Above-ground Biomass Estimation with Geospatial Foundation Models

• URL: http://arxiv.org/abs/2608.04792v1
• Date: Wed, 05 Aug 2026 12:57:18 GMT
• Title: Above-ground Biomass Estimation with Geospatial Foundation Models
• Abstract summary: We present a benchmark of GFMs for global-scale Above-Ground Biomass estimation using the AGBD dataset.<n>We compare 11 GFMs available on PANGAEA and both embedding products against a fully supervised state-of-the-art (SOTA) model.<n>Our results show that GFMs run as frozen encoders substantially underperform with respect to the supervised SOTA model.
• Score: 26.677000802777542
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Accurate estimation of Above-Ground Biomass (AGB) from satellite imagery is essential for the large-scale monitoring of carbon stocks, yet it remains a challenging regression task at global scale. Geospatial Foundation Models (GFMs) have recently emerged as a promising machine learning paradigm to derive general-purpose representations from Earth observation data, but their utility for quantitative regression tasks like biomass estimation remains largely unexplored, as most benchmarks emphasize classification and segmentation. Here, we present a comprehensive benchmark of GFMs for global-scale AGB estimation using the AGBD dataset, a machine learning-ready benchmark spanning diverse biomes and geographies. We distinguish two ways in which GFMs reach practitioners: (i) models distributed as weights to be run by the user, which we evaluate as frozen encoders within the PANGAEA benchmarking framework; and (ii) models distributed as ready-to-use, pre-computed embedding products, for which we evaluate AlphaEarth Foundations (AEF) and TESSERA. We compare 11 GFMs available on PANGAEA and both embedding products against a fully supervised state-of-the-art (SOTA) model, assess their geographical and temporal generalization abilities, as well as agreement with the ESA CCI biomass product on independent reference data. Our results show that GFMs run as frozen encoders substantially underperform with respect to the supervised SOTA model, whereas pre-computed embedding products prove highly effective. An MLP trained on AEF embeddings outperforms the supervised SOTA model trained on AGBD features, and the same SOTA model trained on AEF embeddings (optionally augmented with selected raw features) achieves the best overall result, while also generalizing better across space and time.

Related papers

• Biomazon: A Multimodal Dataset for 3D Forest Structure and Biomass Modeling in the Amazon Basin [2.280283940644759]
  Biomazon is a 20 m multimodal benchmark dataset over the Amazon Basin.<n>It pairs GEDI RH and AGBD targets with multi-sensor predictors.<n>Biomazon establishes a reference benchmark for future work on structurally consistent RH-profile prediction.
  arXiv  Detail & Related papers  (2026-06-03T19:16:35Z)
• FLORO: A Multimodal Geospatial Foundation Model for Ecological Remote Sensing Across Sensors and Scales [65.4821703903285]
  FLORO is a multimodal foundation model designed to learn transferable representations from a small but highly diverse remote sensing corpus.<n> FLORO is pretrained using masked autoencoding on a heterogeneous combination of Sentinel-1, Sentinel-2, SkySAT imagery, elevation, and UAV-derived data.<n>We evaluated FLORO on the PANGAEA benchmark under a frozen-encoder protocol across scene classification, segmentation, and regression tasks.
  arXiv  Detail & Related papers  (2026-05-27T08:55:54Z)
• Ecological mapping with geospatial foundation models [0.8919051099268218]
  This study aims to explore the utility, challenges and opportunities associated with the application of GFMs for ecological uses.<n>We fine-tune several pretrained AI models, namely, Prithvi-E0-2.0 and TerraMind, across three use cases, and compare this with a baseline ResNet-101 model.<n>In all experiments, the GFMs outperform the baseline ResNet models.
  arXiv  Detail & Related papers  (2026-02-11T10:25:51Z)
• GEO-Bench-2: From Performance to Capability, Rethinking Evaluation in Geospatial AI [52.13138825802668]
  GeoFMs are transforming Earth Observation, but evaluation lacks standardized protocols.<n> GEO-Bench-2 addresses this with a comprehensive framework spanning classification, segmentation, regression, object detection, and instance segmentation.<n>Code, data, and leaderboard for GEO-Bench-2 are publicly released under a permissive license.
  arXiv  Detail & Related papers  (2025-11-19T17:45:02Z)
• HyBiomass: Global Hyperspectral Imagery Benchmark Dataset for Evaluating Geospatial Foundation Models in Forest Aboveground Biomass Estimation [1.0408909053766147]
  We introduce a globally distributed benchmark dataset for forest aboveground biomass (AGB) estimation.<n>This benchmark dataset combines co-located hyperspectral imagery (HSI) from the Environmental Mapping and Analysis Program (EnMAP) satellite and predictions of AGB density estimates.<n>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.
  arXiv  Detail & Related papers  (2025-06-12T21:29:20Z)
• TerraFM: A Scalable Foundation Model for Unified Multisensor Earth Observation [65.74990259650984]
  We introduce TerraFM, a scalable self-supervised learning model that leverages globally distributed Sentinel-1 and Sentinel-2 imagery.<n>Our training strategy integrates local-global contrastive learning and introduces a dual-centering mechanism.<n>TerraFM achieves strong generalization on both classification and segmentation tasks, outperforming prior models on GEO-Bench and Copernicus-Bench.
  arXiv  Detail & Related papers  (2025-06-06T17:59:50Z)
• PANGAEA: A Global and Inclusive Benchmark for Geospatial Foundation Models [3.9031647202359667]
  PANGAEA is a standardized evaluation protocol that covers a diverse set of datasets, tasks, resolutions, sensor modalities, and temporalities.<n>We evaluate the most popular GFMs openly available on this benchmark and analyze their performance across several domains.<n>Our findings highlight the limitations of GFMs, under different scenarios, showing that they do not consistently outperform supervised models.
  arXiv  Detail & Related papers  (2024-12-05T14:40:41Z)
• GAMformer: In-Context Learning for Generalized Additive Models [53.08263343627232]
  We introduce GAMformer, the first method to leverage in-context learning to estimate shape functions of a GAM in a single forward pass. Our experiments show that GAMformer performs on par with other leading GAMs across various classification benchmarks.
  arXiv  Detail & Related papers  (2024-10-06T17:28:20Z)
• GenBench: A Benchmarking Suite for Systematic Evaluation of Genomic Foundation Models [56.63218531256961]
  We introduce GenBench, a benchmarking suite specifically tailored for evaluating the efficacy of Genomic Foundation Models. GenBench offers a modular and expandable framework that encapsulates a variety of state-of-the-art methodologies. We provide a nuanced analysis of the interplay between model architecture and dataset characteristics on task-specific performance.
  arXiv  Detail & Related papers  (2024-06-01T08:01:05Z)
• GEO-Bench: Toward Foundation Models for Earth Monitoring [139.77907168809085]
  We propose a benchmark comprised of six classification and six segmentation tasks. This benchmark will be a driver of progress across a variety of Earth monitoring tasks.
  arXiv  Detail & Related papers  (2023-06-06T16:16:05Z)
• Global canopy height estimation with GEDI LIDAR waveforms and Bayesian deep learning [20.692092680921274]
  NASA's Global Ecosystem Dynamics Investigation (GEDI) is a key climate mission whose goal is to advance our understanding of the role of forests in the global carbon cycle. We present a novel supervised machine learning approach to interpret GEDI waveforms and regress canopy top height globally.
  arXiv  Detail & Related papers  (2021-03-05T23:08:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.