{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"submitter":["Parente L"],"funding":["Deutsche Forschungsgemeinschaft (German Research Foundation)"],"pagination":["1303"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC11634896"],"repository":["biostudies-literature"],"omics_type":["Unknown"],"volume":["11(1)"],"pubmed_abstract":["The paper describes the production and evaluation of global grassland extent mapped annually for 2000-2022 at 30 m spatial resolution. The dataset showing the spatiotemporal distribution of cultivated and natural/semi-natural grassland classes was produced by using GLAD Landsat ARD-2 image archive, accompanied by climatic, landform and proximity covariates, spatiotemporal machine learning (per-class Random Forest) and over 2.3 M reference samples (visually interpreted in Very High Resolution imagery). Custom probability thresholds (based on five-fold spatial cross-validation) were used to derive dominant class maps with balanced user's and producer's accuracy, resulting in f1 score of 0.64 and 0.75 for cultivated and natural/semi-natural grassland, respectively. The produced maps (about 4 "],"journal":["Scientific data"],"pubmed_title":["Annual 30-m maps of global grassland class and extent (2000-2022) based on spatiotemporal Machine Learning."],"pmcid":["PMC11634896"],"funding_grant_id":["202548816"],"pubmed_authors":["Bonannella C","Meyer C","Oliveira B","Ferreira L","Mattos AP","Ehrmann S","Fritz S","Sloat L","Mesquita V","Witjes M","Teles N","Hengl T","Hunter M","Consoli D","Sahin M","Stanimirova R","Wheeler I","Parente L","Malek Z","Stolle F"],"additional_accession":[]},"is_claimable":false,"name":"Annual 30-m maps of global grassland class and extent (2000-2022) based on spatiotemporal Machine Learning.","description":"The paper describes the production and evaluation of global grassland extent mapped annually for 2000-2022 at 30 m spatial resolution. The dataset showing the spatiotemporal distribution of cultivated and natural/semi-natural grassland classes was produced by using GLAD Landsat ARD-2 image archive, accompanied by climatic, landform and proximity covariates, spatiotemporal machine learning (per-class Random Forest) and over 2.3 M reference samples (visually interpreted in Very High Resolution imagery). Custom probability thresholds (based on five-fold spatial cross-validation) were used to derive dominant class maps with balanced user's and producer's accuracy, resulting in f1 score of 0.64 and 0.75 for cultivated and natural/semi-natural grassland, respectively. The produced maps (about 4 ","dates":{"release":"2024-01-01T00:00:00Z","publication":"2024 Dec","modification":"2026-05-29T16:37:54.642Z","creation":"2025-04-04T09:12:45.886Z"},"accession":"S-EPMC11634896","cross_references":{"pubmed":["39663386"],"doi":["10.1038/s41597-024-04139-6"]}}