{"type": "FeatureCollection", "features": [{"id": "10.1016/j.jag.2024.103659", "type": "Feature", "geometry": null, "properties": {"license": "Open Access", "updated": "2026-06-27T16:17:54Z", "type": "Journal Article", "created": "2024-01-21", "title": "Automatized Sentinel-2 mosaicking for large area forest mapping", "description": "Creating maps of forest inventory variables is commonly taking advantage of satellite images, which are mosaicked together for gaining larger coverage. Recently, mosaicking has increasingly shifted towards user friendly cloud-based online environments such as Google Earth Engine (GEE), which are equipped with huge image repositories and extensive processing capabilities. This enables the easy transferability of workflows into new image sets and diversifies the range of methodological options for mosaicking. The quality control of the output mosaic, ensuring that the reflectance values are representative to the targeted land cover, is however primarily based on certain assumptions or pre-set rules which may not always produce an optimal result. Our study focuses on assessing and comparing the performance of three different mosaicking algorithms for predicting forest inventory variables, based on an extensive set of field data on the main site type, fertility class, and volume and biomass of growing stock. One of the compared mosaics derives from manual image selection, thus enabling rigorous visual quality control, and two others are resting on GEE-assisted automatized methods which include applying a percentile-based statistic over all the input reflectance values and selecting the best pixels using predefined quality indicators. The results indicate that the manual and the percentile-based mosaics are generally providing the best and relatively equal performance levels. Compared to them, the quality-based mosaic has slightly lower accuracy particularly when predicting continuous variables (i.e., the volume and biomass of growing stock) and it suffers from minor image defects. For the total volume of growing stock, for example, the RMS errors are 56.22 % for the manual, 56.33 % for the percentile-based, and 59.47 % for the quality-based mosaics, respectively. These results indicate that from the perspective of large area forest mapping, automatically generated mosaics may provide approximately similar accuracy as compared to manually controlled workflow at a fraction of the workload.", "keywords": ["Image mosaicking", "Physical geography", "791", "forest research", "04 agricultural and veterinary sciences", "15. Life on land", "Feature prediction", "01 natural sciences", "GB3-5030", "Environmental sciences", "0401 agriculture", " forestry", " and fisheries", "GE1-350", "Sentinel-2", "Google Earth Engine", "satellite images", "Forest inventory", "0105 earth and related environmental sciences"], "contacts": [{"organization": "Balazs Andras, Tuominen Sakari, Pitk\u00e4nen Timo P.,", "roles": ["creator"]}]}, "links": [{"href": "https://doi.org/10.1016/j.jag.2024.103659"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/International%20Journal%20of%20Applied%20Earth%20Observation%20and%20Geoinformation", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.1016/j.jag.2024.103659", "name": "item", "description": "10.1016/j.jag.2024.103659", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.1016/j.jag.2024.103659"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2024-03-01T00:00:00Z"}}, {"id": "10.1016/j.scitotenv.2021.148466", "type": "Feature", "geometry": null, "properties": {"updated": "2026-06-27T16:18:16Z", "type": "Journal Article", "created": "2021-06-12", "title": "Soil erosion assessment in the Blue Nile Basin driven by a novel RUSLE-GEE framework", "description": "Assessment of soil loss and understanding its major drivers are essential to implement targeted management interventions. We have proposed and developed a Revised Universal Soil Loss Equation framework fully implemented in the Google Earth Engine cloud platform (RUSLE-GEE) for high spatial resolution (90 m) soil erosion assessment. Using RUSLE-GEE, we analyzed the soil loss rate for different erosion levels, land cover types, and slopes in the Blue Nile Basin. The results showed that the mean soil loss rate is 39.73, 57.98, and 6.40 t ha\u22121 yr\u22121 for the entire Blue Nile, Upper Blue Nile, and Lower Blue Nile Basins, respectively. Our results also indicated that soil protection measures should be implemented in approximately 27% of the Blue Nile Basin, as these areas face a moderate to high risk of erosion (>10 t ha\u22121 yr\u22121 ). In addition, downscaling the Tropical RainfallMeasuring Mission (TRMM) precipitation data from 25 km to 1 km spatial resolution significantly impacts rainfall erosivity and soil loss rate. In terms of soil erosion assessment, the study showed the rapid characterization of soil loss rates that could be used to prioritize erosion mitigation plans to support sustainable land resources and tackle land degradation in the Blue Nile Basin.", "keywords": ["Conservation of Natural Resources", "Revised Universal Soil Loss Equation", "0207 environmental engineering", "TRMM spatial downscaling", "02 engineering and technology", "15. Life on land", "6. Clean water", "Soil", "13. Climate action", "Soil loss severity analysis", "Geographic Information Systems", "Cloud computing", "Google Earth Engine", "Environmental Monitoring", "Soil Erosion"]}, "links": [{"href": "https://doi.org/10.1016/j.scitotenv.2021.148466"}, {"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.2021.148466", "name": "item", "description": "10.1016/j.scitotenv.2021.148466", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.1016/j.scitotenv.2021.148466"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2021-11-01T00:00:00Z"}}, {"id": "10.1038/s41598-025-93658-2", "type": "Feature", "geometry": null, "properties": {"license": "Open Access", "updated": "2026-06-27T16:19:29Z", "type": "Journal Article", "created": "2025-04-04", "title": "Plasticulture detection at the country scale by combining multispectral and SAR satellite data", "description": "Abstract

The use of plastic films has been growing in agriculture, benefiting consumers and producers. However, concerns have been raised about the environmental impact of plastic film use, with mulching films posing a greater threat than greenhouse films. This calls for large-scale monitoring of different plastic film uses. We used cloud computing, freely available optical and radar satellite images, and machine learning to map plastic-mulched farmland (PMF) and plastic cover above vegetation (PCV) (e.g., greenhouse, tunnel) across Germany. The algorithm detected 103 103 ha of PMF and 37 103 ha of PCV in 2020, while a combination of agricultural statistics and surveys estimated a smaller plasticulture cover of around 100 103 ha in 2019. Based on ground observations, the overall accuracy of the classification is 85.3%. Optical and radar features had similar importance scores, and a distinct backscatter of PCV was related to metal frames underneath the plastic films. Overall, the algorithm achieved great results in the distinction between PCV and PMF. This study maps different plastic film uses at a country scale for the first time and sheds light on the high potential of freely available satellite data for continental monitoring.

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.

", "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": "10.3390/rs13204063", "type": "Feature", "geometry": null, "properties": {"license": "Open Access", "updated": "2026-06-27T16:23:46Z", "type": "Journal Article", "created": "2021-10-12", "title": "Dynamics of Vegetation Greenness and Its Response to Climate Change in Xinjiang over the Past Two Decades", "description": "

Climate change has proven to have a profound impact on the growth of vegetation from various points of view. Understanding how vegetation changes and its response to climatic shift is of vital importance for describing their mutual relationships and projecting future land\u2013climate interactions. Arid areas are considered to be regions that respond most strongly to climate change. Xinjiang, as a typical dryland in China, has received great attention lately for its unique ecological environment. However, comprehensive studies examining vegetation change and its driving factors across Xinjiang are rare. Here, we used the remote sensing datasets (MOD13A2 and TerraClimate) and data of meteorological stations to investigate the trends in the dynamic change in the Normalized Difference Vegetation Index (NDVI) and its response to climate change from 2000 to 2019 across Xinjiang based on the Google Earth platform. We found that the increment rates of growth-season mean and maximum NDVI were 0.0011 per year and 0.0013 per year, respectively, by averaging all of the pixels from the region. The results also showed that, compared with other land use types, cropland had the fastest greening rate, which was mainly distributed among the northern Tianshan Mountains and Southern Junggar Basin and the northern margin of the Tarim Basin. The vegetation browning areas primarily spread over the Ili River Valley where most grasslands were distributed. Moreover, there was a trend of warming and wetting across Xinjiang over the past 20 years; this was determined by analyzing the climate data. Through correlation analysis, we found that the contribution of precipitation to NDVI (R2 = 0.48) was greater than that of temperature to NDVI (R2 = 0.42) throughout Xinjiang. The Standardized Precipitation and Evapotranspiration Index (SPEI) was also computed to better investigate the correlation between climate change and vegetation growth in arid areas. Our results could improve the local management of dryland ecosystems and provide insights into the complex interaction between vegetation and climate change.

", "keywords": ["2. Zero hunger", "arid areas", "Science", "Q", "04 agricultural and veterinary sciences", "15. Life on land", "01 natural sciences", "climate change", "13. Climate action", "11. Sustainability", "0401 agriculture", " forestry", " and fisheries", "MOD13A2", "arid areas; vegetation variation; climate change; MOD13A2; Google Earth Engine", "Google Earth Engine", "vegetation variation", "0105 earth and related environmental sciences"]}, "links": [{"href": "http://www.mdpi.com/2072-4292/13/20/4063/pdf"}, {"href": "https://doi.org/10.3390/rs13204063"}, {"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/rs13204063", "name": "item", "description": "10.3390/rs13204063", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.3390/rs13204063"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2021-10-11T00:00:00Z"}}, {"id": "10.3390/s25072239", "type": "Feature", "geometry": null, "properties": {"updated": "2026-06-27T16:23:48Z", "type": "Journal Article", "created": "2025-04-02", "title": "Machine Learning-Based Harvest Date Detection and Prediction Using SAR Data for the Vojvodina Region (Serbia)", "description": "

Information on the harvest date of crops can help with logistics management in the agricultural industry, planning machinery operations and also with yield prediction modelling. In this study, the determination and prediction of harvest dates for different crops were performed by applying machine learning techniques on C-band synthetic aperture radar (SAR) data. Ground truth data were provided for the Vojvodina region (Serbia), an area with intensive agricultural production, considering winter wheat, maize and soybean fields with exact harvest dates, for the period 2017\u20132020, including 592 samples in total. Data from the Sentinel-1 satellite were used in the study. Time series of backscattering coefficients for vertical\u2013horizontal (VH) and vertical\u2013vertical (VV) polarisations, both from ascending and descending orbits, were collected from Google Earth Engine. Clustering of harvested and unharvested fields was performed with Principal Component Analysis, multidimensional scaling and t-distributed Stochastic Neighbour Embedding, for initial cluster visualization. It is shown that the separability of unharvested and harvested data in two-dimensional space does not depend on the selected method but more on the crop itself. Support Vector Machine and Multi-layer Perceptron were used as classification algorithms for harvest detection, with the former achieving higher accuracies of 79.65% for wheat, 83.41% for maize and 95.97% for soybean. Finally, regression models were developed for the prediction of the harvest date using Random Forest and the long short-term memory network, with the latter achieving better results: an R2 score of 0.72, mean absolute error of 6.80 days and root mean squared error of 9.25 days, for all crops considered together.

", "keywords": ["machine learning", "agricultural production", "Chemical technology", "Sentinel-1", "TP1-1185", "harvest dates", "Google Earth Engine", "Article", "SAR"], "contacts": [{"organization": "Gordan Mimi\u0107, Amit Kumar Mishra, Miljana Markovi\u0107, Branislav \u017divaljevi\u0107, Dejan Pavlovi\u0107, Oskar Marko,", "roles": ["creator"]}]}, "links": [{"href": "https://doi.org/10.3390/s25072239"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Sensors", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.3390/s25072239", "name": "item", "description": "10.3390/s25072239", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.3390/s25072239"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2025-04-02T00:00:00Z"}}, {"id": "10.4995/cigeo2021.2021.12729", "type": "Feature", "geometry": null, "properties": {"license": "Open Access", "updated": "2026-06-27T16:24:12Z", "type": "Journal Article", "created": "2021-10-11", "title": "Methodological proposal for the identification of marginal lands with remote sensing-derived products and ancillary data", "description": "

The concept of marginal land (ML) is dynamic and depends on various factors related to the environment, climate, scale,culture, and economic sector. The current methods for identifying ML are diverse, they employ multiple parameters andvariables derived from land use and land cover, and mostly reflect specific management purposes. A methodologicalapproach for the identification of marginal lands using remote sensing and ancillary data products and validated on samplesfrom four European countries (i.e., Germany, Spain, Greece, and Poland) is presented in this paper. The methodologyproposed combines land use and land cover data sets as excluding indicators (forest, croplands, protected areas,impervious areas, land-use change, water bodies, and permanent snow areas) and environmental constraints informationas marginality indicators: (i) physical soil properties, in terms of slope gradient, erosion, soil depth, soil texture, percentageof coarse soil texture fragments, etc.; (ii) climatic factors e.g. aridity index; (iii) chemical soil properties, including soil pH,cation exchange capacity, contaminants, and toxicity, among others. This provides a common vision of marginality thatintegrates a multidisciplinary approach. To determine the ML, we first analyzed the excluding indicators used to delimit theareas with defined land use. Then, thresholds were determined for each marginality indicator through which the landproductivity progressively decreases. Finally, the marginality indicator layers were combined in Google Earth Engine. Theresult was categorized into 3 levels of productivity of ML: high productivity, low productivity, and potentially unsuitable land.The results obtained indicate that the percentage of marginal land per country is 11.64% in Germany, 19.96% in Spain,18.76% in Greece, and 7.18% in Poland. The overall accuracies obtained per country were 60.61% for Germany, 88.87%for Spain, 71.52% for Greece, and 90.97% for Poland.

", "keywords": ["Cartography", "Land cover", "Cultural Heritage", "Cobertura de suelo", "3D Modelling", "11. Sustainability", "Teledetecci\u00f3n", "Environmental applications", "Uso de suelo", "2. Zero hunger", "Earth observation", "Tierra abandonada", "Remote sensing", "15. Life on land", "GIS", "SIG", "Geophysics", "Idle land", "13. Climate action", "Degradaci\u00f3n del suelo", "Land use", "Land degradation", "land use", " land cover", " idle land", " land degradation", " GIS", " remote sensing", " Google Earth Engine", "Geocomputing", "Google Earth Engine", "Geodesy"]}, "links": [{"href": "https://doi.org/10.4995/cigeo2021.2021.12729"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Proceedings%20-%203rd%20Congress%20in%20Geomatics%20Engineering%20-%20CIGeo", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.4995/cigeo2021.2021.12729", "name": "item", "description": "10.4995/cigeo2021.2021.12729", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.4995/cigeo2021.2021.12729"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2021-07-07T00:00:00Z"}}, {"id": "10.5281/zenodo.8091840", "type": "Feature", "geometry": null, "properties": {"license": "Open Access", "updated": "2026-06-27T16:27:35Z", "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": "

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.

", "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/10.5281/zenodo.8091840"}, {"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": "10.5281/zenodo.8091840", "name": "item", "description": "10.5281/zenodo.8091840", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.5281/zenodo.8091840"}, {"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": "10.5281/zenodo.8090887", "type": "Feature", "geometry": null, "properties": {"license": "Open Access", "updated": "2026-06-27T16:27:34Z", "type": "Journal Article", "created": "2021-10-11", "title": "Dynamics of Vegetation Greenness and Its Response to Climate Change in Xinjiang over the Past Two Decades", "description": "

Climate change has proven to have a profound impact on the growth of vegetation from various points of view. Understanding how vegetation changes and its response to climatic shift is of vital importance for describing their mutual relationships and projecting future land\u2013climate interactions. Arid areas are considered to be regions that respond most strongly to climate change. Xinjiang, as a typical dryland in China, has received great attention lately for its unique ecological environment. However, comprehensive studies examining vegetation change and its driving factors across Xinjiang are rare. Here, we used the remote sensing datasets (MOD13A2 and TerraClimate) and data of meteorological stations to investigate the trends in the dynamic change in the Normalized Difference Vegetation Index (NDVI) and its response to climate change from 2000 to 2019 across Xinjiang based on the Google Earth platform. We found that the increment rates of growth-season mean and maximum NDVI were 0.0011 per year and 0.0013 per year, respectively, by averaging all of the pixels from the region. The results also showed that, compared with other land use types, cropland had the fastest greening rate, which was mainly distributed among the northern Tianshan Mountains and Southern Junggar Basin and the northern margin of the Tarim Basin. The vegetation browning areas primarily spread over the Ili River Valley where most grasslands were distributed. Moreover, there was a trend of warming and wetting across Xinjiang over the past 20 years; this was determined by analyzing the climate data. Through correlation analysis, we found that the contribution of precipitation to NDVI (R2 = 0.48) was greater than that of temperature to NDVI (R2 = 0.42) throughout Xinjiang. The Standardized Precipitation and Evapotranspiration Index (SPEI) was also computed to better investigate the correlation between climate change and vegetation growth in arid areas. Our results could improve the local management of dryland ecosystems and provide insights into the complex interaction between vegetation and climate change.

", "keywords": ["2. Zero hunger", "arid areas", "Science", "Q", "04 agricultural and veterinary sciences", "15. Life on land", "01 natural sciences", "climate change", "13. Climate action", "11. Sustainability", "0401 agriculture", " forestry", " and fisheries", "MOD13A2", "arid areas; vegetation variation; climate change; MOD13A2; Google Earth Engine", "Google Earth Engine", "vegetation variation", "0105 earth and related environmental sciences"]}, "links": [{"href": "http://www.mdpi.com/2072-4292/13/20/4063/pdf"}, {"href": "https://doi.org/10.5281/zenodo.8090887"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Remote%20Sensing", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.5281/zenodo.8090887", "name": "item", "description": "10.5281/zenodo.8090887", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.5281/zenodo.8090887"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2021-10-11T00:00:00Z"}}, {"id": "3206556723", "type": "Feature", "geometry": null, "properties": {"license": "Open Access", "updated": "2026-06-27T16:30:58Z", "type": "Journal Article", "created": "2021-10-12", "title": "Dynamics of Vegetation Greenness and Its Response to Climate Change in Xinjiang over the Past Two Decades", "description": "

Climate change has proven to have a profound impact on the growth of vegetation from various points of view. Understanding how vegetation changes and its response to climatic shift is of vital importance for describing their mutual relationships and projecting future land\u2013climate interactions. Arid areas are considered to be regions that respond most strongly to climate change. Xinjiang, as a typical dryland in China, has received great attention lately for its unique ecological environment. However, comprehensive studies examining vegetation change and its driving factors across Xinjiang are rare. Here, we used the remote sensing datasets (MOD13A2 and TerraClimate) and data of meteorological stations to investigate the trends in the dynamic change in the Normalized Difference Vegetation Index (NDVI) and its response to climate change from 2000 to 2019 across Xinjiang based on the Google Earth platform. We found that the increment rates of growth-season mean and maximum NDVI were 0.0011 per year and 0.0013 per year, respectively, by averaging all of the pixels from the region. The results also showed that, compared with other land use types, cropland had the fastest greening rate, which was mainly distributed among the northern Tianshan Mountains and Southern Junggar Basin and the northern margin of the Tarim Basin. The vegetation browning areas primarily spread over the Ili River Valley where most grasslands were distributed. Moreover, there was a trend of warming and wetting across Xinjiang over the past 20 years; this was determined by analyzing the climate data. Through correlation analysis, we found that the contribution of precipitation to NDVI (R2 = 0.48) was greater than that of temperature to NDVI (R2 = 0.42) throughout Xinjiang. The Standardized Precipitation and Evapotranspiration Index (SPEI) was also computed to better investigate the correlation between climate change and vegetation growth in arid areas. Our results could improve the local management of dryland ecosystems and provide insights into the complex interaction between vegetation and climate change.

", "keywords": ["2. Zero hunger", "arid areas", "Science", "Q", "04 agricultural and veterinary sciences", "15. Life on land", "01 natural sciences", "climate change", "13. Climate action", "11. Sustainability", "0401 agriculture", " forestry", " and fisheries", "MOD13A2", "arid areas; vegetation variation; climate change; MOD13A2; Google Earth Engine", "Google Earth Engine", "vegetation variation", "0105 earth and related environmental sciences"]}, "links": [{"href": "http://www.mdpi.com/2072-4292/13/20/4063/pdf"}, {"href": "https://doi.org/3206556723"}, {"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": "3206556723", "name": "item", "description": "3206556723", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/3206556723"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2021-10-11T00:00:00Z"}}, {"id": "2160/0069afd7-a0c3-4bc2-aff8-aae8953cfc0d", "type": "Feature", "geometry": null, "properties": {"license": "Open Access", "updated": "2026-06-27T16:30:05Z", "type": "Journal Article", "created": "2025-04-02", "title": "Machine Learning-Based Harvest Date Detection and Prediction Using SAR Data for the Vojvodina Region (Serbia)", "description": "

Information on the harvest date of crops can help with logistics management in the agricultural industry, planning machinery operations and also with yield prediction modelling. In this study, the determination and prediction of harvest dates for different crops were performed by applying machine learning techniques on C-band synthetic aperture radar (SAR) data. Ground truth data were provided for the Vojvodina region (Serbia), an area with intensive agricultural production, considering winter wheat, maize and soybean fields with exact harvest dates, for the period 2017\u20132020, including 592 samples in total. Data from the Sentinel-1 satellite were used in the study. Time series of backscattering coefficients for vertical\u2013horizontal (VH) and vertical\u2013vertical (VV) polarisations, both from ascending and descending orbits, were collected from Google Earth Engine. Clustering of harvested and unharvested fields was performed with Principal Component Analysis, multidimensional scaling and t-distributed Stochastic Neighbour Embedding, for initial cluster visualization. It is shown that the separability of unharvested and harvested data in two-dimensional space does not depend on the selected method but more on the crop itself. Support Vector Machine and Multi-layer Perceptron were used as classification algorithms for harvest detection, with the former achieving higher accuracies of 79.65% for wheat, 83.41% for maize and 95.97% for soybean. Finally, regression models were developed for the prediction of the harvest date using Random Forest and the long short-term memory network, with the latter achieving better results: an R2 score of 0.72, mean absolute error of 6.80 days and root mean squared error of 9.25 days, for all crops considered together.

", "keywords": ["machine learning", "agricultural production", "Chemical technology", "Sentinel-1", "NDC 2 - Dim Newyn", "TP1-1185", "harvest dates", "SDG 2 - Zero Hunger", "Google Earth Engine", "Article", "SAR"]}, "links": [{"href": "https://www.mdpi.com/1424-8220/25/7/2239/pdf"}, {"href": "https://doi.org/2160/0069afd7-a0c3-4bc2-aff8-aae8953cfc0d"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Sensors", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "2160/0069afd7-a0c3-4bc2-aff8-aae8953cfc0d", "name": "item", "description": "2160/0069afd7-a0c3-4bc2-aff8-aae8953cfc0d", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/2160/0069afd7-a0c3-4bc2-aff8-aae8953cfc0d"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2025-04-02T00:00:00Z"}}, {"id": "3172178299", "type": "Feature", "geometry": null, "properties": {"updated": "2026-06-27T16:30:53Z", "type": "Journal Article", "created": "2021-06-12", "title": "Soil erosion assessment in the Blue Nile Basin driven by a novel RUSLE-GEE framework", "description": "Assessment of soil loss and understanding its major drivers are essential to implement targeted management interventions. We have proposed and developed a Revised Universal Soil Loss Equation framework fully implemented in the Google Earth Engine cloud platform (RUSLE-GEE) for high spatial resolution (90 m) soil erosion assessment. Using RUSLE-GEE, we analyzed the soil loss rate for different erosion levels, land cover types, and slopes in the Blue Nile Basin. The results showed that the mean soil loss rate is 39.73, 57.98, and 6.40 t ha\u22121 yr\u22121 for the entire Blue Nile, Upper Blue Nile, and Lower Blue Nile Basins, respectively. Our results also indicated that soil protection measures should be implemented in approximately 27% of the Blue Nile Basin, as these areas face a moderate to high risk of erosion (>10 t ha\u22121 yr\u22121 ). In addition, downscaling the Tropical RainfallMeasuring Mission (TRMM) precipitation data from 25 km to 1 km spatial resolution significantly impacts rainfall erosivity and soil loss rate. In terms of soil erosion assessment, the study showed the rapid characterization of soil loss rates that could be used to prioritize erosion mitigation plans to support sustainable land resources and tackle land degradation in the Blue Nile Basin.", "keywords": ["Conservation of Natural Resources", "Revised Universal Soil Loss Equation", "0207 environmental engineering", "TRMM spatial downscaling", "02 engineering and technology", "15. Life on land", "6. Clean water", "Soil", "13. Climate action", "Soil loss severity analysis", "Geographic Information Systems", "Cloud computing", "Google Earth Engine", "Environmental Monitoring", "Soil Erosion"]}, "links": [{"href": "https://doi.org/3172178299"}, {"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": "3172178299", "name": "item", "description": "3172178299", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/3172178299"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2021-11-01T00:00:00Z"}}, {"id": "34175609", "type": "Feature", "geometry": null, "properties": {"updated": "2026-06-27T16:31:07Z", "type": "Journal Article", "created": "2021-06-12", "title": "Soil erosion assessment in the Blue Nile Basin driven by a novel RUSLE-GEE framework", "description": "Assessment of soil loss and understanding its major drivers are essential to implement targeted management interventions. We have proposed and developed a Revised Universal Soil Loss Equation framework fully implemented in the Google Earth Engine cloud platform (RUSLE-GEE) for high spatial resolution (90 m) soil erosion assessment. Using RUSLE-GEE, we analyzed the soil loss rate for different erosion levels, land cover types, and slopes in the Blue Nile Basin. The results showed that the mean soil loss rate is 39.73, 57.98, and 6.40 t ha\u22121 yr\u22121 for the entire Blue Nile, Upper Blue Nile, and Lower Blue Nile Basins, respectively. Our results also indicated that soil protection measures should be implemented in approximately 27% of the Blue Nile Basin, as these areas face a moderate to high risk of erosion (>10 t ha\u22121 yr\u22121 ). In addition, downscaling the Tropical RainfallMeasuring Mission (TRMM) precipitation data from 25 km to 1 km spatial resolution significantly impacts rainfall erosivity and soil loss rate. In terms of soil erosion assessment, the study showed the rapid characterization of soil loss rates that could be used to prioritize erosion mitigation plans to support sustainable land resources and tackle land degradation in the Blue Nile Basin.", "keywords": ["Conservation of Natural Resources", "Revised Universal Soil Loss Equation", "0207 environmental engineering", "TRMM spatial downscaling", "02 engineering and technology", "15. Life on land", "6. Clean water", "Soil", "13. Climate action", "Soil loss severity analysis", "Geographic Information Systems", "Cloud computing", "Google Earth Engine", "Environmental Monitoring", "Soil Erosion"]}, "links": [{"href": "https://doi.org/34175609"}, {"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": "34175609", "name": "item", "description": "34175609", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/34175609"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2021-11-01T00:00:00Z"}}, {"id": "40175409", "type": "Feature", "geometry": null, "properties": {"license": "Open Access", "updated": "2026-06-27T16:31:22Z", "type": "Journal Article", "created": "2025-04-04", "title": "Plasticulture detection at the country scale by combining multispectral and SAR satellite data", "description": "Abstract

The use of plastic films has been growing in agriculture, benefiting consumers and producers. However, concerns have been raised about the environmental impact of plastic film use, with mulching films posing a greater threat than greenhouse films. This calls for large-scale monitoring of different plastic film uses. We used cloud computing, freely available optical and radar satellite images, and machine learning to map plastic-mulched farmland (PMF) and plastic cover above vegetation (PCV) (e.g., greenhouse, tunnel) across Germany. The algorithm detected 103 103 ha of PMF and 37 103 ha of PCV in 2020, while a combination of agricultural statistics and surveys estimated a smaller plasticulture cover of around 100 103 ha in 2019. Based on ground observations, the overall accuracy of the classification is 85.3%. Optical and radar features had similar importance scores, and a distinct backscatter of PCV was related to metal frames underneath the plastic films. Overall, the algorithm achieved great results in the distinction between PCV and PMF. This study maps different plastic film uses at a country scale for the first time and sheds light on the high potential of freely available satellite data for continental monitoring.

Information on the harvest date of crops can help with logistics management in the agricultural industry, planning machinery operations and also with yield prediction modelling. In this study, the determination and prediction of harvest dates for different crops were performed by applying machine learning techniques on C-band synthetic aperture radar (SAR) data. Ground truth data were provided for the Vojvodina region (Serbia), an area with intensive agricultural production, considering winter wheat, maize and soybean fields with exact harvest dates, for the period 2017\u20132020, including 592 samples in total. Data from the Sentinel-1 satellite were used in the study. Time series of backscattering coefficients for vertical\u2013horizontal (VH) and vertical\u2013vertical (VV) polarisations, both from ascending and descending orbits, were collected from Google Earth Engine. Clustering of harvested and unharvested fields was performed with Principal Component Analysis, multidimensional scaling and t-distributed Stochastic Neighbour Embedding, for initial cluster visualization. It is shown that the separability of unharvested and harvested data in two-dimensional space does not depend on the selected method but more on the crop itself. Support Vector Machine and Multi-layer Perceptron were used as classification algorithms for harvest detection, with the former achieving higher accuracies of 79.65% for wheat, 83.41% for maize and 95.97% for soybean. Finally, regression models were developed for the prediction of the harvest date using Random Forest and the long short-term memory network, with the latter achieving better results: an R2 score of 0.72, mean absolute error of 6.80 days and root mean squared error of 9.25 days, for all crops considered together.

", "keywords": ["machine learning", "agricultural production", "Chemical technology", "Sentinel-1", "TP1-1185", "harvest dates", "Google Earth Engine", "Article", "SAR"]}, "links": [{"href": "https://www.mdpi.com/1424-8220/25/7/2239/pdf"}, {"href": "https://doi.org/PMC11990955"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Sensors", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "PMC11990955", "name": "item", "description": "PMC11990955", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/PMC11990955"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2025-04-02T00:00:00Z"}}, {"id": "2ea8942a-ce7f-4661-8431-ae6f0c092f09", "type": "Feature", "geometry": {"type": "Polygon", "coordinates": [[[-17.05, -24.58], [-17.05, 50.73], [109.9, 50.73], [109.9, -24.58], [-17.05, -24.58]]]}, "properties": {"themes": [{"concepts": [{"id": "farming"}], "scheme": "https://standards.iso.org/iso/19139/resources/gmxCodelists.xml#MD_TopicCategoryCode"}, {"concepts": [{"id": "Continents"}], "scheme": "Continents, countries, sea regions of the world."}], "updated": "2021-12-23T14:49:16", "created": "2018", "language": "eng", "title": "China Terrace Map", "description": "This dataset is a China terrace map at 30 m resolution in 2018. It was developed through supervised pixel-based classification using multisource and multi-temporal data based on the Google Earth Engine platform. The overall accuracy and kappa coefficient achieved 94% and 0.72, respectively. The first 30 m China terrace map will be valuable for studies on soil erosion, food security, biogeochemical cycle, biodiversity, and ecosystem service assessments.\n\nDetailed dataset description can be found at: \nhttps://essd.copernicus.org/articles/13/2437/2021/", "formats": [{"name": "tif"}, {"name": "WWW:LINK-1.0-http--link"}, {"name": "OGC:WMS-1.3.0-http-get-capabilities"}], "keywords": ["Global", "Agriculture", "Crop intensity", "Remote sensing", "HiH_FROM-GLC", "China Terrace Map", "Global land cover change", "Land cover series", "Google Earth Engine", "Landsat", "DEM", "Global", " Countries", "Continents"], "contacts": [{"name": "Le Yu, Department of Earth System Science", "organization": "Tsinghua University", "position": null, "roles": ["pointOfContact"], "phones": [{"value": null}], "emails": [{"value": "leyu@tsinghua.edu.cn"}], "addresses": [{"deliveryPoint": [null], "city": null, "administrativeArea": null, "postalCode": null, "country": null}], "links": [{"href": null}]}]}, "links": [{"href": "https://cbw.users.earthengine.app/view/chinaterracemap", "name": "China Terrace Map", "protocol": "WWW:LINK-1.0-http--link", "rel": "information"}, {"href": "https://io.apps.fao.org/geoserver/wms/FROM_GLC/CTM/v2?request=GetCapabilities&service=WMS&version=1.3.0", "name": "CTM:YEAR:YEAR", "description": "China Terrace Map", "protocol": "OGC:WMS-1.3.0-http-get-capabilities", "rel": null}, {"href": "https://data.apps.fao.org:/map/catalog/srv/api/records/2ea8942a-ce7f-4661-8431-ae6f0c092f09/attachments/terrace.png", "name": "preview", "description": "Web image thumbnail (URL)", "protocol": "WWW:LINK-1.0-http--image-thumbnail", "rel": "preview"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/88195af8-6b60-4fea-8c21-1878bae48a20", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "2ea8942a-ce7f-4661-8431-ae6f0c092f09", "name": "item", "description": "2ea8942a-ce7f-4661-8431-ae6f0c092f09", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/2ea8942a-ce7f-4661-8431-ae6f0c092f09"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2001-01-01T00:00:00Z"}}], "links": [{"rel": "self", "type": "application/geo+json", "title": "This document as GeoJSON", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items?keywords=Google+Earth+Engine&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=Google+Earth+Engine&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=Google+Earth+Engine&", "hreflang": "en-US"}, {"rel": "last", "type": "application/geo+json", "title": "items (last)", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items?keywords=Google+Earth+Engine&offset=16", "hreflang": "en-US"}], "numberMatched": 16, "numberReturned": 16, "distributedFeatures": [], "timeStamp": "2026-06-27T23:12:29.822364Z"}