No One Knows the State of the Art in Geospatial Foundation Models
cs.CV, cs.CY
Submitted: 2026-05-12
Updated: 2026-11-06
Code: https://github.com/taylor-geospatial/state-of-gfms
Project page: https://antofuller.github.io/BAD_TABLES.pdf
License: http://creativecommons.org/licenses/by/4.0/
The gist: Geospatial foundation models (GFMs) have been proposed as generalizable backbones for disaster response, land-cover mapping, food-security monitoring, and other high-stakes Earth-observation tasks.
Terminology
Abstract
Geospatial foundation models (GFMs) have been proposed as generalizable backbones for disaster response, land-cover mapping, food-security monitoring, and other high-stakes Earth-observation tasks. Yet the published work about these models does not give reviewers or users enough information to tell which model fits a given task. We argue that nobody knows what the current state of the art is in geospatial foundation models. The methods may be useful, but the GFM literature does not standardize evaluations, training and testing protocols, released weights, or pretraining controls well enough for anyone to compare or rank them. In a 152-paper audit, we find 47 cross-paper disagreements of at least 5 percentage points, including 18 of at least 10 points, within model, benchmark, and protocol groups; 94/126 papers with pretraining data use a configuration no other paper uses; and 39% of GFM papers release no model weights. This lack of community standards can be solved. We propose six concrete expectations: named-license weight release, shared core evaluations, copied-versus-rerun baseline annotations, variance reporting, one shared evaluation harness, and data-vs-architecture-vs-algorithm controls. These gaps are a coordination failure, not a fault of any individual lab; the authors of this paper, like many others in the GFM community, have contributed to them. Rather than just critiquing the community, we aim to provide concrete steps toward a shared understanding of how to evaluate and improve GFMs.
Sources
- On the Opportunities and Risks of Foundation Models
- AlphaEarth Foundations: An embedding field model for accurate and efficient global mapping from sparse label data
- TerraFM: A Scalable Foundation Model for Unified Multisensor Earth Observation
- The Benchmark Lottery
- OlmoEarth: Stable Latent Image Modeling for Multimodal Earth Observation
- RingMo-Agent: A Unified Remote Sensing Foundation Model for Multi-Platform and Multi-Modal Reasoning
- Pretrain Where? Investigating How Pretraining Data Diversity Impacts Geospatial Foundation Model Performance
- Docling: An Efficient Open-Source Toolkit for AI-driven Document Conversion
- PANGAEA: A Global and Inclusive Benchmark for Geospatial Foundation Models
- GEO-Bench-2: From Performance to Capability, Rethinking Evaluation in Geospatial AI
- Neural Plasticity-Inspired Multimodal Foundation Model for Earth Observation
- A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs