Benchmarking Geospatial Foundation Models for Agriculture Applications

• URL: http://arxiv.org/abs/2606.29664v1
• Date: Mon, 29 Jun 2026 00:19:38 GMT
• Title: Benchmarking Geospatial Foundation Models for Agriculture Applications
• Abstract summary: Geospatial foundation models pretrained on satellite imagery promise broad generalization across remote sensing tasks and regions.<n>This paper evaluates three models, Prithvi, SpectralGPT, and SatMAE, on multi-temporal crop segmentation and change detection across four U.S. states.<n>All three degrade sharply under regional distribution shift, predicting only the most common crops while missing rare ones.
• Score: 9.739789487287576
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Geospatial foundation models pretrained on satellite imagery promise broad generalization across remote sensing tasks and regions, but their geographic transferability has not been systematically tested, especially in agriculture applications. This paper presents a controlled benchmark that evaluates three models, Prithvi, SpectralGPT, and SatMAE, on multi-temporal crop segmentation and change detection across four U.S. states, Iowa, North Carolina, California, and Minnesota. By assigning each train, validation, and test split to a separate region, we measure how well each model transfers to land it has not seen. All three degrade sharply under regional distribution shift, predicting only the most common crops while missing rare ones. We further find that fitting these models to a shared input format affects each one differently, which complicates direct architectural comparison. These results expose key limitations of current geospatial foundation models for agriculture and point to region aware evaluation as a necessary standard.

Related papers

• Embeddings based Anomaly Detection for Cleaning Global Crop Type Reference Datasets [0.15404975601060747]
  We propose a practical, locality-aware, embedding-based anomaly (EBA) framework that operates on the embeddings of a pretrained Earth-observation encoder.<n>We score each labelled sample against other samples of the same crop in the same area using a pretrained embedding, flag the ones that stand out, and test whether removing or down-weighting them before training yields a better model.
  arXiv  Detail & Related papers  (2026-07-27T00:52:52Z)
• PRUE: A Practical Recipe for Field Boundary Segmentation at Scale [50.194423500109025]
  We conduct the first systematic evaluation of segmentation and geospatial foundation models (GFMs) for global field boundary delineation.<n>A U-Net semantic segmentation model outperforms instance-based and GFM alternatives on a suite of performance and deployment metrics.<n>Our approach provides a practical framework for reliable, scalable, and reproducible field boundary delineation across model design, training, and inference.
  arXiv  Detail & Related papers  (2026-03-28T02:47:46Z)
• 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)
• 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)
• CrossEarth: Geospatial Vision Foundation Model for Domain Generalizable Remote Sensing Semantic Segmentation [85.22910555280414]
  CrossEarth is a vision foundation model for semantic segmentation.<n>CrossEarth demonstrates strong cross-domain generalization through a specially designed data-level Earth-Style Injection pipeline.<n>For the semantic segmentation task, we have curated an RSDG benchmark comprising 32 cross-domain settings across various regions, spectral bands, platforms, and climates.
  arXiv  Detail & Related papers  (2024-10-30T01:22:37Z)
• Cross Domain Early Crop Mapping using CropSTGAN [12.271756709807898]
  This paper introduces the Crop Mapping Spectral-temporal Generative Adrial Neural Network (CropSTGAN) CropSTGAN learns to transform the target domain's spectral features to those of the source domain, effectively bridging large dissimilarities. In experiments, CropSTGAN is benchmarked against various state-of-the-art (SOTA) methods.
  arXiv  Detail & Related papers  (2024-01-15T00:27:41Z)
• Exploring Generalisability of Self-Distillation with No Labels for SAR-Based Vegetation Prediction [5.057850174013128]
  We pre-train a DINO-ViT based model using two Synthetic Aperture Radar datasets (S1GRD or GSSIC) across three regions (China, Conus, Europe) We fine-tune the models on smaller labeled datasets to predict vegetation percentage, and empirically study the connection between the embedding space of the models and their ability to generalize across diverse geographic regions and to unseen data.
  arXiv  Detail & Related papers  (2023-10-03T13:41:13Z)
• GeoNet: Benchmarking Unsupervised Adaptation across Geographies [71.23141626803287]
  We study the problem of geographic robustness and make three main contributions. First, we introduce a large-scale dataset GeoNet for geographic adaptation. Second, we hypothesize that the major source of domain shifts arise from significant variations in scene context. Third, we conduct an extensive evaluation of several state-of-the-art unsupervised domain adaptation algorithms and architectures.
  arXiv  Detail & Related papers  (2023-03-27T17:59:34Z)
• Activation Regression for Continuous Domain Generalization with Applications to Crop Classification [48.795866501365694]
  Geographic variance in satellite imagery impacts the ability of machine learning models to generalise to new regions. We model geographic generalisation in medium resolution Landsat-8 satellite imagery as a continuous domain adaptation problem. We develop a dataset spatially distributed across the entire continental United States.
  arXiv  Detail & Related papers  (2022-04-14T15:41:39Z)
• Using Machine Learning to generate an open-access cropland map from satellite images time series in the Indian Himalayan Region [0.28675177318965034]
  We develop an ML pipeline that relies on Sentinel-2 satellite images time series. We generate a cropland map for three districts of Himachal Pradesh, spanning 14,600 km2, which improves the resolution and quality of existing public maps.
  arXiv  Detail & Related papers  (2022-03-28T12:08:06Z)

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.