041fc7b2-c6da-44cf-9c03-526e85c7ef87 English Dataseries German Aerospace Center (DLR) geoservice@dlr.de 2026-01-20T13:46:46 ISO 19115-1:2014/19139 2003/Cor.1:2006 2 128 10 128 30 false HyBiomass - EnMAP L2A / GEDI L4A - Near-Global 2026-01-12T12:48:00 https://geoservice.dlr.de/catalogue/srv/metadata/041fc7b2-c6da-44cf-9c03-526e85c7ef87 Comprehensive evaluation of geospatial foundation models (Geo-FMs) requires benchmarking across diverse tasks, sensors, and geographic regions. However, most existing benchmark datasets are limited to segmentation or classification tasks, and focus on specific geographic areas. To address this gap, we introduce a globally distributed dataset for forest aboveground biomass (AGB) estimation, a pixelwise regression task. This benchmark dataset combines co-located hyperspectral imagery (HSI) from the Environmental Mapping and Analysis Program (EnMAP) satellite and predictions of AGB density estimates derived from the global ecosystem dynamics investigation (GEDI) lidars, covering seven continental regions. Our experimental results on this dataset demonstrate that the evaluated Geo- FMs can match or, in some cases, surpass the performance of a baseline U-Net, especially when fine-tuning the encoder. By releasing this globally distributed hyperspectral benchmark dataset, we aim to facilitate the development and evaluation of Geo-FMs for HSI applications. Leveraging this dataset additionally enables research into geographic bias and the generalization capacity of Geo-FMs. Published in IEEE Geoscience and Remote Sensing Letters: https://ieeexplore.ieee.org/document/11164504. German Aerospace Center (DLR) aaron.banze@dlr.de German Aerospace Center (DLR) geoservice@dlr.de https://geoservice.dlr.de/catalogue/srv/api/records/041fc7b2-c6da-44cf-9c03-526e85c7ef87/attachments/hybiomass_ql.jpg large_thumbnail https://geoservice.dlr.de/catalogue/srv/api/records/041fc7b2-c6da-44cf-9c03-526e85c7ef87/attachments/hybiomass_ql_s.jpg thumbnail Land cover Orthoimagery GEMET - INSPIRE themes, version 1.0 2008-06-01 geonetwork.thesaurus.external.theme.inspire-theme Global Spatial scope 2024-05-23 geonetwork.thesaurus.external.place.SpatialScope.en DLR EOC EnMAP Imagery Hyperspectral Geospatial Foundation Models Hyperspectral Sensor Forest Biomass Estimation Regression Nutzungseinschränkungen: Das DLR ist nicht haftbar für Schäden, die sich aus der Nutzung ergeben. / Use Limitations: DLR not liable for damage resulting from use. Öffentlicher Zugriff beschränkt entsprechend Artikel 13(1)(e) der INSPIRE-Richtlinie: e) aufgrund nachteiliger Auswirkungen auf die Rechte des geistigen Eigentums Nutzungsbedingungen: Lizenz, https://www.enmap.org/data_access/ Terms of use: https://www.enmap.org/data_access/ 60000 English imageryBaseMapsEarthCover -180.00 180.00 -55.00 54.00 2022-05-01T00:00:00 2024-05-01T00:00:00 GeoTIFF https://download.geoservice.dlr.de/ENMAP/files/HYBIOMASS WWW:LINK-1.0-http--link EOC Download Service EOC Download Service https://doi.org/10.1109/LGRS.2025.3610178 WWW:LINK-1.0-http--link Scientific publication https://geoservice.dlr.de/web/datasets/enmap_hybiomass WWW:LINK-1.0-http--link EOC Geoservice Dataset Conformity_001 INSPIRE Commission Regulation (EU) No 1089/2010 of 23 November 2010 implementing Directive 2007/2/EC of the European Parliament and of the Council as regards interoperability of spatial data sets and services 2010-12-08 See the referenced specification. true Input data: HyBiomass is derived from DLR EnMAP L2A data and GEDI L4A Footprint Level Aboveground Biomass Density. Processing information: HyBiomass includes EnMAP tiles selected for SpectralEarth, which have been filtered for clouds and other atmospheric artifacts. We refer to the publication for details on quality filters applied to the GEDI shots. The co-located tiles have been patchified into 128x128 spatial pixels. Quality assurance: The data quality aligns with that of the EnMAP L2A data and GEDI L4A product.