{"type": "FeatureCollection", "features": [{"id": "10.1111/ejss.12998", "type": "Feature", "geometry": null, "properties": {"updated": "2026-07-27T16:19:22Z", "type": "Journal Article", "created": "2020-05-21", "title": "Machine learning in space and time for modelling soil organic carbon change", "description": "Abstract<p>Spatially resolved estimates of change in soil organic carbon (SOC) stocks are necessary for supporting national and international policies aimed at achieving land degradation neutrality and climate change mitigation. In this work we report on the development, implementation and application of a data\uffe2\uff80\uff90driven, statistical method for mapping SOC stocks in space and time, using Argentina as a pilot. We used quantile regression forest machine learning to predict annual SOC stock at 0\uffe2\uff80\uff9330\uffe2\uff80\uff89cm depth at 250\uffe2\uff80\uff89m resolution for Argentina between 1982 and 2017. The model was calibrated using over 5,000 SOC stock values from the 36\uffe2\uff80\uff90year time period and 35 environmental covariates. We preprocessed normalized difference vegetation index (NDVI) dynamic covariates using a temporal low\uffe2\uff80\uff90pass filter to allow the SOC stock for a given year to depend on the NDVI of the current as well as preceding years. Predictions had modest temporal variation, with an average decrease for the entire country from 2.55 to 2.48\uffe2\uff80\uff89kg\uffe2\uff80\uff89C\uffe2\uff80\uff89m\uffe2\uff88\uff922 over the 36\uffe2\uff80\uff90year period (equivalent to a decline of 211 Gg C, 3.0% of the total 0\uffe2\uff80\uff9330\uffe2\uff80\uff89cm SOC stock in Argentina). The Pampa region had a larger estimated SOC stock decrease from 4.62 to 4.34\uffe2\uff80\uff89kg\uffe2\uff80\uff89C\uffe2\uff80\uff89m\uffe2\uff88\uff922 (5.9%) during the same period. For the 2001\uffe2\uff80\uff932015 period, predicted temporal variation was seven\uffe2\uff80\uff90fold larger than that obtained using the Tier 1 approach of the Intergovernmental Panel on Climate Change and United Nations Convention to Combat Desertification. Prediction uncertainties turned out to be substantial, mainly due to the limited number and poor spatial and temporal distribution of the calibration data, and the limited explanatory power of the covariates. Cross\uffe2\uff80\uff90validation confirmed that SOC stock prediction accuracy was limited, with a mean error of 0.03\uffe2\uff80\uff89kg\uffe2\uff80\uff89C\uffe2\uff80\uff89m\uffe2\uff88\uff922 and a root mean squared error of 2.04\uffe2\uff80\uff89kg\uffe2\uff80\uff89C\uffe2\uff80\uff89m\uffe2\uff88\uff922. In spite of the large uncertainties, this work showed that machine learning methods can be used for space\uffe2\uff80\uff93time SOC mapping and may yield valuable information to land managers and policymakers, provided that SOC observation density in space and time is sufficiently large.</p>Highlights<p> <p>We tested the use of machine learning for space\uffe2\uff80\uff93time mapping of soil organic carbon (SOC) stock.</p> <p>Predictions for Argentina from 1982 to 2017 showed a 3% decrease of the topsoil SOC stock over time.</p> <p>The machine learning model predicted a greater temporal variation than the IPCC Tier 1 approach.</p> <p>Accurate machine learning SOC stock prediction requires dense soil sampling in space and time.</p> </p", "keywords": ["Estimaci\u00f3n de las Existencias de Carbono", "2. Zero hunger", "quantile regression forest", "land degradation", "Climate Change", "carbon stock", "Argentina", "Carbon Stock Assessments", "04 agricultural and veterinary sciences", "15. Life on land", "01 natural sciences", "Space-time Mapping", "space\u2013time mapping", "climate change", "Bosque de Regresi\u00f3n de Cuantiles", "13. Climate action", "Cambio Clim\u00e1tico", "Land Degradation", "Quantile Regression Rorest", "0401 agriculture", " forestry", " and fisheries", "Mapeo Espacio-tiempo", "Degradaci\u00f3n de Tierras", "0105 earth and related environmental sciences"]}, "links": [{"href": "https://onlinelibrary.wiley.com/doi/pdf/10.1111/ejss.12998"}, {"href": "https://doi.org/10.1111/ejss.12998"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/European%20Journal%20of%20Soil%20Science", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.1111/ejss.12998", "name": "item", "description": "10.1111/ejss.12998", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.1111/ejss.12998"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2020-06-30T00:00:00Z"}}, {"id": "10.3389/fsoil.2023.1268037", "type": "Feature", "geometry": null, "properties": {"updated": "2026-07-27T16:21:40Z", "type": "Journal Article", "created": "2023-12-18", "title": "Sustainable soil and land management: a systems-oriented overview of scientific literature", "description": "<?xml version='1.0' encoding='UTF-8'?><article><p>Healthy soil is vital for our wellbeing and wealth. However, increasing demand for food and biomass may lead to unsustainable soil and land management practices that threaten soils. Other degradation processes such as soil sealing also endanger soil resources. Identifying and accessing the best available knowledge is crucial to address related sustainability issues and promote the needed transition towards sustainable soil and land management practices. Such knowledge has to cover all knowledge domains, system knowledge, target knowledge, and transformation knowledge. However, a comprehensive overview of existing research addressing societal needs related to soil is still missing, which hinders the identification of knowledge gaps. This study provides a detailed analysis of scientific literature to identify ongoing research activities and trends. A quantitative and qualitative analysis of scientific literature related to sustainable soil and land management was conducted. A systems-oriented analytical framework was used that combines soil and land related societal challenges with related knowledge domains. Our analysis revealed a significant increase in scientific publications and related interest in soil and land use-related research, above the average increase of publications within all scientific fields. Different forms of reduction and remediation of soil degradation processes (e.g. erosion, contamination) have been studied most extensively. Other topic areas like land take mitigation, soil biodiversity increase, increase of ecosystem services provision and climate change mitigation and adaption seem to be rather recent concerns, less investigated. We could highlight the importance of context-specific research, as different regions require different practices. For instance, boreal, tropical, karst and peatland regions were less studied. Furthermore, we found that diversifying soil management practices such as agroforestry or including livestock into arable systems are valuable options for increasing biomass, mitigating/adapting to climate change, and improving soil related ecosystem services. A recent trend towards the latter research topic indicates the transition from a soil conservation-oriented perspective to a soil service-oriented perspective, which may be better suited to integrate the social and economic dimensions of soil health improvement alongside the ecological dimension.</p></article>", "keywords": ["Societal challenge", "2. Zero hunger", "CorTexT", "Soil mission", "Knowledge gaps", "Engineering geology. Rock mechanics. Soil mechanics. Underground construction", "[SDV.SA.SDS]Life Sciences [q-bio]/Agricultural sciences/Soil study", "15. Life on land", "societal challenge", "333", "6. Clean water", "Literature analysis", "knowledge gaps", "12. Responsible consumption", "Chemistry", "13. Climate action", "11. Sustainability", "TA703-712", "Stock assessment", "literature analysis", "[SDV.SA.SDS] Life Sciences [q-bio]/Agricultural sciences/Soil study", "stock assessment", "QD1-999", "soil mission"]}, "links": [{"href": "https://doi.org/10.3389/fsoil.2023.1268037"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Frontiers%20in%20Soil%20Science", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.3389/fsoil.2023.1268037", "name": "item", "description": "10.3389/fsoil.2023.1268037", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.3389/fsoil.2023.1268037"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2023-12-18T00:00:00Z"}}, {"id": "20.500.12123/8054", "type": "Feature", "geometry": null, "properties": {"updated": "2026-07-27T16:26:47Z", "type": "Journal Article", "created": "2020-05-20", "title": "Machine learning in space and time for modelling soil organic carbon change", "description": "Abstract                                                             <p>                       Spatially resolved estimates of change in soil organic carbon (SOC) stocks are necessary for supporting national and international policies aimed at achieving land degradation neutrality and climate change mitigation. In this work we report on the development, implementation and application of a data\uffe2\uff80\uff90driven, statistical method for mapping SOC stocks in space and time, using Argentina as a pilot. We used quantile regression forest machine learning to predict annual SOC stock at 0\uffe2\uff80\uff9330\uffe2\uff80\uff89cm depth at 250\uffe2\uff80\uff89m resolution for Argentina between 1982 and 2017. The model was calibrated using over 5,000 SOC stock values from the 36\uffe2\uff80\uff90year time period and 35 environmental covariates. We preprocessed normalized difference vegetation index (NDVI) dynamic covariates using a temporal low\uffe2\uff80\uff90pass filter to allow the SOC stock for a given year to depend on the NDVI of the current as well as preceding years. Predictions had modest temporal variation, with an average decrease for the entire country from 2.55 to 2.48\uffe2\uff80\uff89kg\uffe2\uff80\uff89C\uffe2\uff80\uff89m                       \uffe2\uff88\uff922                       over the 36\uffe2\uff80\uff90year period (equivalent to a decline of 211 Gg C, 3.0% of the total 0\uffe2\uff80\uff9330\uffe2\uff80\uff89cm SOC stock in Argentina). The Pampa region had a larger estimated SOC stock decrease from 4.62 to 4.34\uffe2\uff80\uff89kg\uffe2\uff80\uff89C\uffe2\uff80\uff89m                       \uffe2\uff88\uff922                       (5.9%) during the same period. For the 2001\uffe2\uff80\uff932015 period, predicted temporal variation was seven\uffe2\uff80\uff90fold larger than that obtained using the Tier 1 approach of the Intergovernmental Panel on Climate Change and United Nations Convention to Combat Desertification. Prediction uncertainties turned out to be substantial, mainly due to the limited number and poor spatial and temporal distribution of the calibration data, and the limited explanatory power of the covariates. Cross\uffe2\uff80\uff90validation confirmed that SOC stock prediction accuracy was limited, with a mean error of 0.03\uffe2\uff80\uff89kg\uffe2\uff80\uff89C\uffe2\uff80\uff89m                       \uffe2\uff88\uff922                       and a root mean squared error of 2.04\uffe2\uff80\uff89kg\uffe2\uff80\uff89C\uffe2\uff80\uff89m                       \uffe2\uff88\uff922                       . In spite of the large uncertainties, this work showed that machine learning methods can be used for space\uffe2\uff80\uff93time SOC mapping and may yield valuable information to land managers and policymakers, provided that SOC observation density in space and time is sufficiently large.                     </p>                                                           Highlights                     <p>                                                                           <p>We tested the use of machine learning for space\uffe2\uff80\uff93time mapping of soil organic carbon (SOC) stock.</p>                                                                             <p>Predictions for Argentina from 1982 to 2017 showed a 3% decrease of the topsoil SOC stock over time.</p>                                                                             <p>The machine learning model predicted a greater temporal variation than the IPCC Tier 1 approach.</p>                                                                             <p>Accurate machine learning SOC stock prediction requires dense soil sampling in space and time.</p>                                                                     </p>", "keywords": ["Estimaci\u00f3n de las Existencias de Carbono", "2. Zero hunger", "quantile regression forest", "land degradation", "Climate Change", "carbon stock", "Argentina", "Carbon Stock Assessments", "04 agricultural and veterinary sciences", "15. Life on land", "01 natural sciences", "Space-time Mapping", "space\u2013time mapping", "climate change", "Bosque de Regresi\u00f3n de Cuantiles", "13. Climate action", "Cambio Clim\u00e1tico", "Land Degradation", "Quantile Regression Rorest", "0401 agriculture", " forestry", " and fisheries", "Mapeo Espacio-tiempo", "Degradaci\u00f3n de Tierras", "0105 earth and related environmental sciences"]}, "links": [{"href": "https://onlinelibrary.wiley.com/doi/pdf/10.1111/ejss.12998"}, {"href": "https://doi.org/20.500.12123/8054"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/European%20Journal%20of%20Soil%20Science", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "20.500.12123/8054", "name": "item", "description": "20.500.12123/8054", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/20.500.12123/8054"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2020-06-30T00:00:00Z"}}], "links": [{"rel": "self", "type": "application/geo+json", "title": "This document as GeoJSON", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items?keywords=stock+assessment&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=stock+assessment&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=stock+assessment&", "hreflang": "en-US"}, {"rel": "last", "type": "application/geo+json", "title": "items (last)", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items?keywords=stock+assessment&offset=3", "hreflang": "en-US"}], "numberMatched": 3, "numberReturned": 3, "distributedFeatures": [], "timeStamp": "2026-07-27T18:05:55.985484Z"}