{"type": "FeatureCollection", "features": [{"id": "10.1109/jphotov.2019.2943706", "type": "Feature", "geometry": null, "properties": {"updated": "2026-10-06T16:17:54Z", "type": "Journal Article", "created": "2019-10-23", "title": "Extracting and Generating PV Soiling Profiles for Analysis, Forecasting, and Cleaning Optimization", "description": "<p>&lt;div&gt;&lt;div&gt;&lt;div&gt;&lt;div&gt;The identification and prediction of the daily soiling profiles of a photovoltaic site is essential to plan the optimal cleaning schedule. In this article, we analyze and propose various methods to extract and generate photovoltaic soiling profiles, in order to improve the analysis and the forecast of the losses. New soiling rate extraction methods are proposed to reflect the seasonal variability of the soiling rates and, for this reason, are found to identify the most convenient cleaning day with the highest accuracy for the investigated sites. Also, we present an approach that could be used to predict future soiling losses through the implementation of stochastic weather generation algorithms whose ability to identify in advance the best cleaning schedule is also successfully tested. The methods presented in this article can optimize the operation and maintenance schedule and could make it possible, in the future, to predict soiling losses through analysis based only on environmental parameters, such as rainfall and particulate matter, without the need of long-term soiling data.&lt;/div&gt;&lt;/div&gt;&lt;/div&gt;&lt;/div&gt;</p>", "keywords": ["Optimization", "Power", " Energy and Industry Applications", "Schedules", "Rain", "Cleaning", "Field Performance", "solar energy", "0211 other engineering and technologies", "02 engineering and technology", "Prediction methods", "7. Clean energy", "13. Climate action", "Soil measurements", "time series analysis", "0202 electrical engineering", " electronic engineering", " information engineering", "soiling", "stochastic processes", "Data mining", "Photovoltaic systems", "field performance; optimization; photovoltaic (PV) systems; prediction methods; soiling; solar energy; stochastic processes; time series analysis"]}, "links": [{"href": "https://iris.uniroma1.it/bitstream/11573/1625584/3/Micheli_postprint_Extracting_2020.pdf"}, {"href": "http://xplorestaging.ieee.org/ielx7/5503869/8939133/08880477.pdf?arnumber=8880477"}, {"href": "https://doi.org/10.1109/jphotov.2019.2943706"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/IEEE%20Journal%20of%20Photovoltaics", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.1109/jphotov.2019.2943706", "name": "item", "description": "10.1109/jphotov.2019.2943706", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.1109/jphotov.2019.2943706"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2019-11-03T00:00:00Z"}}, {"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": "10.3389/fenvs.2019.00058", "type": "Feature", "geometry": null, "properties": {"updated": "2026-10-06T16:19:29Z", "type": "Journal Article", "created": "2019-05-17", "title": "Development of an Agricultural Primary Productivity Decision Support Model: A Case Study in France", "description": "Agricultural soils provide society with several functions, one of which is primary productivity. This function is defined as the capacity of a soil to supply nutrients and water and to produce plant biomass for human use, providing food, feed, fiber, and fuel. For farmers, the productivity function delivers an economic basis and is a prerequisite for agricultural sustainability. Our study was designed to develop an agricultural primary productivity decision support model. To obtain a highly accurate decision support model that helps farmers and advisors to assess and manage the provision of the primary productivity soil function on their agricultural fields, we addressed the following specific objectives: (i) to construct a qualitative decision support model to assess the primary productivity soil function at the agricultural field level; (ii) to carry out verification, calibration, and sensitivity analysis of this model; and (iii) to validate the model based on empirical data. The result is a hierarchical qualitative model consisting of 25 input attributes describing soil properties, environmental conditions, cropping specifications, and management practices on each respective field. An extensive dataset from France containing data from 399 sites was used to calibrate and validate the model. The large amount of data enabled data mining to support model calibration. The accuracy of the decision support model prior to calibration supported by data mining was similar to 40%. The data mining approach improved the accuracy to 77%. The proposed methodology of combining decision modeling and data mining proved to be an important step forward. This iterative approach yielded an accurate, reliable, and useful decision support model for the assessment of the primary productivity soil function at the field level. This can assist farmers and advisors in selecting the most appropriate crop management practices. Embedding this decision support model in a set of complementary models for four adjacent soil functions, as endeavored in the H2020 LANDMARK project, will help take the integrated sustainability of arable cropping systems to a new level.", "keywords": ["2. Zero hunger", "agricultural decision-making", "006", "data mining", "04 agricultural and veterinary sciences", "soil functions", "15. Life on land", "[SHS.ECO]Humanities and Social Sciences/Economics and Finance", "yield", "12. Responsible consumption", "Environmental sciences", "expert knowledge", "decision support model", "0401 agriculture", " forestry", " and fisheries", "GE1-350", "[SHS.ECO] Humanities and Social Sciences/Economics and Finance"]}, "links": [{"href": "https://doi.org/10.3389/fenvs.2019.00058"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Frontiers%20in%20Environmental%20Science", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.3389/fenvs.2019.00058", "name": "item", "description": "10.3389/fenvs.2019.00058", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.3389/fenvs.2019.00058"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2019-05-17T00:00:00Z"}}, {"id": "10.5194/bg-2021-323", "type": "Feature", "geometry": null, "properties": {"updated": "2026-10-06T16:20:12Z", "type": "Report", "created": "2021-12-15", "title": "Reviews and syntheses: The promise of big soil data, moving current practices towards future potential", "description": "<?xml version='1.0' encoding='UTF-8'?><article><p>Abstract. In the age of big data, soil data are more available than ever, but -outside of a few large soil survey resources- remain largely unusable for informing soil management and understanding Earth system processes outside of the original study. Data science has promised a fully reusable research pipeline where data from past studies are used to contextualize new findings and reanalyzed for global relevance. Yet synthesis projects encounter challenges at all steps of the data reuse pipeline, including unavailable data, labor-intensive transcription of datasets, incomplete metadata, and a lack of communication between collaborators. Here, using insights from a diversity of soil, data and climate scientists, we summarize current practices in soil data synthesis across all stages of database creation: data discovery, input, harmonization, curation, and publication. We then suggest new soil-focused semantic tools to improve existing data pipelines, such as ontologies, vocabulary lists, and community practices. Our goal is to provide the soil data community with an overview of current practices in soil data and where we need to go to fully leverage big data to solve soil problems in the next century.                         </p></article>", "keywords": ["FOS: Computer and information sciences", "Data Sharing", "Biomedical Ontologies and Text Mining", "Data management", "Leverage (statistics)", "01 natural sciences", "Data science", "Data Sharing and Stewardship in Science", "Database", "Big data", "Biochemistry", " Genetics and Molecular Biology", "Machine learning", "Molecular Biology", "Data mining", "0105 earth and related environmental sciences", "2. Zero hunger", "Metadata", "Ecology", "Data curation", "Physics", "Life Sciences", "Acoustics", "15. Life on land", "Computer science", "World Wide Web", "Harmonization", "13. Climate action", "FOS: Biological sciences", "Computer Science", "Physical Sciences", "Environmental Science", "Data Reuse", "Environmental DNA in Biodiversity Monitoring", "Information Systems"]}, "links": [{"href": "https://doi.org/10.5194/bg-2021-323"}, {"rel": "self", "type": "application/geo+json", "title": "10.5194/bg-2021-323", "name": "item", "description": "10.5194/bg-2021-323", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.5194/bg-2021-323"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2021-12-15T00:00:00Z"}}, {"id": "10.5194/bg-19-3505-2022", "type": "Feature", "geometry": null, "properties": {"updated": "2026-10-06T16:20:11Z", "type": "Journal Article", "created": "2022-07-28", "title": "Reviews and syntheses: The promise of big diverse soil data, moving current practices towards future potential", "description": "<?xml version='1.0' encoding='UTF-8'?><article><p>Abstract. In the age of big data, soil data are more available and richer than ever, but \u2013 outside of a few large soil survey resources \u2013 they remain largely unusable for informing soil management and understanding Earth system processes beyond the original study. Data science has promised a fully reusable research pipeline where data from past studies are used to contextualize new findings and reanalyzed for new insight. Yet synthesis projects encounter challenges at all steps of the data reuse pipeline, including unavailable data, labor-intensive transcription of datasets, incomplete metadata, and a lack of communication between collaborators. Here, using insights from a diversity of soil, data, and climate scientists, we summarize current practices in soil data synthesis across all stages of database creation: availability, input, harmonization, curation, and publication. We then suggest new soil-focused semantic tools to improve existing data pipelines, such as ontologies, vocabulary lists, and community practices. Our goal is to provide the soil data community with an overview of current practices in soil data and where we need to go to fully leverage big data to solve soil problems in the next century.                     </p></article>", "keywords": ["FOS: Computer and information sciences", "0301 basic medicine", "Data Sharing", "Information Systems and Management", "literature review", "1904 Earth-Surface Processes", "Social Sciences", "data set", "01 natural sciences", "Decision Sciences", "Data science", "Life", "QH501-531", "910 Geography & travel", "soil analysis", "database", "QH540-549.5", "2. Zero hunger", "QE1-996.5", "000", "Ecology", "communication", "Physics", "Earth", "Geology", "[SDU.ENVI] Sciences of the Universe [physics]/Continental interfaces", " environment", "World Wide Web", "10122 Institute of Geography", "soil survey", "Physical Sciences", "Data Reuse", "environment", "Information Systems", "Evolution", "future prospect", "Data management", "Data Sharing and Stewardship in Science", "Database", "Big data", "03 medical and health sciences", "Behavior and Systematics", "Data mining", "0105 earth and related environmental sciences", "[SDU.OCEAN]Sciences of the Universe [physics]/Ocean", "Management and Reproducibility of Scientific Workflows", "Metadata", "Data curation", "Atmosphere", "[SDU.OCEAN] Sciences of the Universe [physics]/Ocean", " Atmosphere", "Acoustics", "15. Life on land", "Computer science", "1105 Ecology", " Evolution", " Behavior and Systematics", "Surface Processes", "Harmonization", "FOS: Biological sciences", "Computer Science", "Environmental Science", "[SDU.ENVI]Sciences of the Universe [physics]/Continental interfaces", "soil management", "Research Data", "Environmental DNA in Biodiversity Monitoring"]}, "links": [{"href": "https://doi.org/10.5194/bg-19-3505-2022"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Biogeosciences", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.5194/bg-19-3505-2022", "name": "item", "description": "10.5194/bg-19-3505-2022", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.5194/bg-19-3505-2022"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2022-07-28T00:00:00Z"}}, {"id": "20.500.11850/521965", "type": "Feature", "geometry": null, "properties": {"updated": "2026-10-06T16:22:49Z", "type": "Report", "created": "2021-12-15", "title": "Reviews and syntheses: The promise of big soil data, moving current practices towards future potential", "description": "<?xml version='1.0' encoding='UTF-8'?><article><p>Abstract. In the age of big data, soil data are more available than ever, but -outside of a few large soil survey resources- remain largely unusable for informing soil management and understanding Earth system processes outside of the original study. Data science has promised a fully reusable research pipeline where data from past studies are used to contextualize new findings and reanalyzed for global relevance. Yet synthesis projects encounter challenges at all steps of the data reuse pipeline, including unavailable data, labor-intensive transcription of datasets, incomplete metadata, and a lack of communication between collaborators. Here, using insights from a diversity of soil, data and climate scientists, we summarize current practices in soil data synthesis across all stages of database creation: data discovery, input, harmonization, curation, and publication. We then suggest new soil-focused semantic tools to improve existing data pipelines, such as ontologies, vocabulary lists, and community practices. Our goal is to provide the soil data community with an overview of current practices in soil data and where we need to go to fully leverage big data to solve soil problems in the next century.</p></article>", "keywords": ["FOS: Computer and information sciences", "Data Sharing", "Biomedical Ontologies and Text Mining", "Data management", "Leverage (statistics)", "01 natural sciences", "Data science", "Data Sharing and Stewardship in Science", "Database", "Big data", "Biochemistry", " Genetics and Molecular Biology", "Machine learning", "Molecular Biology", "Data mining", "0105 earth and related environmental sciences", "2. Zero hunger", "Metadata", "Ecology", "Data curation", "Physics", "Life Sciences", "Acoustics", "15. Life on land", "Computer science", "World Wide Web", "Harmonization", "13. Climate action", "FOS: Biological sciences", "Computer Science", "Physical Sciences", "Environmental Science", "Data Reuse", "Environmental DNA in Biodiversity Monitoring", "Information Systems"]}, "links": [{"href": "https://doi.org/20.500.11850/521965"}, {"rel": "self", "type": "application/geo+json", "title": "20.500.11850/521965", "name": "item", "description": "20.500.11850/521965", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/20.500.11850/521965"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2021-12-15T00:00:00Z"}}, {"id": "10.5281/zenodo.14092313", "type": "Feature", "geometry": null, "properties": {"updated": "2026-10-06T16:20:46Z", "type": "Dataset", "title": "D4.3_Probefield_Dataset", "description": "Open AccessOrigin: WP4. This dataset contains VISNIR spectra from in situ measurements and laboratory analyses of air-dried and sieved samples (<2 mm), including pXRF analysis, all conducted by CSIC (Spain). The dataset includes samples collected from various field locations, with corresponding laboratory data from Italy and Turkey. In total, 136 samples were collected from experimental agricultural fields managed by CREA (IT) and TAGEM (TR).\u00a0  The dataset contains information on sampling date, sample_ID, site, crop, depth (cm), coordinates (in LAEA projection), and the corresponding analyzed values for the following parameters: texture (%, sand, silt, clay), pH (Ext 1:2.5), EC (Ext 1:5) (mS/cm), carbonate (% CaCO\u2083), active carbonate (%), organic carbon (%), total nitrogen (%), available phosphorus (mg/kg), cation exchange capacity (CEC, meq/100g), exchangeable bases (meq/100g), elemental analysis (pXRF), and VNIR-pretreated spectra (350\u20132500 nm). An additional sheet contains metadata on the lab methods used. The following pretreatments were applied to the absorbance value of VNIR spectral data: Standardization and correction factor with lucky bay sand following internal soil standard (ISS); Code Trimming; splice Correction; Savitzky-Golay smoothing filter; aggregation side 8 wavelength resampling", "keywords": ["Soil sciences", "EJP SOIL", "Probefield", "Data mining", "Spectroscopy"], "contacts": [{"organization": "Barbetti, Roberto", "roles": ["creator"]}]}, "links": [{"href": "https://doi.org/10.5281/zenodo.14092313"}, {"rel": "self", "type": "application/geo+json", "title": "10.5281/zenodo.14092313", "name": "item", "description": "10.5281/zenodo.14092313", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.5281/zenodo.14092313"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2024-11-12T00:00:00Z"}}, {"id": "10.5281/zenodo.14104497", "type": "Feature", "geometry": null, "properties": {"updated": "2026-10-06T16:20:46Z", "type": "Dataset", "title": "D4.3_Probefield_Dataset", "description": "Open AccessOrigin: WP4. This dataset contains VISNIR spectra from in situ measurements and laboratory analyses of air-dried and sieved samples (<2 mm), including pXRF analysis, all conducted by CSIC (Spain). The dataset includes samples collected from various field locations, with corresponding laboratory data from Italy and Turkey. In total, 136 samples were collected from experimental agricultural fields managed by CREA (IT) and TAGEM (TR).\u00a0  The dataset contains information on sampling date, sample_ID, site, crop, depth (cm), coordinates (in LAEA projection), and the corresponding analyzed values for the following parameters: texture (%, sand, silt, clay), pH (Ext 1:2.5), EC (Ext 1:5) (mS/cm), carbonate (% CaCO\u2083), active carbonate (%), organic carbon (%), total nitrogen (%), available phosphorus (mg/kg), cation exchange capacity (CEC, meq/100g), exchangeable bases (meq/100g), elemental analysis (pXRF), and VNIR-pretreated spectra (350\u20132500 nm). An additional sheet contains metadata on the lab methods used. The following pretreatments were applied to the absorbance value of VNIR spectral data: Standardization and correction factor with lucky bay sand following internal soil standard (ISS); Code Trimming; splice Correction; Savitzky-Golay smoothing filter; aggregation side 8 wavelength resampling", "keywords": ["Soil sciences", "EJP SOIL", "Probefield", "Data mining", "Spectroscopy"], "contacts": [{"organization": "Barbetti, Roberto", "roles": ["creator"]}]}, "links": [{"href": "https://doi.org/10.5281/zenodo.14104497"}, {"rel": "self", "type": "application/geo+json", "title": "10.5281/zenodo.14104497", "name": "item", "description": "10.5281/zenodo.14104497", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.5281/zenodo.14104497"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2024-11-12T00:00:00Z"}}, {"id": "PMC9308969", "type": "Feature", "geometry": null, "properties": {"updated": "2026-10-06T16:25:05Z", "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": "<title>Abstract</title>                 <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/PMC9308969"}, {"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": "PMC9308969", "name": "item", "description": "PMC9308969", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/PMC9308969"}, {"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": "3164960866", "type": "Feature", "geometry": null, "properties": {"updated": "2026-10-06T16:23:25Z", "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/3164960866"}, {"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": "3164960866", "name": "item", "description": "3164960866", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/3164960866"}, {"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": "20.500.11850/562259", "type": "Feature", "geometry": null, "properties": {"updated": "2026-10-06T16:22:50Z", "type": "Journal Article", "created": "2022-07-28", "title": "Reviews and syntheses: The promise of big diverse soil data, moving current practices towards future potential", "description": "<?xml version='1.0' encoding='UTF-8'?><article><p>Abstract. In the age of big data, soil data are more available and richer than ever, but \u2013 outside of a few large soil survey resources \u2013 they remain largely unusable for informing soil management and understanding Earth system processes beyond the original study. Data science has promised a fully reusable research pipeline where data from past studies are used to contextualize new findings and reanalyzed for new insight. Yet synthesis projects encounter challenges at all steps of the data reuse pipeline, including unavailable data, labor-intensive transcription of datasets, incomplete metadata, and a lack of communication between collaborators. Here, using insights from a diversity of soil, data, and climate scientists, we summarize current practices in soil data synthesis across all stages of database creation: availability, input, harmonization, curation, and publication. We then suggest new soil-focused semantic tools to improve existing data pipelines, such as ontologies, vocabulary lists, and community practices. Our goal is to provide the soil data community with an overview of current practices in soil data and where we need to go to fully leverage big data to solve soil problems in the next century.</p></article>", "keywords": ["FOS: Computer and information sciences", "0301 basic medicine", "Data Sharing", "Information Systems and Management", "literature review", "1904 Earth-Surface Processes", "Social Sciences", "data set", "01 natural sciences", "Decision Sciences", "Data science", "Life", "QH501-531", "910 Geography & travel", "soil analysis", "database", "QH540-549.5", "2. Zero hunger", "QE1-996.5", "000", "Ecology", "communication", "Physics", "Earth", "Geology", "[SDU.ENVI] Sciences of the Universe [physics]/Continental interfaces", " environment", "World Wide Web", "10122 Institute of Geography", "soil survey", "Physical Sciences", "Data Reuse", "environment", "Information Systems", "Evolution", "future prospect", "Data management", "Data Sharing and Stewardship in Science", "Database", "Big data", "03 medical and health sciences", "Behavior and Systematics", "Data mining", "0105 earth and related environmental sciences", "[SDU.OCEAN]Sciences of the Universe [physics]/Ocean", "Management and Reproducibility of Scientific Workflows", "Metadata", "Data curation", "Atmosphere", "[SDU.OCEAN] Sciences of the Universe [physics]/Ocean", " Atmosphere", "Acoustics", "15. Life on land", "Computer science", "1105 Ecology", " Evolution", " Behavior and Systematics", "Surface Processes", "Harmonization", "FOS: Biological sciences", "Computer Science", "Environmental Science", "[SDU.ENVI]Sciences of the Universe [physics]/Continental interfaces", "soil management", "Research Data", "Environmental DNA in Biodiversity Monitoring"]}, "links": [{"href": "https://doi.org/20.500.11850/562259"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Biogeosciences", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "20.500.11850/562259", "name": "item", "description": "20.500.11850/562259", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/20.500.11850/562259"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2022-07-28T00:00:00Z"}}, {"id": "2946389500", "type": "Feature", "geometry": null, "properties": {"updated": "2026-10-06T16:23:11Z", "type": "Journal Article", "created": "2019-05-17", "title": "Development of an Agricultural Primary Productivity Decision Support Model: A Case Study in France", "description": "Agricultural soils provide society with several functions, one of which is primary productivity. This function is defined as the capacity of a soil to supply nutrients and water and to produce plant biomass for human use, providing food, feed, fiber, and fuel. For farmers, the productivity function delivers an economic basis and is a prerequisite for agricultural sustainability. Our study was designed to develop an agricultural primary productivity decision support model. To obtain a highly accurate decision support model that helps farmers and advisors to assess and manage the provision of the primary productivity soil function on their agricultural fields, we addressed the following specific objectives: (i) to construct a qualitative decision support model to assess the primary productivity soil function at the agricultural field level; (ii) to carry out verification, calibration, and sensitivity analysis of this model; and (iii) to validate the model based on empirical data. The result is a hierarchical qualitative model consisting of 25 input attributes describing soil properties, environmental conditions, cropping specifications, and management practices on each respective field. An extensive dataset from France containing data from 399 sites was used to calibrate and validate the model. The large amount of data enabled data mining to support model calibration. The accuracy of the decision support model prior to calibration supported by data mining was similar to 40%. The data mining approach improved the accuracy to 77%. The proposed methodology of combining decision modeling and data mining proved to be an important step forward. This iterative approach yielded an accurate, reliable, and useful decision support model for the assessment of the primary productivity soil function at the field level. This can assist farmers and advisors in selecting the most appropriate crop management practices. Embedding this decision support model in a set of complementary models for four adjacent soil functions, as endeavored in the H2020 LANDMARK project, will help take the integrated sustainability of arable cropping systems to a new level.", "keywords": ["2. Zero hunger", "agricultural decision-making", "006", "data mining", "04 agricultural and veterinary sciences", "soil functions", "15. Life on land", "[SHS.ECO]Humanities and Social Sciences/Economics and Finance", "yield", "12. Responsible consumption", "Environmental sciences", "expert knowledge", "decision support model", "0401 agriculture", " forestry", " and fisheries", "GE1-350", "[SHS.ECO] Humanities and Social Sciences/Economics and Finance"]}, "links": [{"href": "https://doi.org/2946389500"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Frontiers%20in%20Environmental%20Science", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "2946389500", "name": "item", "description": "2946389500", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/2946389500"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2019-05-17T00:00:00Z"}}], "links": [{"rel": "self", "type": "application/geo+json", "title": "This document as GeoJSON", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items?keywords=Data+mining&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=Data+mining&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=Data+mining&", "hreflang": "en-US"}, {"rel": "last", "type": "application/geo+json", "title": "items (last)", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items?keywords=Data+mining&offset=12", "hreflang": "en-US"}], "numberMatched": 12, "numberReturned": 12, "distributedFeatures": [], "timeStamp": "2026-11-22T20:07:34.231050Z"}