Annual 30-m maps of global grassland class and extent (2000–2022) based on spatiotemporal Machine Learning

20180 15 108357 2 328174 document 108357 s41597-024-04139-6.pdf application/pdf f8662c43bb2938f382c480298013f585 MD5 6387175 2024-12-11 17:12:35 https://pure.iiasa.ac.at/id/eprint/20180/1/s41597-024-04139-6.pdf 20180 1 1 application/pdf text en public cc_by_4

s41597-024-04139-6.pdf

published 108358 1 328178 document 108358 indexcodes.txt text/x-c++ cfbb3fb99076b2d3cc8246b8f1b58d88 MD5 21792 2024-12-11 17:13:16 https://pure.iiasa.ac.at/id/eprint/20180/2/indexcodes.txt 20180 2 2 text/x-c++ other Generate index codes conversion from text to indexcodes en public

indexcodes.txt

lightbox.jpg

preview.jpg

medium.jpg

small.jpg

http://eprints.org/relation/isVersionOf https://pure.iiasa.ac.at/id/document/108357 http://eprints.org/relation/isVolatileVersionOf https://pure.iiasa.ac.at/id/document/108357 http://eprints.org/relation/issmallThumbnailVersionOf https://pure.iiasa.ac.at/id/document/108357 archive 2 disk0/00/02/01/80 2024-12-11 17:12:52 2025-02-03 12:48:04 2024-12-11 17:12:52 article show Parente L. Sloat L. Mesquita V. Consoli D. Stanimirova R. Hengl T. Bonannella C. Teles N. Wheeler I. Hunter M. Ehrmann S. Ferreira L. Mattos A.P. Oliveira B. Meyer C. Şahin M. Witjes M. Fritz S. 8130 0000-0003-0420-8549 Malek Z. 1957 0000-0002-6981-6708 Stolle F. Annual 30-m maps of global grassland class and extent (2000–2022) based on spatiotemporal Machine Learning pub ASA NODES SI 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 TB in size) are available under an open data license as Cloud-Optimized GeoTIFFs and as Google Earth Engine assets. The suggested uses of data include (1) integration with other compatible land cover products and (2) tracking the intensity and drivers of conversion of land to cultivated grasslands and from natural / semi-natural grasslands into other land use systems. 2024-12-11 10.1038/s41597-024-04139-6 98 2606 public Scientific Data 11 e1303 TRUE 2052-4463 Open-Earth-Monitor Cyberinfrastructure (OEMC, HE 101059548) yes info:eu-repo/grantAgreement/EC/HORIZON/101059548/EU//OEMC info:eu-repo/semantics/article info:eu-repo/semantics/openAccess