HyBiomass: Global Hyperspectral Imagery Benchmark Dataset for Evaluating Geospatial Foundation Models in Forest Aboveground Biomass Estimation

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,...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE geoscience and remote sensing letters Jg. 22; S. 1 - 5
Hauptverfasser: Banze, Aaron, Stassin, Timothee, Braham, Nassim Ait Ali, Kuzu, Ridvan Salih, Besnard, Simon, Schmitt, Michael
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Piscataway IEEE 2025
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
Aboveground biomass (AGB)
Benchmark testing
Benchmarks
Biological system modeling
Biomass
Datasets
Ecosystem dynamics
Environmental Mapping and Analysis Program (EnMAP)
Estimation
Forest biomass
Forestry
Geospatial analysis
geospatial foundation models (Geo-FMs)
global ecosystem dynamics investigation (GEDI)
hyperspectral imagery (HSI)
Hyperspectral imaging
Imagery
Laser radar
remote sensing
Satellites
Vegetation mapping
ISSN:1545-598X, 1558-0571
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung: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. We also find that the performance difference between the U-Net and Geo-FMs depends on the dataset size for each region and highlight the importance of the token patch size in the Vision Transformer (ViT) backbone for accurate predictions in pixelwise regression tasks. 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.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1545-598X
1558-0571
DOI:10.1109/LGRS.2025.3610178