-01398-7", "type": "Feature", "geometry": null, "properties": {"updated": "2026-10-06T16:14:44Z", "type": "Journal Article", "created": "2022-07-11", "title": "Timber tensile strength in mixed stands of European beech (Fagus sylvatica L.).", "description": "Abstract<p>The conversion to climate-stable, resilient and productive forests has resulted in an increasing share of mixed stands. Different growth conditions and silvicultural treatments lead to an increased scatter in strength compared to what is expected from monoculture experience. The study (i) quantified the magnitude of variation in strength of European beech timber from stands of different composition and (ii) showed the impact of grading on the characteristic strength value of timber coming from those stands. Strength grading models and machine settings for hardwood tensile classes on over 900 European beech (Fagus sylvatica L.) boards were derived. One model used only the dynamic modulus of elasticity (Edyn), and a more complex model used a knot value in addition. Afterwards, 407 boards from pure beech stands as well as mixed stands of beech with Douglas fir (Pseudotsuga menziesii (Mirb.) Franco), Norway spruce (Picea abies (L.) Karst.), sessile oak (Quercus petraea (Matt.) Liebl.), and Scots pine (Pinus sylvestris L.) were graded and analyzed for their material properties from tension tests parallel to grain. Although a variance components analysis attributed only 4.2% of the variation to mixture, the ungraded timber showed significant strength differences between the pure and the beech-pine stands (65.2 versus 46.6\uffc2\uffa0MPa). The yield of the material graded to the highest class in a class combination was higher in pure beech stands. The required characteristic strength values were mostly met for boards from the pure stands; while boards from the beech-pine mixed stands hardly ever reached the required values. To reduce strength variation and guarantee reliable timber products, strength grading should consider the various growth situations in forests when sampling material for the derivation of settings.</p>", "keywords": ["690", "0106 biological sciences", "Original ; Wood Science & Technology ; Ceramics", " Glass", " Composites", " Natural Materials ; Manufacturing", " Machines", " Tools", " Processes", "ddc:630", "0401 agriculture", " forestry", " and fisheries", "04 agricultural and veterinary sciences", "15. Life on land", "01 natural sciences", "ddc:"]}, "links": [{"href": "https://link.springer.com/content/pdf/10.1007/s00226-022-01398-7.pdf"}, {"href": "https://doi.org/10.1007/s00226-022-01398-7"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Wood%20Science%20and%20Technology", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.1007/s00226-022-01398-7", "name": "item", "description": "10.1007/s00226-022-01398-7", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.1007/s00226-022-01398-7"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2022-07-01T00:00:00Z"}}, {"id": "10.1016/j.geoderma.2019.114061", "type": "Feature", "geometry": null, "properties": {"updated": "2026-10-06T16:16:19Z", "type": "Journal Article", "created": "2019-11-28", "title": "High-resolution and three-dimensional mapping of soil texture of China", "description": "The lack of detailed three-dimensional soil texture information largely restricts many applications in agriculture, hydrology, climate, ecology and environment. This study predicted 90 m resolution spatial variations of sand, silt and clay contents at a national extent across China and at multiple depths 0\u20135, 5\u201315, 15\u201330, 30\u201360, 60\u2013100 and 100\u2013200 cm. We used 4579 soil profiles collected from a national soil series inventory conducted recently and currently available environmental covariates. The covariates characterized environmental factors including climate, parent materials, terrain, vegetation and soil conditions. We constructed random forest models and employed a parallel computing strategy for the predictions of soil texture fractions based on its relationship with the environmental factors. Quantile regression forest was used to estimate the uncertainty of the predictions. Results showed that the predicted maps were much more accurate and detailed than the conventional linkage maps and the SoilGrids250m product, and could well represent spatial variation of soil texture across China. The relative accuracy improvement was around 245\u2013370% relative to the linkage maps and 83\u2013112% relative to the SoilGrids250m product with regard to the R2, and it was around 24\u201326% and 14\u201319% respectively with regard to the RMSE. The wide range between 5% lower and 95% upper prediction limits may suggest that there was a substantial room to improve current predictions. Besides, we found that climate and terrain factors are major controllers for spatial patterns of soil texture in China. The heat and water-driven physical and chemical weathering and wind-driven erosion processes primarily shape the pattern of clay content. The terrain, wind and water-driven deposition, erosion and transportation sorting processes of soil particles primarily shape the pattern of silt. The findings provide clues for modeling future soil evolution and for national soil security management under the background of global and regional environmental changes.", "keywords": ["2. Zero hunger", "Digital soil mapping", "13. Climate action", "Large extent", "Machine learning", "Environmental factors", "Uncertainty", "0401 agriculture", " forestry", " and fisheries", "04 agricultural and veterinary sciences", "15. Life on land", "01 natural sciences", "0105 earth and related environmental sciences"]}, "links": [{"href": "https://doi.org/10.1016/j.geoderma.2019.114061"}, {"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.2019.114061", "name": "item", "description": "10.1016/j.geoderma.2019.114061", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.1016/j.geoderma.2019.114061"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2020-03-01T00:00:00Z"}}, {"id": "10.1016/j.geoderma.2019.114145", "type": "Feature", "geometry": null, "properties": {"updated": "2026-10-06T16:16:19Z", "type": "Journal Article", "created": "2019-12-30", "title": "Pedoclimatic zone-based three-dimensional soil organic carbon mapping in China", "description": "Up-to-date maps of soil organic carbon (SOC) concentrations can provide vital information for monitoring global or regional soil C changes and soil quality. In this study, a national soil dataset collected in the 2010 s was applied to produce SOC maps of mainland China at soil depths of 0\u20135 cm, 5\u201315 cm, 15\u201330 cm, 30\u201360 cm, 60\u2013100 cm and 100\u2013200 cm. A stacking ensemble learning framework was utilized to take advantage of the optimal predictions from individual models. A voting-based ensemble learning model (VELM) was proposed with consideration of pedoclimatic zones. In this model, three machine learning models were separately trained for every pedoclimatic zone, and their predictions were selectively merged together. A weighted ensemble learning model (WELM), in which the parameterization considered all zones (i.e., the whole study area) simultaneously, was also trained for comparison. The overall R2 values of these two methods ranged from 0.16 to 0.57 and decreased with depth. Based on the independent validation, the R2 values ranged from 0.41 to 0.57 in the topsoil (0\u20135 cm, 5\u201315 cm and 15\u201330 cm). Overall accuracy metrics implied that the VELM and WELM yielded nearly the same prediction performances. However, model validation in the pedoclimatic zones showed that the VELM obviously outperformed the WELM, with the VELM generally improving the accuracy by 12.6%. Based on the independent validation, we also compared our predictions with other soil map products. Although the spatial patterns were similar, the predicted SOC maps outperformed two other products. The comparison of the two ensemble models should serve as a reminder that if new national or regional soil maps are generated, validation based on pedoclimatic zones or other soil-landscape units may be necessary before applying these maps.", "keywords": ["Digital soil mapping", "13. Climate action", "Ensemble learning", "Machine learning", "Uncertainty", "0401 agriculture", " forestry", " and fisheries", "Model comparison", "04 agricultural and veterinary sciences", "15. Life on land"], "contacts": [{"organization": "Song, Xiao-Dong, Wu, Hua-Yong, Ju, Bing, Liu, Feng, Yang, Fei, Li, De-Cheng, Zhao, Yu-Guo, Yang, Jin-Ling, Zhang, Gan-Lin,", "roles": ["creator"]}]}, "links": [{"href": "https://doi.org/10.1016/j.geoderma.2019.114145"}, {"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.2019.114145", "name": "item", "description": "10.1016/j.geoderma.2019.114145", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.1016/j.geoderma.2019.114145"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2020-04-01T00:00:00Z"}}, {"id": "10.1007/s10661-023-11079-y", "type": "Feature", "geometry": null, "properties": {"updated": "2026-10-06T16:15:02Z", "type": "Journal Article", "created": "2023-03-25", "title": "Evaluating the impacts of sustainable land management practices on water quality in an agricultural catchment in Lower Austria using SWAT", "description": "Abstract <p>Managing agricultural watersheds in an environmentally friendly manner necessitate the strategic implementation of well-targeted sustainable land management (SLM) practices that limit soil and nonpoint source pollution losses and translocation. Watershed-scale SLM-scenario modeling has the potential to identify efficient and effective management strategies from the field to the integrated landscape level. In a case study targeting a 66-hectare watershed in Petzenkirchen, Lower Austria, the Soil and Water Assessment Tool (SWAT) was utilized to evaluate a variety of locally adoptable SLM practices. SWAT was calibrated and validated (monthly) at the catchment outlet for flow, sediment, nitrate-nitrogen (NO3\uffe2\uff80\uff93N), ammonium nitrogen (NH4\uffe2\uff80\uff93N), and mineralized phosphorus (PO4\uffe2\uff80\uff93P) using SWATplusR. Considering the locally existing agricultural practices and socioeconomic and environmental factors of the research area, four conservation practices were evaluated: baseline scenario, contour farming (CF), winter cover crops (CC), and a combination of no-till and cover crops (NT\uffe2\uff80\uff89+\uffe2\uff80\uff89CC). The NT\uffe2\uff80\uff89+\uffe2\uff80\uff89CC SLM practice was found to be the most effective soil conservation practice in reducing soil loss by around 80%, whereas CF obtained the best results for decreasing the nutrient loads of NO3\uffe2\uff80\uff93N and PO4\uffe2\uff80\uff93P by 11% and 35%, respectively. The findings of this study imply that the setup SWAT model can serve the context-specific performance assessment and eventual promotion of SLM interventions that mitigate on-site land degradation and the consequential off-site environmental pollution resulting from agricultural nonpoint sources.</p", "keywords": ["Agricultural and Biological Sciences", "Soil", "Context (archaeology)", "Engineering", "Water Quality", "Soil water", "Water Science and Technology", "Watershed Management", "2. Zero hunger", "Geography", "Ecology", "Life Sciences", "Soil and Water Assessment Tool", "Agriculture", "Hydrology (agriculture)", "6. Clean water", "Soil Erosion and Agricultural Sustainability", "Water resource management", "Hydrological Modeling and Water Resource Management", "Water quality", "Archaeology", "Austria", "Physical Sciences", "SWAT model", "Environmental Monitoring", "Cartography", "Conservation of Natural Resources", "Biogeochemical Cycling of Nutrients in Aquatic Ecosystems", "Drainage basin", "Nitrogen", "Soil Science", "Streamflow", "Article", "Environmental science", "Soil quality", "Machine learning", "Environmental Chemistry", "Civil engineering", "Biology", "Nonpoint source pollution", "Soil science", "15. Life on land", "Watershed Simulation", "Watershed management", "Watershed", "Computer science", "Geotechnical engineering", "13. Climate action", "FOS: Biological sciences", "Environmental Science", "Land use", "FOS: Civil engineering"]}, "links": [{"href": "https://doi.org/10.1007/s10661-023-11079-y"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Environmental%20Monitoring%20and%20Assessment", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.1007/s10661-023-11079-y", "name": "item", "description": "10.1007/s10661-023-11079-y", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.1007/s10661-023-11079-y"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2023-03-25T00:00:00Z"}}, {"id": "10.1016/j.compag.2021.106421", "type": "Feature", "geometry": null, "properties": {"updated": "2026-10-06T16:15:52Z", "type": "Journal Article", "created": "2021-08-31", "title": "Estimation of nitrogen nutrition index in rice from UAV RGB images coupled with machine learning algorithms", "description": "Rapid and accurate estimation of rice Nitrogen Nutrition Index (NNI) is beneficial for management of nitrogen application in rice production. Traditional estimation methods required manual actual measurement data in the field, which was time-consuming and cost-expensive, and RGB images from unmanned aerial vehicle (UAV) provided an alternative option for nitrogen nutrition index (NNI) monitoring. In this study, RGB images from unmanned aerial vehicle (UAV) were obtained from each growth period of rice, and six machine learning (ML) algorithms, i.e., adaptive boosting (AB), artificial neural network (ANN), K-nearest neighbor (KNN), partial least squares (PLSR), random forest (RF) and support vector machine (SVM), were used to extract target information for estimating NNI as well as vegetation index (VI). Results showed that most UAV VIs were significantly correlated with rice NNI at the key growing periods; the estimation results of rice NNI using six ML algorithms showed that the RF algorithms performed the best at each growth period with the determination coefficient (R<sup>2</sup> ) ranged from 0.88 to 0.96 and room mean square error (RMSE) ranged from 0.03 to 0.07, in which the estimation of NNI was the best in filling period and the early jointing stage. Rice NNI at the early jointing stage was significantly correlated with soil available nitrogen (AN) with the R<sup>2 </sup>of 0.84 in Pukou and 0.72 in Luhe, respectively, and rice NNI was significantly correlated with the yield with the R2 of more than 0.7 in Pukou at the whole period and more than 0.7 in Luhe from late jointing to maturity stage. Therefore, the combination of RGB images from UAV and ML algorithms was a scalable, simple and inexpensive method for rapid qualification of rice NNI, which effectively improved nitrogen use efficiency and provided guidance for precision fertilization in rice production.", "keywords": ["2. Zero hunger", "Machine learning", "0211 other engineering and technologies", "0401 agriculture", " forestry", " and fisheries", "Precision fertilization", "Rice", "Nitrogen nutrition index", "Unmanned aerial vehicle", "04 agricultural and veterinary sciences", "02 engineering and technology", "6. Clean water"], "contacts": [{"organization": "Zhengchao Qiu, Ma, Fei, Zhenwang Li, Xuebin Xu, Haixiao Ge, Changwen Du,", "roles": ["creator"]}]}, "links": [{"href": "https://doi.org/10.1016/j.compag.2021.106421"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Computers%20and%20Electronics%20in%20Agriculture", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.1016/j.compag.2021.106421", "name": "item", "description": "10.1016/j.compag.2021.106421", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.1016/j.compag.2021.106421"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2021-10-01T00:00:00Z"}}, {"id": "10.1016/j.compag.2019.05.012", "type": "Feature", "geometry": null, "properties": {"updated": "2026-10-06T16:15:52Z", "type": "Journal Article", "created": "2019-05-13", "title": "A weighted multivariate spatial clustering model to determine irrigation management zones", "description": "Open AccessPeer reviewed", "keywords": ["0106 biological sciences", "2. Zero hunger", "Machine learning", "0401 agriculture", " forestry", " and fisheries", "04 agricultural and veterinary sciences", "Precision irrigation", "15. Life on land", "01 natural sciences", "Spatial modeling", "6. Clean water"]}, "links": [{"href": "https://doi.org/10.1016/j.compag.2019.05.012"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Computers%20and%20Electronics%20in%20Agriculture", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.1016/j.compag.2019.05.012", "name": "item", "description": "10.1016/j.compag.2019.05.012", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.1016/j.compag.2019.05.012"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2019-07-01T00:00:00Z"}}, {"id": "10.1016/j.envpol.2011.02.024", "type": "Feature", "geometry": null, "properties": {"updated": "2026-10-06T16:16:02Z", "type": "Journal Article", "created": "2011-06-08", "title": "Developments In Greenhouse Gas Emissions And Net Energy Use In Danish Agriculture - How To Achieve Substantial Co2 Reductions?", "description": "Greenhouse gas (GHG) emissions from agriculture are a significant contributor to total Danish emissions. Consequently, much effort is currently given to the exploration of potential strategies to reduce agricultural emissions. This paper presents results from a study estimating agricultural GHG emissions in the form of methane, nitrous oxide and carbon dioxide (including carbon sources and sinks, and the impact of energy consumption/bioenergy production) from Danish agriculture in the years 1990-2010. An analysis of possible measures to reduce the GHG emissions indicated that a 50-70% reduction of agricultural emissions by 2050 relative to 1990 is achievable, including mitigation measures in relation to the handling of manure and fertilisers, optimization of animal feeding, cropping practices, and land use changes with more organic farming, afforestation and energy crops. In addition, the bioenergy production may be increased significantly without reducing the food production, whereby Danish agriculture could achieve a positive energy balance.", "keywords": ["Buildings and machinery", "Greenhouse Effect", "Landscape and recreation", "Livestock", "Denmark", "Nitrous Oxide", "Air and water emissions", "Models", " Biological", "7. Clean energy", "01 natural sciences", "12. Responsible consumption", "Soil", "11. Sustainability", "Farm nutrient management", "Animals", "Animal Husbandry", "Fertilizers", "0105 earth and related environmental sciences", "2. Zero hunger", "Air Pollutants", "Nutrient turnover", "Agriculture", "04 agricultural and veterinary sciences", "Carbon Dioxide", "15. Life on land", "Manure", "13. Climate action", "0401 agriculture", " forestry", " and fisheries", "Environmental Monitoring"]}, "links": [{"href": "https://doi.org/10.1016/j.envpol.2011.02.024"}, {"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.2011.02.024", "name": "item", "description": "10.1016/j.envpol.2011.02.024", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.1016/j.envpol.2011.02.024"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2011-11-01T00:00:00Z"}}, {"id": "10.1016/j.geoderma.2025.117216", "type": "Feature", "geometry": null, "properties": {"updated": "2026-10-06T16:16:20Z", "type": "Journal Article", "created": "2025-02-17", "title": "Digital mapping of peat thickness and extent in Finland using remote sensing and machine learning", "description": "Accurate data on peat extent and thickness is essential for managing drained peatlands and reducing greenhouse gas emissions. Machine learning-based digital soil mapping offers an effective approach for large-scale peat occurrence prediction. In this study, we present a workflow for producing peat occurrence maps for the whole of Finland. For this, we used random forest classification to map areas with peat thicknesses of\u00a0\u2265\u00a010\u00a0cm, \u226530\u00a0cm, \u226540\u00a0cm, and\u00a0>\u00a060\u00a0cm. The input data consisted of 3.5 million point observations and 188 feature rasters from various sources. We carefully split the reference data into training and test sets, allowing for independent and robust model validation. Feature selection included an initial screening for multicollinearity using correlation-based feature pruning, followed by final selection using a genetic algorithm. Feature importance was evaluated using permutation importance and SHAP values. The resulting models utilized 26\u201333 features, achieving overall accuracies and F1-scores between 86\u201395\u00a0% and 0.82\u20130.95, respectively. The most important features included soil wetness indices, terrain roughness indices, and natural gamma radiation. Additionally, we provided an approach for evaluating spatial prediction uncertainty based on the models\u2019 internal prediction agreement. Compared to existing superficial deposit maps, our peat predictions significantly improve the spatial detail of peatlands at the national level, offering new opportunities for land use planning and emission mitigation. Our exceptionally comprehensive approach is broadly applicable, offering new insights into optimizing machine learning-based digital peatland mapping, particularly through refining feature selection to account for local conditions and enhance prediction accuracy.", "keywords": ["550", "Peatland", "Science", "Peat thickness", "Q", "Remote sensing", "630", "remote sensing", "machine learning", "Digital soil mapping", "Machine learning", "Feature selection", "Nation-wide dataset", "Uncertainty quantification"]}, "links": [{"href": "https://doi.org/10.1016/j.geoderma.2025.117216"}, {"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.2025.117216", "name": "item", "description": "10.1016/j.geoderma.2025.117216", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.1016/j.geoderma.2025.117216"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2025-03-01T00:00:00Z"}}, {"id": "10.1016/j.iswcr.2024.10.002", "type": "Feature", "geometry": null, "properties": {"updated": "2026-10-06T16:16:22Z", "type": "Journal Article", "created": "2024-10-09", "title": "Visible, near-infrared, and shortwave-infrared spectra as an input variable for digital mapping of soil organic carbon", "description": "This study proposes a novel methodology to employ discrete point spectra as input variable for digital mapping of soil organic carbon (SOC). Accordingly, two SOC modeling approaches were used in three agricultural sites in Czech Republic: i) machine learning (ML) including partial least squares regression (PLSR), cubist, random forest (RF), and support vector regression (SVR), and ii) regression kriging (RK) by the combination of ordinary kriging (OK) and PLSR (PLSR-K), cubist (cubist-K), RF (RF-K), and SVR (SVR-K). Models were developed on environmental predictor covariates (EPCs) and thirty genetic algorithms (GA)-selected visible, near-infrared, and shortwave-infrared (VNIR\u2013SWIR) wavelengths spectra, individually and combined. Thirty rasters were then created using interpolation of the selected spectra and served as the input variables \u2013 with and without EPCs \u2013 to test and compare the developed models and SOC predictive maps with each other and with those retrieved from the third approach: iii) kriging using OK of the measured and ML-predicted SOC. The impact of employing selected wavelengths\u2019 spectra and EPCs on models' performance was investigated using independent test samples and the uncertainty associated with the produced maps. Using interpolated spectra as the only input variable yielded a relatively acceptable accuracy (Nov\u00e1 Ves: RMSE\u00a0=\u00a00.19%, \u00dadrnice: RMSE\u00a0=\u00a00.12%, Klu\u010dov: RMSE\u00a0=\u00a00.13%). In comparison, the interpolated spectra coupled with EPCs enhanced the results. Regarding the uncertainty, however, the ML-based SOC maps were more reliable, than RK-based ones. Furthermore, maps produced using both spectra and EPCs showed less uncertainty than those constructed on the individual datasets.", "keywords": ["SOC modeling and mapping", "Regression kriging", "EJP SOIL", "ProbeField", "550", "Interpolated spectra", "EJPSOIL", "Machine learning", "Uncertainty", "TA1-2040", "Engineering (General). Civil engineering (General)"]}, "links": [{"href": "https://doi.org/10.1016/j.iswcr.2024.10.002"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/International%20Soil%20and%20Water%20Conservation%20Research", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.1016/j.iswcr.2024.10.002", "name": "item", "description": "10.1016/j.iswcr.2024.10.002", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.1016/j.iswcr.2024.10.002"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2025-03-01T00:00:00Z"}}, {"id": "10.1016/j.still.2011.01.001", "type": "Feature", "geometry": null, "properties": {"updated": "2026-10-06T16:16:53Z", "type": "Journal Article", "created": "2011-02-04", "title": "Determination Of The Quality Index Of A Paleudult Under Sunflower Culture And Different Management Systems", "description": "Soil is an essential resource for life and its properties are susceptible to be modified by tillage systems. The impact of management practices on soil functions can be assessed through a soil quality index. It is interesting to assess soil quality in different soil types. Therefore, the aim of this study was to determine the soil quality index of a Paleudult under different management conditions and sunflower culture. The experiment was carried out in Botucatu (SP, Brazil), in an 11-year non-tilled area used for growing soybean and maize during summer and black oat or triticale in winter. Four management systems were considered: no-tillage with a hoe planter (NTh), no-tillage with a double-disk planter (NTd), reduced tillage (RT) and conventional tillage (CT). Soil samples were taken from the planting lines at harvest time. To determine the soil quality indices, following the methodology proposed by Karlen and Stott (1994), three main soil functions were assessed: soil capacity for root development, water storage capacity of the soil and nutrient supply capacity of the soil. The studied Paleudult was considered a soil with good quality under all the observed management systems. However, the soil quality indices varied between treatments being 0.64, 0.68, 0.86 and 0.79 under NTh, NTd, RT and CT, respectively. Physical attributes such as resistance to penetration and macroporosity increased the soil quality index in RT and CT compared to NTh and NTd. The soil quality indices obtained suggested that the evaluated soil is adequate for sunflower production under our study conditions. In view of the SQI values, RT is the most suitable management for this site since it preserves soil quality and provides an acceptable sunflower yield.", "keywords": ["Yield", "Sao Paulo [Brazil]", "Glycine max", "Avena strigosa", "maize", "Triticosecale", "Zea mays", "01 natural sciences", "Soil quality", "soil type", "Soil health", "Sustainable development", "Rating", "soybean", "Agricultural machinery", "Productivity", "macropore", "0105 earth and related environmental sciences", "2. Zero hunger", "soil nutrient", "Agriculture", "water storage", "04 agricultural and veterinary sciences", "crop yield", "15. Life on land", "Quality assurance", "6. Clean water", "Management", "Soil productivity", "Fish", "Sustainability", "Indicators of soil quality", "Botucatu", "tillage", "Soils", "dicotyledon", "Helianthus", "0401 agriculture", " forestry", " and fisheries", "Brazil"]}, "links": [{"href": "https://doi.org/10.1016/j.still.2011.01.001"}, {"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.2011.01.001", "name": "item", "description": "10.1016/j.still.2011.01.001", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.1016/j.still.2011.01.001"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2011-04-01T00:00:00Z"}}, {"id": "10.1016/j.jsv.2021.116196", "type": "Feature", "geometry": null, "properties": {"updated": "2026-10-06T16:16:29Z", "type": "Journal Article", "created": "2021-05-10", "title": "Structural identification with physics-informed neural ordinary differential equations", "description": "Open AccessISSN:0022-460X", "keywords": ["Scientific machine learning", "Structural damage detection", "Neural ordinary differential equations", "Structural health monitoring", "0202 electrical engineering", " electronic engineering", " information engineering", "02 engineering and technology", "Discrepancy modeling", "Physics-informed machine learning", "Structural identification", "0201 civil engineering"]}, "links": [{"href": "https://doi.org/10.1016/j.jsv.2021.116196"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Journal%20of%20Sound%20and%20Vibration", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.1016/j.jsv.2021.116196", "name": "item", "description": "10.1016/j.jsv.2021.116196", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.1016/j.jsv.2021.116196"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2021-09-01T00:00:00Z"}}, {"id": "10.1016/j.proeng.2017.09.509", "type": "Feature", "geometry": null, "properties": {"updated": "2026-10-06T16:16:32Z", "type": "Journal Article", "created": "2017-09-12", "title": "Fatigue assessment of a wind turbine blade when output from multiple aero-elastic simulators are available", "description": "Open AccessAero-elasticity is a term that refers to the interaction between the aerodynamic, inertial and elastic loads when a structure is exposed to fluid flow such as turbulent wind inflow. Various commercial and research-based simulators are available to compute the wind turbine aero-elastic loads. These aero-elastic simulators are of varying complexity and might bear different underlying assumptions, pertaining to physics, mathematical and computational formulations. However, currently established practice dictates that the adopted aero-elastic simulators are verified and validated on the basis of measurements from test wind turbines. As a result, it is generally hard to establish one simulator as superior to another in terms of their predicted output. The objective in this paper is to statistically aggregate the fatigue load on a wind turbine blade when simultaneous simulations are performed using multiple simulators. The simulators of the wind turbine blade are of varying fidelity, and uncertainty in the modelling and assumptions on the model inputs are implicitly included, and taken into account in the statistical analysis. The main concept followed here is that rather than treating the output of the simulators as individual information sources, we consider them as part of an ensemble, which can be clustered and then aggregated to predict the \u201cmost likely\u201d fatigue load, hence reducing the inherent model-form uncertainty.", "keywords": ["Finite elements", "Uncertainty", "Wind turbine; Aeroelasticity; Uncertainty; Fatigue; Ensemble Aggregation; Data fusion; Finite elements; Machine learning", "02 engineering and technology", "Data fusion", "7. Clean energy", "01 natural sciences", "0201 civil engineering", "Ensemble Aggregation", "Machine learning", "Aeroelasticity", "0101 mathematics", "Wind turbine", "Fatigue"]}, "links": [{"href": "https://doi.org/10.1016/j.proeng.2017.09.509"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Procedia%20Engineering", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.1016/j.proeng.2017.09.509", "name": "item", "description": "10.1016/j.proeng.2017.09.509", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.1016/j.proeng.2017.09.509"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2017-01-01T00:00:00Z"}}, {"id": "10.1016/j.scitotenv.2021.152880", "type": "Feature", "geometry": null, "properties": {"updated": "2026-10-06T16:16:37Z", "type": "Journal Article", "created": "2022-01-06", "title": "Exploring the potential role of environmental and multi-source satellite data in crop yield prediction across Northeast China", "description": "Open AccessLe d\u00e9veloppement d'un syst\u00e8me pr\u00e9cis de pr\u00e9diction du rendement des cultures \u00e0 grande \u00e9chelle est d'une importance primordiale pour la gestion des ressources agricoles et la s\u00e9curit\u00e9 alimentaire mondiale. L'observation de la Terre fournit une source unique d'informations pour surveiller les cultures \u00e0 partir d'une diversit\u00e9 de gammes spectrales. Cependant, l'utilisation int\u00e9gr\u00e9e de ces donn\u00e9es et de leurs valeurs dans la pr\u00e9diction du rendement des cultures est encore peu \u00e9tudi\u00e9e. Ici, nous avons propos\u00e9 la combinaison de donn\u00e9es environnementales (climat, sol, g\u00e9ographie et topographie) avec de multiples donn\u00e9es satellitaires (indices de v\u00e9g\u00e9tation optiques, fluorescence induite par le soleil (SIF), temp\u00e9rature de surface du sol (LST) et profondeur optique de la v\u00e9g\u00e9tation micro-ondes (VOD)) dans le cadre pour estimer le rendement des cultures de ma\u00efs, de riz et de soja dans le nord-est de la Chine, et leur valeur unique et leur influence relative sur la pr\u00e9diction du rendement ont \u00e9t\u00e9 \u00e9valu\u00e9es. Deux m\u00e9thodes de r\u00e9gression lin\u00e9aire, trois m\u00e9thodes d'apprentissage automatique (ML) et un mod\u00e8le d'ensemble ML ont \u00e9t\u00e9 adopt\u00e9s pour construire des mod\u00e8les de pr\u00e9diction de rendement. Les r\u00e9sultats ont montr\u00e9 que les m\u00e9thodes individuelles de ML surpassaient les m\u00e9thodes de r\u00e9gression lin\u00e9aire, le mod\u00e8le d'ensemble de ML a encore am\u00e9lior\u00e9 les mod\u00e8les de ML uniques. De plus, les mod\u00e8les avec plus d'intrants ont obtenu de meilleures performances, la combinaison de donn\u00e9es satellitaires avec des donn\u00e9es environnementales, qui expliquaient respectivement 72\u00a0%, 69\u00a0% et 57\u00a0% de la variabilit\u00e9 du rendement du ma\u00efs, du riz et du soja, a d\u00e9montr\u00e9 des performances de pr\u00e9diction du rendement sup\u00e9rieures \u00e0 celles des intrants individuels. Alors que les donn\u00e9es satellitaires ont contribu\u00e9 \u00e0 la pr\u00e9diction du rendement des cultures principalement au d\u00e9but de la pointe de la saison de croissance, les donn\u00e9es climatiques ont fourni des informations suppl\u00e9mentaires principalement \u00e0 la pointe de la fin de la saison. Nous avons \u00e9galement constat\u00e9 que l'utilisation combin\u00e9e de l'IVE, du LST et du SIF a am\u00e9lior\u00e9 la pr\u00e9cision du mod\u00e8le par rapport au mod\u00e8le d'IVE de r\u00e9f\u00e9rence. Cependant, les indices de v\u00e9g\u00e9tation bas\u00e9s sur l'optique partageaient des informations similaires et ne fournissaient pas beaucoup d'informations suppl\u00e9mentaires au-del\u00e0 de l'IVE. Les pr\u00e9visions de rendement en cours de saison ont montr\u00e9 que les rendements des cultures peuvent \u00eatre pr\u00e9vus de mani\u00e8re satisfaisante deux \u00e0 trois mois avant la r\u00e9colte. La g\u00e9ographie, la topographie, la VOD, l'IVE, les param\u00e8tres hydrauliques du sol et les param\u00e8tres nutritifs sont plus importants pour la pr\u00e9diction du rendement des cultures.", "keywords": ["Atmospheric sciences", "Climate", "Multi-source satellite data", "Normalized Difference Vegetation Index", "Engineering", "Pathology", "Climate change", "Urban Heat Islands and Mitigation Strategies", "Linear regression", "2. Zero hunger", "Global and Planetary Change", "Vegetation Monitoring", "Ecology", "Geography", "Statistics", "Agriculture", "Geology", "Remote Sensing in Vegetation Monitoring and Phenology", "04 agricultural and veterinary sciences", "Remote sensing", "Aerospace engineering", "Archaeology", "Physical Sciences", "Metallurgy", "Medicine", "Seasons", "Global Vegetation Models", "Biomass Estimation", "Regression analysis", "Vegetation (pathology)", "Crops", " Agricultural", "Environmental Engineering", "Environmental data", "Yield (engineering)", "Zea mays", "Environmental science", "Machine learning", "FOS: Mathematics", "Crop yield", "Biology", "Global Forest Drought Response and Climate Change", "FOS: Environmental engineering", "Predictive modelling", "Food security", "FOS: Earth and related environmental sciences", "15. Life on land", "Agronomy", "Materials science", "Yield prediction", "Satellite", "13. Climate action", "FOS: Biological sciences", "Environmental Science", "Growing season", "0401 agriculture", " forestry", " and fisheries", "Mathematics"], "contacts": [{"organization": "Zhenwang Li, Lei Ding, Donghui Xu,", "roles": ["creator"]}]}, "links": [{"href": "https://doi.org/10.1016/j.scitotenv.2021.152880"}, {"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.2021.152880", "name": "item", "description": "10.1016/j.scitotenv.2021.152880", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.1016/j.scitotenv.2021.152880"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2022-04-01T00:00:00Z"}}, {"id": "10.1016/j.scitotenv.2022.156582", "type": "Feature", "geometry": null, "properties": {"updated": "2026-10-06T16:16:37Z", "type": "Journal Article", "created": "2022-06-14", "title": "Potential of visible and near infrared spectroscopy coupled with machine learning for predicting soil metal concentrations at the regional scale", "description": "Chemical analytical methods for metal analysis in soils are laborious, time-consuming and costly. This paper aims to evaluate the potential of short-range (SR) and full-range (FR) visible and infrared spectroscopy (vis-NIR) combined with linear and nonlinear calibration methods to estimate concentrations of nickel (Ni), cobalt (Co), cadmium (Cd), lead (Pb) and copper (Cu) in soils. A total of 435 soil samples were collected over agricultural sites, forest (7 %), pasture (5 %) and fallow land across a region in the northern part of Belgium. Generally, better predictions were obtained when using partial least squares regression (PLSR) and nonlinear calibration method [i.e., random forest (RF)] for processing of the spectral data, than when using support vector machine (SVM). FR generally outperformed SR and provided the best prediction results for Ni (R<sup>2</sup><sub>p</sub> = 0.76), Co (R<sup>2</sup><sub>p</sub> = 0.77), Cd (R<sup>2</sup><sub>p</sub> = 0.64) and Pb (R<sup>2</sup><sub>p</sub> = 0.65), when using PLSR and RF. SVM produced the best prediction result only for Pb (R<sup>2</sup><sub>p</sub> = 0.57) using the SR spectra. The metals Ni, Co, Cd and Pb can be predicted successfully (good accuracy) from the FR vis-NIR spectra using PLSR for Co, and RF for Ni, Cd, Pb and Cu. Compared to the FR spectrophotometer, improvement in accuracy was obtained for Cd and Co, using the SR spectra when combined with PLSR and RF, respectively. It is concluded that the SR spectrometer can be used successfully for the prediction of Co with RF (R<sup>2</sup><sub>p</sub> = 0.70), while it best predicted Cd with PLSR with an R<sup>2</sup><sub>p</sub> value of 0.67, which is of value for regional survey.", "keywords": ["Spectroscopy", " Near-Infrared", "Support Vector Machine", "RANGE", "Machine", "Machine learning modelling", "learning modelling", "REFLECTANCE SPECTROSCOPY", "CONTAMINATION", "Soil", "Lead", "Soil contamination", "Nickel", "Metals", "Earth and Environmental Sciences", "Soil Pollutants", "Chemometrics", "Cadmium", "Near-infrared spectra"]}, "links": [{"href": "https://doi.org/10.1016/j.scitotenv.2022.156582"}, {"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.2022.156582", "name": "item", "description": "10.1016/j.scitotenv.2022.156582", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.1016/j.scitotenv.2022.156582"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2022-10-01T00:00:00Z"}}, {"id": "10.1016/j.srs.2024.100118", "type": "Feature", "geometry": null, "properties": {"updated": "2026-10-06T16:16:48Z", "type": "Journal Article", "created": "2024-01-28", "title": "Satellite-based soil organic carbon mapping on European soils using available datasets and support sampling", "description": "Soil organic carbon (SOC) plays a major role in the global carbon cycle and is an important factor for soil health and fertility. Accurate mapping of SOC and other influencing parameters are crucial to guide the optimization of agricultural land management to maintain and restore soil health, to increase soil fertility, and thus to quantify its potential for sequestering CO2. Remote sensing and machine learning techniques offer promising approaches for predicting SOC distribution. In this study, we used remote sensing data and machine learning algorithms to map SOC at regional to large scale, which we then combined with temporospatial and spectral signature-based soil sampling to integrate local ground measurements. A rigorous validation approach was performed where several independent unseen datasets with a high number of samples were used, which additionally involved densely sampled fields. We found that our approach could predict SOC with an average percentage error of less than 10\u00a0% with an R2 of 0.91 using support sampling on croplands located on mineral soils, demonstrating the potential of remote sensing, machine learning, and specific ground measurements for mapping SOC. Our results suggest that this approach could make small carbon differences measurable and inform carbon sequestration efforts and improve our understanding of the impacts of land use and field management practices on soil carbon cycling.", "keywords": ["2. Zero hunger", "Physical geography", "Precision agriculture", "Science", "Q", "04 agricultural and veterinary sciences", "Remote sensing", "15. Life on land", "01 natural sciences", "GB3-5030", "13. Climate action", "Soil health", "Machine learning", "Soil carbon mapping", "0401 agriculture", " forestry", " and fisheries", "Soil carbon sequestration", "0105 earth and related environmental sciences"]}, "links": [{"href": "https://doi.org/10.1016/j.srs.2024.100118"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Science%20of%20Remote%20Sensing", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.1016/j.srs.2024.100118", "name": "item", "description": "10.1016/j.srs.2024.100118", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.1016/j.srs.2024.100118"}, {"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.still.2018.05.016", "type": "Feature", "geometry": null, "properties": {"updated": "2026-10-06T16:16:56Z", "type": "Journal Article", "created": "2018-06-11", "title": "The Benefits Of Conservation Agriculture On Soil Organic Carbon And Yield In Southern Africa Are Site-Specific", "description": "Abstract   Conservation agriculture (CA), with reduced tillage, permanent soil cover and diversified cropping systems, is advocated in southern Africa to improve soil quality, reduce input costs and mitigate climate-induced risks. However, improvements in terms of yield and soil organic carbon (SOC) under CA are slow and variable and many small-scale farmers are unable to buffer themselves against potential short-term financial losses. In this study we examined the effects of CA-related management practices on SOC sequestration and productivity at two medium-term sites on a sandy soil (eight year trial) and clay soil (six years) in maize producing areas of South Africa. Using field data, current input costs and market prices for crops, we calculated the gross margin for each system. Treatments compared conventional ploughing under maize monoculture with reduced tillage, intercropping and crop rotation. On the clay soil, SOC was increased under reduced tillage (57.6\u202ft C ha\u22121) compared to conventional tillage (54.9\u202ft C ha\u22121) while there was no difference for the sandy soil (19.7\u202ft C ha\u22121 average across treatments). Profitability was most strongly influenced by seasonal rainfall, but was higher on the sandy soil than the clay soil, with an average gross margin of R11,344 ha\u22121 and R5,686 ha\u22121, respectively. This study has demonstrated that while certain CA practices can create site-specific benefits for farmers, it is highly dependent on local weather and soil conditions. For the clay soil an additional payment scheme would be required to reward farmers in southern Africa for C-sequestration to make CA profitable and achieve increased C-mitigation through soil sequestration.", "keywords": ["2. Zero hunger", "Conservation agriculture (CA)", "Losses", "Cropping systems", "Soil organic carbon (SOC)", "Crops", "Small-scale farmers", "04 agricultural and veterinary sciences", "15. Life on land", "Zea mays", "Maize", "Costs", "Intercropping", "Crop rotation", "Soil conservation", "Sand", "Monoculture", "Reduced tillage", "Soil conditions", "Clay", "0401 agriculture", " forestry", " and fisheries", "Profitability", "Agricultural machinery", "Organic carbon"]}, "links": [{"href": "https://doi.org/10.1016/j.still.2018.05.016"}, {"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.2018.05.016", "name": "item", "description": "10.1016/j.still.2018.05.016", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.1016/j.still.2018.05.016"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2018-11-01T00:00:00Z"}}, {"id": "10.1016/j.still.2013.02.008", "type": "Feature", "geometry": null, "properties": {"updated": "2026-10-06T16:16:54Z", "type": "Journal Article", "created": "2013-03-19", "title": "Cover Crops And No-Till Effects On Physical Fractions Of Soil Organic Matter", "description": "Brazilian Agricultural Research Corporation (EMBRAPA) Rice and Beans Research Center, Santo Antonio de Goias, GO", "keywords": ["land use change", "Soil management", "Aggregates", "Millet", "fallow", "grass", "Cultivation", "Soil pollution", "soil depth", "Crops", "cover crop", "Plants (botany)", "soil organic matter", "Organic compounds", "soil quality", "zero tillage", "Agricultural machinery", "soil aggregate", "Panicum maximum", "2. Zero hunger", "soil surface", "rice", "Brachiaria brizantha", "Biological materials", "04 agricultural and veterinary sciences", "Biogeochemistry", "15. Life on land", "sustainability", "Agronomy", "Brachiaria ruziziensis", "13. Climate action", "Soils", "conservation tillage", "0401 agriculture", " forestry", " and fisheries", "total organic carbon", "plowing"]}, "links": [{"href": "https://doi.org/10.1016/j.still.2013.02.008"}, {"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.2013.02.008", "name": "item", "description": "10.1016/j.still.2013.02.008", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.1016/j.still.2013.02.008"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2013-06-01T00:00:00Z"}}, {"id": "10.1016/j.tifs.2021.10.002", "type": "Feature", "geometry": null, "properties": {"updated": "2026-10-06T16:16:57Z", "type": "Journal Article", "created": "2021-10-07", "title": "Vegetable waste and by-products to feed a healthy gut microbiota: current evidence, machine learning and computational tools to design novel microbiome-targeted foods", "description": "[Background] Food waste management is a key issue to global food security and friendly environmental governance. Worldwide, one-third of food produced for human consumption is lost or wasted along the food supply chain, primary production and food processing representing the most significant loses. Therefore, the need to achieve zero waste production schemes is becoming a priority to meet Sustainable Development Goals. Increasing evidence points towards vegetable food waste as a rich source of a wide array of carbohydrate structures and fibres providing the opportunity to identify and develop alternative approaches to valorize agro-food waste. [Scope and approach] This review describes the valorization of vegetable waste and by-products via production of (novel) substrates targeted to gut microbiota modulation, emphasizing the importance of raw materials and structural-functional properties of carbohydrates. Furthermore, we propose a novel framework for the rational selection of vegetable sources with potential prebiotic activity, based on machine learning and other computational tools applied to available literature and public database information. [Key findings and conclusions] Integration of the body of knowledge within the field of vegetable food waste valorization, from different perspectives, allows a rational selection of carbohydrate-based substrates with promising prebiotic activities. By exploring the interactions among dietary fibre and gut microbial ecosystems using computational tools fed with structural, functional and genomic data, we can identify substrates with potential to selectively stimulate gut commensals, in agreement with experimental evidence. Our approach establishes a new framework that can be extended to a wide range of commensal microbes and carbohydrate structures. The work in our research groups was funded by the European Union's Horizon 2020 research and innovation programme under grant agreement No 818368 (MASTER), and the grants RTI 2018-095021-J-I00 (funded by (MCIU/AEI/FEDER, UE), AGL 2017-84614-C2-1-R and AGL 2016-78311-R (funded by (MINECO/AEI/FEDER, UE). Carlos Sabater acknowledges his Postdoctoral research contract funded by the Instituto de Investigaci\u00f3n Sanitaria del Principado de Asturias (ISPA) and Postdoctoral research contract Juan de la Cierva-Formaci\u00f3n from Spanish Ministry of Science and Innovation (FJC 2019-042125-I). Peer reviewed", "keywords": ["2. Zero hunger", "0301 basic medicine", "0303 health sciences", "Circular economy", "Glycosidase activity", "15. Life on land", "6. Clean water", "Vegetable food waste valorization", "12. Responsible consumption", "03 medical and health sciences", "Prebiotics", "13. Climate action", "Machine learning", "11. Sustainability", "Microbiome"]}, "links": [{"href": "https://doi.org/10.1016/j.tifs.2021.10.002"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Trends%20in%20Food%20Science%20%26amp%3B%20Technology", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.1016/j.tifs.2021.10.002", "name": "item", "description": "10.1016/j.tifs.2021.10.002", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.1016/j.tifs.2021.10.002"}, {"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": "10.1029/2018jg004795", "type": "Feature", "geometry": null, "properties": {"updated": "2026-10-06T16:17:11Z", "type": "Journal Article", "created": "2019-04-09", "title": "Comparison With Global Soil Radiocarbon Observations Indicates Needed Carbon Cycle Improvements in the E3SM Land Model", "description": "Abstract<p>We evaluated global soil organic carbon (SOC) stocks and turnover time predictions from a global land model (ELMv1\uffe2\uff80\uff90ECA) integrated in an Earth System Model (E3SM) by comparing them with observed soil bulk and \uffce\uff9414C values around the world. We analyzed observed and simulated SOC stocks and \uffce\uff9414C values using machine learning methods at the Earth System Model grid cell scale (~200\uffc2\uffa0km). In grid cells with sufficient observations, the model provided reasonable estimates of soil carbon stocks across soil depth and \uffce\uff9414C values near the surface but underestimated \uffce\uff9414C at depth. Among many explanatory variables, soil albedo index, soil order, plant function type, air temperature, and SOC content were major factors affecting predicted SOC \uffce\uff9414C values. The influences of soil albedo index, soil order, and air temperature were primarily important in the shallow subsurface (\uffe2\uff89\uffa430\uffc2\uffa0cm). We also performed sensitivity studies using different vertical root distributions and decomposition turnover times and compared to observed SOC stock and \uffce\uff9414C profiles. The analyses support the role of vegetation in affecting soil carbon turnover, particularly in deep soil, possibly through supplying fresh carbon and degrading physical\uffe2\uff80\uff90chemical protection of SOC via root activities. Allowing for grid cell\uffe2\uff80\uff90specific rooting and decomposition rates substantially reduced discrepancies between observed and predicted \uffce\uff9414C values and SOC content. Our results highlight the need for more explicit representation of roots, microbes, and soil physical protection in land models.</p", "keywords": ["2. Zero hunger", "advanced land modeling", "Earth System Models", "3706 Geophysics (for-2020)", "15. Life on land", "01 natural sciences", "Climate Action", "soil organic carbon", "Geophysics", "37 Earth Sciences (for-2020)", "machine learning", "statistical analysis", "13. Climate action", "0404 Geophysics (for)", "Earth Sciences", "radiocarbon", "13 Climate Action (sdg)", "0105 earth and related environmental sciences"]}, "links": [{"href": "https://agupubs.onlinelibrary.wiley.com/doi/pdf/10.1029/2018JG004795"}, {"href": "https://escholarship.org/content/qt4h72t9fq/qt4h72t9fq.pdf"}, {"href": "https://doi.org/10.1029/2018jg004795"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Journal%20of%20Geophysical%20Research%3A%20Biogeosciences", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.1029/2018jg004795", "name": "item", "description": "10.1029/2018jg004795", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.1029/2018jg004795"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2019-05-01T00:00:00Z"}}, {"id": "10.1038/s41598-021-02302-2", "type": "Feature", "geometry": null, "properties": {"updated": "2026-10-06T16:17:20Z", "type": "Journal Article", "created": "2021-11-30", "title": "Predicting sensitivity of recently harvested tomatoes and tomato sepals to future fungal infections", "description": "Abstract<p>Tomato is an important commercial product which is perishable by nature and highly susceptible to fungal incidence once it is harvested. Not all tomatoes are equally vulnerable to pathogenic fungi, and an early detection of the vulnerable ones can help in taking timely preventive actions, ranging from isolating tomato batches to adjusting storage conditions, but also in making right business decisions like dynamic pricing based on quality or better shelf life estimate. More importantly, early detection of vulnerable produce can help in taking timely actions to minimize potential post-harvest losses. This paper investigates Near-infrared (NIR) hyperspectral imaging (1000\uffe2\uff80\uff931700\uffc2\uffa0nm) and machine learning to build models to automatically predict the susceptibility of sepals of recently harvested tomatoes to future fungal infections. Hyperspectral images of newly harvested tomatoes (cultivar Brioso) from 5 different growers were acquired before the onset of any visible fungal infection. After imaging, the tomatoes were placed under controlled conditions suited for fungal germination and growth for a 4-day period, and then imaged using normal color cameras. All sepals in the color images were ranked for fungal severity using crowdsourcing, and the final severity of each sepal was fused using principal component analysis. A novel hyperspectral data processing pipeline is presented which was used to automatically segment the tomato sepals from spectral images with multiple tomatoes connected via a truss. The key modelling question addressed in this research is whether there is a correlation between the hyperspectral data captured at harvest and the fungal infection observed 4 days later. Using 10-fold and group k-fold cross-validation, XG-Boost and Random Forest based regression models were trained on the features derived from the hyperspectral data corresponding to each sepal in the training set and tested on hold out test set. The best model found a Pearson correlation of 0.837, showing that there is strong linear correlation between the NIR spectra and the future fungal severity of the sepal. The sepal specific predictions were aggregated to predict the susceptibility of individual tomatoes, and a correlation of 0.92 was found. Besides modelling, focus is also on model interpretation, particularly to understand which spectral features are most relevant to model prediction. Two approaches to model interpretation were explored, feature importance and SHAP (SHapley Additive exPlanations), resulting in similar conclusions that the NIR range between 1390\uffe2\uff80\uff931420\uffc2\uffa0nm contributes most to the model\uffe2\uff80\uff99s final decision.</p", "keywords": ["Crops", " Agricultural", "2. Zero hunger", "0301 basic medicine", "Principal Component Analysis", "0303 health sciences", "Spectroscopy", " Near-Infrared", "Science", "Q", "R", "Reproducibility of Results", "Microbiology", "Article", "Pattern Recognition", " Automated", "Machine Learning", "03 medical and health sciences", "Deep Learning", "Solanum lycopersicum", "Fruit", "Calibration", "Life Science", "Medicine", "Algorithms", "Software", "Plant Diseases"]}, "links": [{"href": "https://www.nature.com/articles/s41598-021-02302-2.pdf"}, {"href": "https://doi.org/10.1038/s41598-021-02302-2"}, {"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/s41598-021-02302-2", "name": "item", "description": "10.1038/s41598-021-02302-2", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.1038/s41598-021-02302-2"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2021-11-30T00:00:00Z"}}, {"id": "10.1038/s41598-019-56868-z", "type": "Feature", "geometry": null, "properties": {"updated": "2026-10-06T16:17:20Z", "type": "Journal Article", "created": "2020-01-09", "title": "Modelling photovoltaic soiling losses through optical characterization", "description": "Abstract<p>The accumulation of soiling on photovoltaic (PV) modules affects PV systems worldwide. Soiling consists of mineral dust, soot particles, aerosols, pollen, fungi and/or other contaminants that deposit on the surface of PV modules. Soiling absorbs, scatters, and reflects a fraction of the incoming sunlight, reducing the intensity that reaches the active part of the solar cell. Here, we report on the comparison of naturally accumulated soiling on coupons of PV glass soiled at seven locations worldwide. The spectral hemispherical transmittance was measured. It was found that natural soiling disproportionately impacts the blue and ultraviolet (UV) portions of the spectrum compared to the visible and infrared (IR). Also, the general shape of the transmittance spectra was similar at all the studied sites and could adequately be described by a modified form of the \uffc3\uff85ngstr\uffc3\uffb6m turbidity equation. In addition, the distribution of particles sizes was found to follow the IEST-STD-CC 1246E cleanliness standard. The fractional coverage of the glass surface by particles could be determined directly or indirectly and, as expected, has a linear correlation with the transmittance. It thus becomes feasible to estimate the optical consequences of the soiling of PV modules from the particle size distribution and the cleanliness value.</p>", "keywords": ["Photovoltaic Arrays", "Cleanliness", "Particle", "PV", "02 engineering and technology", "Oceanography", "7. Clean energy", "soiling; experimental; transmittance; spectrum", "Turbidity", "Size", "Materials Science and Engineering", "\u00c5ngstr\u00f6m turbidity equation", "Transmittance", "0202 electrical engineering", " electronic engineering", " information engineering", "Photovoltaic system", "Ultraviolet", "Microscopy", "Soiling", "Energy", "Ecology", "Physics", "Q", "R", "Imaging and sensing", "Geology", "Particle size", "6. Clean water", "Photovoltaic Efficiency", "Chemistry", "Physical chemistry", "Particle (ecology)", "Physical Sciences", "Sunlight", "Medicine", "Infrared", "570", "Particle-size distribution", "PV System", "Energy science and technology", "Science", "Optical spectroscopy", "Partial Shading", "530", "Modelling", "Article", "Environmental science", "Techniques and instrumentation", "Optical physics", "Meteorology", "Artificial Intelligence", "Machine Learning Methods for Solar Radiation Forecasting", "Optical techniques", "Optoelectronics", "Aerosol", "Biology", "Renewable Energy", " Sustainability and the Environment", "Electronics", " photonics and device physics", "Building Integrated Photovoltaics", "Optics", "Photovoltaic Maximum Power Point Tracking Techniques", "FOS: Earth and related environmental sciences", "Materials science", "Photovoltaics", "Optics and photonics", "13. Climate action", "FOS: Biological sciences", "Computer Science", "Solar Thermal Energy Technologies"]}, "links": [{"href": "https://iris.uniroma1.it/bitstream/11573/1625670/2/Smestad_Modelling_2020.pdf"}, {"href": "https://www.nature.com/articles/s41598-019-56868-z.pdf"}, {"href": "https://doi.org/10.1038/s41598-019-56868-z"}, {"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/s41598-019-56868-z", "name": "item", "description": "10.1038/s41598-019-56868-z", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.1038/s41598-019-56868-z"}, {"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": "10.1039/d1ra03337a", "type": "Feature", "geometry": null, "properties": {"updated": "2026-10-06T16:17:23Z", "type": "Journal Article", "created": "2021-09-10", "title": "Exploring the performance of a functionalized CNT-based sensor array for breathomics through clustering and classification algorithms: from gas sensing of selective biomarkers to discrimination of chronic obstructive pulmonary disease", "description": "<?xml version='1.0' encoding='UTF-8'?><article><p>Extensive application of clustering and classification algorithms shows the potential of a CNT-based sensor array in breathomics.</p></article>", "keywords": ["electronic nose", "Linear discriminant analysis", "Principal component analysis", "Breath analysis", "02 engineering and technology", "sensors", "Supported Vectror Machine", "01 natural sciences", "nanotubes", "Ammonia; Biomarkers; Carbon nanotubes; Classification (of information); Clustering algorithms; Molecules; Nitrogen oxides; Principal component analysis; Sulfur compounds; Support vector machines", "0104 chemical sciences", "3. Good health", "breathomics", "Chemistry", "SWCNTs", "COPD", "ta318", "e-nose", "0210 nano-technology", "ta215"]}, "links": [{"href": "https://iris.cnr.it/bitstream/20.500.14243/536855/1/RSC%20Adv._2021.pdf"}, {"href": "https://boa.unimib.it/bitstream/10281/517427/2/d1ra03337a.pdf%3b"}, {"href": "https://publicatt.unicatt.it/bitstream/10807/190102/1/d1ra03337a.pdf"}, {"href": "http://pubs.rsc.org/en/content/articlepdf/2021/RA/D1RA03337A"}, {"href": "https://doi.org/10.1039/d1ra03337a"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/RSC%20Advances", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.1039/d1ra03337a", "name": "item", "description": "10.1039/d1ra03337a", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.1039/d1ra03337a"}, {"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": "10.1101/2023.12.16.572011", "type": "Feature", "geometry": null, "properties": {"updated": "2026-10-06T16:17:51Z", "type": "Journal Article", "created": "2023-12-18", "title": "Open Soil Spectral Library (OSSL): Building reproducible soil calibration models through open development and community engagement", "description": "Abstract<p>Soil spectroscopy is a widely used method for estimating soil properties that are important to environmental and agricultural monitoring. However, a bottleneck to its more widespread adoption is the need for establishing large reference datasets for training machine learning (ML) models, which are called soil spectral libraries (SSLs). Similarly, the prediction capacity of new samples is also subject to the number and diversity of soil types and conditions represented in the SSLs. To help bridge this gap and enable hundreds of stakeholders to collect more affordable soil data by leveraging a centralized open resource, the Soil Spectroscopy for Global Good has created the Open Soil Spectral Library (OSSL). In this paper, we describe the procedures for collecting and harmonizing several SSLs that are incorporated into the OSSL, followed by exploratory analysis and predictive modeling. The results of 10-fold cross-validation with refitting show that, in general, mid-infrared (MIR)-based models are significantly more accurate than visible and near-infrared (VisNIR) or near-infrared (NIR) models. From independent model evaluation, we found that Cubist comes out as the best-performing ML algorithm for the calibration and delivery of reliable outputs (prediction uncertainty and representation flag). Although many soil properties are well predicted, total sulfur, extractable sodium, and electrical conductivity performed poorly in all spectral regions, with some other extractable nutrients and physical soil properties also performing poorly in one or two spectral regions (VisNIR or Neospectra NIR). Hence, the use of predictive models based solely on spectral variations has limitations. This study also presents and discusses several other open resources that were developed from the OSSL, aspects of opening data, current limitations, and future development. With this genuinely open science project, we hope that OSSL becomes the driver of the soil spectroscopy community to accelerate the pace of scientific discovery and innovation.</p", "keywords": ["2. Zero hunger", "Science", "Spectrum Analysis", "Q", "R", "15. Life on land", "Machine Learning", "Soil", "13. Climate action", "Calibration", "Medicine", "Algorithms", "Research Article", "Environmental Monitoring"]}, "links": [{"href": "https://doi.org/10.1101/2023.12.16.572011"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/PLOS%20ONE", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.1101/2023.12.16.572011", "name": "item", "description": "10.1101/2023.12.16.572011", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.1101/2023.12.16.572011"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2023-12-17T00:00:00Z"}}, {"id": "10.1080/02827581.2018.1562567", "type": "Feature", "geometry": null, "properties": {"updated": "2026-10-06T16:17:39Z", "type": "Journal Article", "created": "2019-01-07", "title": "Predicting forwarder rut formation on fine-grained mineral soils", "description": "Predictive factors for forwarder rut formation were studied on fine-grained mineral soils. The study was carried out in southern Finland in mid-May, when the soil water contents were high after sno...", "keywords": ["fine-grained soil", "soil damage", "ta1171", "rut formation", "0401 agriculture", " forestry", " and fisheries", "penetration resistance", "04 agricultural and veterinary sciences", "volumetric water content", "15. Life on land", "ta4112", "forest machinery"]}, "links": [{"href": "https://www.tandfonline.com/doi/pdf/10.1080/02827581.2018.1562567"}, {"href": "https://doi.org/10.1080/02827581.2018.1562567"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Scandinavian%20Journal%20of%20Forest%20Research", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.1080/02827581.2018.1562567", "name": "item", "description": "10.1080/02827581.2018.1562567", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.1080/02827581.2018.1562567"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2019-01-06T00:00:00Z"}}, {"id": "10.1080/10106049.2025.2493741", "type": "Feature", "geometry": null, "properties": {"updated": "2026-10-06T16:17:40Z", "type": "Journal Article", "created": "2025-04-28", "title": "The model for grain wheat yield prediction at high spatial resolution based on physical-geographical properties and satellite vegetation indices", "description": "Precision agriculture is promising approach for improving agricultural production, especially nowadays when the population is rapidly increasing. For that, crop yield estimation provides valuable information. The main research focus was to predict within-field grain yield and detect its drivers. The Random Forest regression model on data from diverse sources at the 10-meter spatial resolution was developed. The study was conducted in the Vojvodina region (Serbia) for eight wheat-planted fields, having precise grain yield data. Open-source data including 15 vegetation indices (VIs) was calculated from Sentinel-2 satellite bands, physical-geographical features obtained from the digital elevation model and soil properties. The model succeeded in predicting the wheat grain yield with the RMSE of 0.66 t/ha (average yield of 0.09 t/ha) and the best predictors were VIs considering chlorophyll and moisture content in plants, while physical-geographical properties managed to explain within-field variability. This methodology can be applied to other crops (maize, soybean).", "keywords": ["Topography", "remote sensing", "Physical geography", "machine learning", "remotesensing", "wheat yield", "GB3-5030"], "contacts": [{"organization": "Blagojevi\u0107, Dragana, Pajevi\u0107, Nina, Mimi\u0107, Gordan, \u0106ukovi\u0107, Stefanija, Markovi\u0107, Slobodan B., Maestrini, Bernardo, Brdar, Sanja,", "roles": ["creator"]}]}, "links": [{"href": "https://doi.org/10.1080/10106049.2025.2493741"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Geocarto%20International", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.1080/10106049.2025.2493741", "name": "item", "description": "10.1080/10106049.2025.2493741", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.1080/10106049.2025.2493741"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2025-04-28T00:00:00Z"}}, {"id": "10.1080/1062936x.2023.2254225", "type": "Feature", "geometry": null, "properties": {"updated": "2026-10-06T16:17:41Z", "type": "Journal Article", "created": "2023-09-06", "title": "What is the ecotoxicity of a given chemical for a given aquatic species? Predicting interactions between species and chemicals using recommender system techniques", "description": "Ecotoxicological safety assessment of chemicals requires toxicity data on multiple species, despite the general desire of minimizing animal testing. Predictive models, specifically machine learning (ML) methods, are one of the tools capable of solving this apparent contradiction as they allow to generalize toxicity patterns across chemicals and species. However, despite the availability of large public toxicity datasets, the data is highly sparse, complicating model development. The aim of this study is to provide insights into how ML can predict toxicity using a large but sparse dataset. We developed models to predict LC50-values, based on experimental LC50-data covering 2431 organic chemicals and 1506 aquatic species from the ECOTOX-database. Several well-known ML techniques were evaluated and a new ML model was developed, inspired by recommender systems. This new model involves a simple linear model that learns low-rank interactions between species and chemicals using factorization machines. We evaluated the predictive performances of the developed models based on two validation settings: 1) predicting unseen chemical-species pairs, and 2) predicting unseen chemicals. The results of this study show that ML models can accurately predict LC50-values in both validation settings. Moreover, we show that the novel factorization machine approach can match well-tuned, complex, ML approaches.", "keywords": ["modelling", "Machine Learning", "machine learning", "Machine learning", "Animals", "Quantitative Structure-Activity Relationship", "prediction", "Ecotoxicology", "LC50", "aquatic toxicity", "species sensitivity"]}, "links": [{"href": "https://www.tandfonline.com/doi/pdf/10.1080/1062936X.2023.2254225"}, {"href": "https://doi.org/10.1080/1062936x.2023.2254225"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/SAR%20and%20QSAR%20in%20Environmental%20Research", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.1080/1062936x.2023.2254225", "name": "item", "description": "10.1080/1062936x.2023.2254225", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.1080/1062936x.2023.2254225"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2023-09-06T00:00:00Z"}}, {"id": "10.1080/10934520601015354", "type": "Feature", "geometry": null, "properties": {"updated": "2026-10-06T16:17:41Z", "type": "Journal Article", "created": "2006-11-27", "title": "A Comparison Of Greenhouse Gas Emissions From Inputs Into Farm Enterprises In Southeast Queensland, Australia", "description": "One of the assumptions underlying efforts to convert cropping land, especially marginal crop land, to plantations is that there will be a net reduction in greenhouse gas emissions, with a gas 'sink' replacing a high energy system in which the breakdown of biomass is routinely accelerated to prepare for new crops. This research, based on case studies in Kingaroy in southeast Queensland, compares the amount of greenhouse gas (GHGs) emissions from a peanut/maize crop rotation, a pasture system for beef production and a spotted gum (Corymbia citriodora) timber plantation. Three production inputs, fuel, farm machinery and agrochemicals (fertilizer, pesticides and herbicides) are considered. The study extends beyond the farm gate to include packing and transportation and the time period is 30 years. The results suggest that replacing the crops with plantations would indeed reduce emissions but that a pasture system would have even lower net emissions. These findings cast some doubt on the case for farm forestry as a relatively effective means of ameliorating greenhouse gas emissions.", "keywords": ["Greenhouse Effect", "2. Zero hunger", "Air Pollutants", "330", "Australia", "farm machines", "Agriculture", "04 agricultural and veterinary sciences", "15. Life on land", "7. Clean energy", "630", "12. Responsible consumption", "greenhouse gas", "13. Climate action", "Air Pollution", "fuels", "11. Sustainability", "0401 agriculture", " forestry", " and fisheries", "Gases", "Queensland", "Fertilizers", "Kingaroy", "agrochemicals", "Vehicle Emissions"]}, "links": [{"href": "https://doi.org/10.1080/10934520601015354"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Journal%20of%20Environmental%20Science%20and%20Health%2C%20Part%20A", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.1080/10934520601015354", "name": "item", "description": "10.1080/10934520601015354", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.1080/10934520601015354"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2007-05-07T00:00:00Z"}}, {"id": "10.1080/14942119.2018.1419677", "type": "Feature", "geometry": null, "properties": {"updated": "2026-10-06T16:17:41Z", "type": "Journal Article", "created": "2018-01-24", "title": "Wheel rut measurements by forest machine-mounted LiDAR sensors \u2013 accuracy and potential for operational applications?", "description": "ABSTRACTSoil rutting caused by forest operations has negative economic and ecological effects and thus limits for rutting are set by forest laws and sustainability criteria. Extensive data on rut depths are necessary for post-harvest quality control and development of models that link environmental conditions to rut formation. This study explored the use of a Light Detection and Ranging (LiDAR) sensor mounted on a forest harvester and forwarder to measure rut depths in real harvesting conditions in Southern Finland. LiDAR-derived rut depths were compared to manually measured rut depths. The results showed that at 10\u201320\u00a0m spatial resolution, the LiDAR method can provide unbiased estimates of rut depth with root mean square error (RMSE) < 3.5 cm compared to the manual rut depth measurements. The results suggest that a LiDAR sensor mounted on a forest vehicle can in future provide a viable method for the large-scale collection of rut depth data as part of normal forestry operations.", "keywords": ["forest trafficability", "ta113", "550", "forest machine instrumentation", "0401 agriculture", " forestry", " and fisheries", "04 agricultural and veterinary sciences", "LIDAR sensor", "15. Life on land", "sensors", "ta4112", "rut measurement", "rut depth", "620"]}, "links": [{"href": "https://www.tandfonline.com/doi/pdf/10.1080/14942119.2018.1419677"}, {"href": "https://doi.org/10.1080/14942119.2018.1419677"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/International%20Journal%20of%20Forest%20Engineering", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.1080/14942119.2018.1419677", "name": "item", "description": "10.1080/14942119.2018.1419677", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.1080/14942119.2018.1419677"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2018-01-02T00:00:00Z"}}, {"id": "10.1088/1748-9326/adfe83", "type": "Feature", "geometry": null, "properties": {"updated": "2026-10-06T16:17:44Z", "type": "Journal Article", "created": "2025-09-02", "title": "Mining global soil carbon datasets: can modern machine learning uncover the missing pieces of process-based models?", "description": "Abstract                <p>The future of terrestrial soil carbon stocks plays a crucial role in climate change prediction. Modern machine learning techniques are now widely applied in soil science to predict the spatial distribution of soil properties from observational data. Beyond prediction, the use of machine learning as a data-mining tool offers a promising pathway for improving soil carbon modelling and refining projections of climate\uffe2\uff80\uff93carbon feedbacks. In this paper, we review recent advances in the application of machine learning to global soil carbon modelling as a data-mining tool and highlight its potential to drive an iterative feedback loop that improves the representation of soil carbon dynamics in Earth System Models.</p", "keywords": ["machine learning", "data-mining", "global soil carbon map", "global soil carbon modelling", "[SDE.IE] Environmental Sciences/Environmental Engineering", "[INFO.INFO-LG] Computer Science [cs]/Machine Learning [cs.LG]", "FairCarboN", "[PHYS.PHYS.PHYS-DATA-AN] Physics [physics]/Physics [physics]/Data Analysis", " Statistics and Probability [physics.data-an]", "[SDU.ENVI] Sciences of the Universe [physics]/Continental interfaces", " environment"]}, "links": [{"href": "https://doi.org/10.1088/1748-9326/adfe83"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Environmental%20Research%20Letters", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.1088/1748-9326/adfe83", "name": "item", "description": "10.1088/1748-9326/adfe83", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.1088/1748-9326/adfe83"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2025-09-02T00:00:00Z"}}, {"id": "10.3390/rs14030541", "type": "Feature", "geometry": null, "properties": {"updated": "2026-10-06T16:19:45Z", "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": "10.1109/access.2023.3339884", "type": "Feature", "geometry": null, "properties": {"updated": "2026-10-06T16:17:53Z", "type": "Journal Article", "created": "2023-12-05", "title": "Classifying the Vermicompost Production Stages Using Thermal Camera Data", "description": "The procedure of processing the vermicompost production includes several stages, where the vermicompost material has different temperatures during these different stages. Thermal sensors play a key role in numerous fields, such as medical and agricultural applications. Thermal cameras can produce a thermal image or an array of values representing the array of sensory data. i.e., an array of temperatures. In this study, we proposed the first thermal imagery dataset of the vermicompost production process. The contributions of this work are two-fold using the proposed dataset. First, we framed the process of predicting the vermicompost production process as a classification problem. Second, we compared classifying the different stages of the process of vermicompost production based on two different input types, namely, thermal images and an array of temperatures. In other words, the classifier will be fed with an input (an image or an array of temperatures), and then the classifier will predict the vermicompost production stage. In this context, we utilized several machine and deep learning models as classifiers. For the utilized dataset, the study has been conducted on a set of images collected during the vermicompost production procedure which was collected every 14 days over 42 consecutive days, i.e., four classes. We proposed running a series of experiments to determine which input type yields better classification accuracy. The obtained results show that using thermal images for the sake of classifying the vermicompost production stages achieved higher accuracy, about 92&#x0025;, in comparison to using the sensor array data, about 60&#x0025;.", "keywords": ["machine learning", "SENet", "deep learning", "Electrical engineering. Electronics. Nuclear engineering", "sensor array", "Classification", "ResNet", "TK1-9971"]}, "links": [{"href": "https://doi.org/10.1109/access.2023.3339884"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/IEEE%20Access", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.1109/access.2023.3339884", "name": "item", "description": "10.1109/access.2023.3339884", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.1109/access.2023.3339884"}, {"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": "10.1109/jstars.2024.3422494", "type": "Feature", "geometry": null, "properties": {"updated": "2026-10-06T16:17:54Z", "type": "Journal Article", "created": "2024-07-03", "title": "Soil Texture and pH Mapping Using Remote Sensing and Support Sampling", "description": "Soil pH and texture are valuable information for agriculture, supporting the achievement of high productivity and low environmental impact, which is the basis for sustainable agricultural production. In this study, we present novel soil mapping techniques that integrate high-spatial-resolution satellite and ground data, surpassing traditional methods in precision and reliability. By synergizing remote sensing data, including polarimetric synthetic aperture and multispectral imagery, with climate and terrain information, alongside coarse-resolution soil data, we achieved high accuracy, with an average error of less than 6&#x0025;, in predicting soil pH and texture parameters. Notably, the approach allows for detailed mapping at the pixel level, revealing nuanced variability within 10&#x00D7;10 m field pixels. Considering the accuracy, the method establishes itself as a benchmark for field management guidelines integrating a precision sampling approach, offering actual and high spatial resolution information crucial for sustainable agricultural practices. This holistic approach allows new opportunities to revolutionize soil management practices, facilitating variable rate applications, soil moisture, and fertilization mapping and ultimately enhancing agri-environmental sustainability.", "keywords": ["2. Zero hunger", "precision agriculture", "STEROPES", "soil health", "QC801-809", "Geophysics. Cosmic physics", "Machine learning (ML)", "04 agricultural and veterinary sciences", "Remote sensing", "15. Life on land", "01 natural sciences", "soil mapping", "12. Responsible consumption", "Machine Learning", "Ocean engineering", "remote sensing", "13. Climate action", "0401 agriculture", " forestry", " and fisheries", "TC1501-1800", "0105 earth and related environmental sciences"], "contacts": [{"organization": "Y\u00fcz\u00fcg\u00fcll\u00fc, Onur, Fajraoui, Noura, Liebisch, Frank,", "roles": ["creator"]}]}, "links": [{"href": "https://doi.org/10.1109/jstars.2024.3422494"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/IEEE%20Journal%20of%20Selected%20Topics%20in%20Applied%20Earth%20Observations%20and%20Remote%20Sensing", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.1109/jstars.2024.3422494", "name": "item", "description": "10.1109/jstars.2024.3422494", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.1109/jstars.2024.3422494"}, {"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": "10.1111/gcb.15817", "type": "Feature", "geometry": null, "properties": {"updated": "2026-10-06T16:18:02Z", "type": "Journal Article", "created": "2021-08-05", "title": "Predicting ecosystem responses by data\u2010driven reciprocal modelling", "description": "Abstract<p>Treatment effects are traditionally quantified in controlled experiments. However, experimental control is often achieved at the expense of representativeness. Here, we present a data\uffe2\uff80\uff90driven reciprocal modelling framework to quantify the individual effects of environmental treatments under field conditions. The framework requires a representative survey data set describing the treatment (A or B), its responding target variable and other environmental properties that cause variability of the target within the region or population studied. A machine learning model is trained to predict the target only based on observations in group A. This model is then applied to group B, with predictions restricted to the model's space of applicability. The resulting residuals represent case\uffe2\uff80\uff90specific effect size estimates and thus provide a quantification of treatment effects. This paper illustrates the new concept of such data\uffe2\uff80\uff90driven reciprocal modelling to estimate spatially explicit effects of land\uffe2\uff80\uff90use change on organic carbon stocks in European agricultural soils. For many environmental treatments, the proposed concept can provide accurate effect size estimates that are more representative than could feasibly ever be achieved with controlled experiments.</p", "keywords": ["Carbon Sequestration", "Agriculture", "04 agricultural and veterinary sciences", "15. Life on land", "Carbon", "causation", "land-use change", "soil organic carbon", "Soil", "machine learning", "correlation", "statistical modelling", "0401 agriculture", " forestry", " and fisheries", "Ecosystem"]}, "links": [{"href": "https://onlinelibrary.wiley.com/doi/pdf/10.1111/gcb.15817"}, {"href": "https://doi.org/10.1111/gcb.15817"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Global%20Change%20Biology", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.1111/gcb.15817", "name": "item", "description": "10.1111/gcb.15817", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.1111/gcb.15817"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2021-08-14T00:00:00Z"}}, {"id": "10.1111/gcb.17309", "type": "Feature", "geometry": null, "properties": {"updated": "2026-10-06T16:18:03Z", "type": "Journal Article", "created": "2024-05-15", "title": "Global evidence for joint effects of multiple natural and anthropogenic drivers on soil nitrogen cycling", "description": "Abstract<p>Global soil nitrogen (N) cycling remains poorly understood due to its complex driving mechanisms. Here, we present a comprehensive analysis of global soil \uffce\uffb415N, a stable isotopic signature indicative of the N input\uffe2\uff80\uff93output balance, using a machine\uffe2\uff80\uff90learning approach on 10,676 observations from 2670 sites. Our findings reveal prevalent joint effects of climatic conditions, plant N\uffe2\uff80\uff90use strategies, soil properties, and other natural and anthropogenic forcings on global soil \uffce\uffb415N. The joint effects of multiple drivers govern the latitudinal distribution of soil \uffce\uffb415N, with more rapid N cycling at lower latitudes than at higher latitudes. In contrast to previous climate\uffe2\uff80\uff90focused models, our data\uffe2\uff80\uff90driven model more accurately simulates spatial changes in global soil \uffce\uffb415N, highlighting the need to consider the joint effects of multiple drivers to estimate the Earth's N budget. These insights contribute to the reconciliation of discordances among empirical, theoretical, and modeling studies on soil N cycling, as well as sustainable N management.</p", "keywords": ["2. Zero hunger", "0301 basic medicine", "[SDU.OCEAN]Sciences of the Universe [physics]/Ocean", "570", "0303 health sciences", "550", "Nitrogen Isotopes", "Atmosphere", "[SDU.OCEAN] Sciences of the Universe [physics]/Ocean", " Atmosphere", "Nitrogen", "Climate", "Nitrogen Cycle", "Models", " Theoretical", "15. Life on land", "[SDU.ENVI] Sciences of the Universe [physics]/Continental interfaces", " environment", "Machine Learning", "Soil", "03 medical and health sciences", "13. Climate action", "[SDU.ENVI]Sciences of the Universe [physics]/Continental interfaces", "environment"]}, "links": [{"href": "https://doi.org/10.1111/gcb.17309"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Global%20Change%20Biology", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.1111/gcb.17309", "name": "item", "description": "10.1111/gcb.17309", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.1111/gcb.17309"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2024-05-01T00:00:00Z"}}, {"id": "10.1111/nph.18387", "type": "Feature", "geometry": null, "properties": {"updated": "2026-10-06T16:18:19Z", "type": "Journal Article", "created": "2020-04-18", "title": "RootPainter: deep learning segmentation of biological images with corrective annotation", "description": "<p>We present RootPainter, a GUI-based software tool for the rapid training of deep neural networks for use in biological image analysis. RootPainter facilitates both fully-automatic and semi-automatic image segmentation. We investigate the effectiveness of RootPainter using three plant image datasets, evaluating its potential for root length extraction from chicory roots in soil, biopore counting and root nodule counting from scanned roots. We also use RootPainter to compare dense annotations to corrective ones which are added during the training based on the weaknesses of the current model.</p>", "keywords": ["Buildings and machinery", "0301 basic medicine", "phenotyping", "root nodule", "biopore", "interactive machine learning", "Research", "segmentation", "deep learning", "rhizotron", "Breeding and genetics", "Machine Learning", "Soil", "03 medical and health sciences", "Deep Learning", "GUI", "Farm nutrient management", "Image Processing", " Computer-Assisted", "Neural Networks", " Computer"]}, "links": [{"href": "https://www.biorxiv.org/content/10.1101/2020.04.16.044461v1.full.pdf"}, {"href": "https://nph.onlinelibrary.wiley.com/doi/pdf/10.1111/nph.18387"}, {"href": "https://doi.org/10.1111/nph.18387"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/New%20Phytologist", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.1111/nph.18387", "name": "item", "description": "10.1111/nph.18387", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.1111/nph.18387"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2020-04-18T00:00:00Z"}}, {"id": "10.1111/wre.12255", "type": "Feature", "geometry": null, "properties": {"updated": "2026-10-06T16:18:21Z", "type": "Journal Article", "created": "2017-05-25", "title": "Big Data for weed control and crop protection", "description": "Summary<p>Farmers have access to many data\uffe2\uff80\uff90intensive technologies to help them monitor and control weeds and pests. Data collection, data modelling and analysis, and data sharing have become core challenges in weed control and crop protection. We review the challenges and opportunities of Big Data in agriculture: the nature of data collected, Big Data analytics and tools to present the analyses that allow improved crop management decisions for weed control and crop protection. Big Data storage and querying incurs significant challenges, due to the need to distribute data across several machines, as well as due to constantly growing and evolving data from different sources. Semantic technologies are helpful when data from several sources are combined, which involves the challenge of detecting interactions of potential agronomic importance and establishing relationships between data items in terms of meanings and units. Data ownership is analysed using the ethical matrix method to identify the concerns of farmers, agribusiness owners, consumers and the environment. Big Data analytics models are outlined, together with numerical algorithms for training them. Advances and tools to present processed Big Data in the form of actionable information to farmers are reviewed, and a success story from the Netherlands is highlighted. Finally, it is argued that the potential utility of Big Data for weed control is large, especially for invasive, parasitic and herbicide\uffe2\uff80\uff90resistant weeds. This potential can only be realised when agricultural scientists collaborate with data scientists and when organisational, ethical and legal arrangements of data sharing are established.</p", "keywords": ["2. Zero hunger", "Support vector machine", "Data ownership", "0401 agriculture", " forestry", " and fisheries", "Data sharing", "Multivariate regression", "04 agricultural and veterinary sciences", "15. Life on land", "Graphical model", "Neural network", "Semantics"]}, "links": [{"href": "http://onlinelibrary.wiley.com/wol1/doi/10.1111/wre.12255/fullpdf"}, {"href": "https://doi.org/10.1111/wre.12255"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Weed%20Research", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.1111/wre.12255", "name": "item", "description": "10.1111/wre.12255", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.1111/wre.12255"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2017-05-24T00:00:00Z"}}, {"id": "10.3168/jds.2019-16575", "type": "Feature", "geometry": null, "properties": {"updated": "2026-10-06T16:19:28Z", "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": "10.13140/rg.2.2.23926.55365", "type": "Feature", "geometry": null, "properties": {"updated": "2026-10-06T16:18:33Z", "type": "Report", "title": "Predicting Soil Organic Matter Content using Machine Learning Models based on Sentinel-2 Imagery", "description": "We used machine learning to process Sentinel 2 multispectral images and infer the amount of soil organic matter using satellite soil indices.", "keywords": ["Machine Learning", "Soil Organic Matter", "Sentinel 2", "15. Life on land"], "contacts": [{"organization": "Vladimir \u0106iri\u0107, Sanja Brdar, Predrag Lugonja, Oskar Marko, Vladimir Crnojevi\u0107,", "roles": ["creator"]}]}, "links": [{"href": "https://doi.org/10.13140/rg.2.2.23926.55365"}, {"rel": "self", "type": "application/geo+json", "title": "10.13140/rg.2.2.23926.55365", "name": "item", "description": "10.13140/rg.2.2.23926.55365", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.13140/rg.2.2.23926.55365"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2019-01-01T00:00:00Z"}}, {"id": "10.3390/plants11152070", "type": "Feature", "geometry": null, "properties": {"updated": "2026-10-06T16:19:43Z", "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": "10.21203/rs.3.rs-561383/v1", "type": "Feature", "geometry": null, "properties": {"updated": "2026-10-06T16:18:59Z", "type": "Journal Article", "created": "2021-05-27", "title": "A spatiotemporal ensemble machine learning framework for generating land use / land cover time-series maps for Europe (2000 \u2013 2019) based on LUCAS, CORINE and GLAD Landsat", "description": "Abstract         <p>A seamless spatiotemporal machine learning framework for automated prediction, uncertainty assessment, and analysis of land use / land cover (LULC) dynamics is presented. The framework includes: (1) harmonization and preprocessing of high-resolution spatial and spatiotemporal covariate datasets (GLAD Landsat, NPP/VIIRS) including 5 million harmonized LUCAS and CORINE Land Cover-derived training samples, (2) model building based on spatial k-fold cross-validation and hyper-parameter optimization, (3) prediction of the most probable class, class probabilities and uncertainty per pixel, (4) LULC change analysis on time-series of produced maps. The spatiotemporal ensemble model was fitted by combining random forest, gradient boosted trees, and artificial neural network, with logistic regressor as meta-learner. The results show that the most important covariates for mapping LULC in Europe are: seasonal aggregates of Landsat green and near-infrared bands, multiple Landsat-derived spectral indices, and elevation. Spatial cross-validation of the model indicates consistent performance across multiple years with 62%, 70%, and 87% accuracy when predicting 33 (level-3), 14 (level-2), and 5 classes (level-1); with artificial surface classes such as 'airports' and 'railroads' showing the lowest match with validation points. The spatiotemporal model outperforms spatial models on known-year classification by 2.7% and unknown-year classification by 3.5%. Results of the accuracy assessment using 48,365 independent test samples shows 87% match with the validation points. Results of time-series analysis (time-series of LULC probabilities and NDVI images) suggest gradual deforestation trends in large parts of Sweden, the Alps, and Scotland. An advantage of using spatiotemporal ML is that the fitted model can be used to predict LULC in years that were not included in its training dataset, allowing generalization to past and future periods, e.g. to predict land cover for years prior to 2000 and beyond 2020. The generated land cover time-series data stack (ODSE-LULC), including the training points, is publicly available via the Open Data Science (ODS)-Europe Viewer.</p", "keywords": ["Time Factors", "Spatiotemporal", "QH301-705.5", "Data Mining and Machine Learning", "Urbanization", "Uncertainty", "Spatial analysis", "R", "Environmental monitoring", "04 agricultural and veterinary sciences", "15. Life on land", "01 natural sciences", "Europe", "Big data", "Machine learning", "Medicine", "0401 agriculture", " forestry", " and fisheries", "Biology (General)", "Landsat", "Ensemble", "Land use/land cover", "Environmental Monitoring", "Probability", "0105 earth and related environmental sciences"]}, "links": [{"href": "https://doi.org/10.21203/rs.3.rs-561383/v1"}, {"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-561383/v1", "name": "item", "description": "10.21203/rs.3.rs-561383/v1", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.21203/rs.3.rs-561383/v1"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2021-05-27T00:00:00Z"}}, {"id": "10.20944/preprints202404.0289.v1", "type": "Feature", "geometry": null, "properties": {"updated": "2026-10-06T16:18:58Z", "type": "Journal Article", "created": "2024-04-04", "title": "A Novel Microfluidics Droplet-Based Interdigitated Ring-Shaped Electrode Sensor for Lab-on-a-Chip Applications", "description": "<?xml version='1.0' encoding='UTF-8'?><article><p>Droplet-based microfluidics has revolutionized numerous fields such as biomedical research, pharmaceuticals, drug discovery, food engineering, flow chemistry, and cosmetics. This paper presents a comprehensive study focusing on the detection and characterization of droplets with volumes in the nanoliter range. Leveraging the precise control of minute liquid volumes, we introduced a novel spectroscopic On-Chip microsensor equipped with integrated microfluidic channels for droplet generation, characterization, and sensing, simultaneously. The microsensor, designed with Interdigitated-Ring-Shaped Electrodes (IRSE) and seamlessly integrated with microfluidic channels, offers enhanced capacitance and impedance signal amplitudes, reproducibility, and reliability in droplet analysis. We were able to make analyses of droplets length in the range 1.0-6.0 mm, velocity 0.66-2.51 mm/s, droplet volume 1.07nL-113.46nL. Experimental results demonstrated that the microsensor&amp;#039;s has a great performance in terms of droplet size, velocity, and length, with a significant signal amplitude of capacitance and impedance, and real-time detection capabilities, thereby highlighting its potential for facilitating microcapsule reactions and enabling on-site real-time detection for chemical and biosensor analyses on-chip.</p></article>", "keywords": ["0301 basic medicine", "lab-on-a-chip sensor", "03 medical and health sciences", "spectroscopic sensing", "droplet-based microfluidics", "TJ1-1570", "real-time", "microfluidics device", "Mechanical engineering and machinery", "interdigitated electrode", "01 natural sciences", "Article", "0104 chemical sciences"]}, "links": [{"href": "https://doi.org/10.20944/preprints202404.0289.v1"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Micromachines", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.20944/preprints202404.0289.v1", "name": "item", "description": "10.20944/preprints202404.0289.v1", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.20944/preprints202404.0289.v1"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2024-04-03T00:00:00Z"}}, {"id": "10.21203/rs.3.rs-3607847/v1", "type": "Feature", "geometry": null, "properties": {"updated": "2026-10-06T16:18:59Z", "type": "Journal Article", "created": "2023-11-15", "title": "Advancements in Biotransformation Pathway Prediction: Enhancements, Datasets, and Novel Functionalities in enviPath", "description": "<title>Abstract</title>         <p>enviPath is a widely used database and prediction system for microbial biotransformation pathways of primarily xenobiotic compounds. Data and prediction system are freely available both via a web interface and a public REST API. Since its initial release in 2016, we extended the data available in enviPath and improved the performance of the prediction system and usability of the overall system. We now provide three diverse data sets, covering microbial biotransformation in different environments and under different experimental conditions. This also enabled developing a pathway prediction model that is applicable to a more diverse set of chemicals. In the prediction engine, we implemented a new evaluation tailored towards pathway prediction, which returns a more honest and holistic view on the performance. We also implemented a novel applicability domain algorithm, which allows the user to estimate how well the model will perform on their data. Finally, we improved the implementation to speed up the overall system and provide new functionality via a plugin system. Overall, enviPath has developed into a reliable database and prediction system with a unique use case in research in microbial biotransformations.</p>", "keywords": ["10120 Department of Chemistry", "0301 basic medicine", "0303 health sciences", "Biodegradation database", "Information technology", "T58.5-58.64", "1704 Computer Graphics and Computer-Aided Design", "3. Good health", "Database", "Chemistry", "03 medical and health sciences", "Metabolic pathways", "540 Chemistry", "Machine learning", "1706 Computer Science Applications", "Biodegradation pathway prediction", "3309 Library and Information Sciences", "1606 Physical and Theoretical Chemistry", "QD1-999"]}, "links": [{"href": "https://doi.org/10.21203/rs.3.rs-3607847/v1"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Journal%20of%20Cheminformatics", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.21203/rs.3.rs-3607847/v1", "name": "item", "description": "10.21203/rs.3.rs-3607847/v1", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.21203/rs.3.rs-3607847/v1"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2023-11-15T00:00:00Z"}}, {"id": "10.21203/rs.3.rs-4951965/v1", "type": "Feature", "geometry": null, "properties": {"updated": "2026-10-06T16:18:59Z", "type": "Journal Article", "created": "2024-10-15", "title": "All black: a microplastic extraction combined with colour-based analysis allows identification and characterisation of tire wear particles (TWP) in soils", "description": "<title>Abstract</title>         <p>While tire wear particles (TWP) have been estimated to represent more than 90% of the total microplastic (MP) emitted in European countries and may have environmental health effects, only few data about TWP concentrations and characteristics are available today. The lack of data stems from the fact that no standardized, cost efficient or accessible extraction and identification method is available yet. We present a method allowing the extraction of TWP from soil, performing analysis with a conventional optical microscope and a machine learning approach to identify TWP in soil based on their colour. The lowest size of TWP which could be measured reliably with an acceptable recovery using our experimental set-up was 35 \u00b5m. Further improvements would be possible given more advanced technical infrastructure (higher optical magnification and image quality). Our method showed a mean recovery of 85% in the 35-2000 \u00b5m particle size range and no blank contamination. We tested for possible interference from charcoal (as another black soil component with similar properties) in the soils and found a reduction of the interference from charcoal by 92% during extraction. We applied our method to a highway adjacent soil at 1 m, 2 m, 5 m, and 10 m and detected TWP in all samples with a tendency to higher concentrations at 1 m and 2 m from the road compared to 10 m from the road. The observed TWP concentrations were in the same order of magnitude as what was previously reported in literature in highway adjacent soils. These results demonstrate the potential of the method to provide quantitative data on the occurrence and characteristics of TWP in the environment. The method can be easily implemented in many labs, and help to address our knowledge gap regarding TWP concentrations in soils.</p>", "keywords": ["TP1080-1185", "Segmentation", "TD172-193.5", "Tire wear", "Soil pollution", "Machine learning", "Microplastic", "Methodology", "Polymers and polymer manufacture", "Optical microscopy", "Environmental pollution"]}, "links": [{"href": "https://doi.org/10.21203/rs.3.rs-4951965/v1"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Microplastics%20and%20Nanoplastics", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.21203/rs.3.rs-4951965/v1", "name": "item", "description": "10.21203/rs.3.rs-4951965/v1", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.21203/rs.3.rs-4951965/v1"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2024-10-15T00:00:00Z"}}], "links": [{"rel": "self", "type": "application/geo+json", "title": "This document as GeoJSON", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items?keywords=Machine&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=Machine&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=Machine&", "hreflang": "en-US"}, {"rel": "next", "type": "application/geo+json", "title": "items (next)", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items?keywords=Machine&offset=50", "hreflang": "en-US"}], "numberMatched": 172, "numberReturned": 50, "distributedFeatures": [], "timeStamp": "2026-11-22T14:04:34.850645Z"}