Geospatial Foundation Models to Enable Progress on Sustainable Development Goals
Pedram Ghamisi, Weikang Yu, Xiaokang Zhang, Aldino Rizaldy, Jian Wang, Chufeng Zhou, Richard Gloaguen, Gustau Camps-Valls

TL;DR
This paper introduces SustainFM, a benchmarking framework for geospatial foundation models aligned with Sustainable Development Goals, assessing their performance, transferability, and energy efficiency across diverse Earth Observation tasks.
Contribution
It provides a comprehensive evaluation of geospatial foundation models in sustainability contexts, highlighting their strengths, limitations, and the need for impact-driven deployment metrics.
Findings
FMs often outperform traditional methods on diverse geospatial tasks.
Evaluation should include transferability, generalization, and energy efficiency.
FMs enable scalable solutions for complex sustainability challenges.
Abstract
Foundation Models (FMs) are large-scale, pre-trained artificial intelligence (AI) systems that have revolutionized natural language processing and computer vision, and are now advancing geospatial analysis and Earth Observation (EO). They promise improved generalization across tasks, scalability, and efficient adaptation with minimal labeled data. However, despite the rapid proliferation of geospatial FMs, their real-world utility and alignment with global sustainability goals remain underexplored. We introduce SustainFM, a comprehensive benchmarking framework grounded in the 17 Sustainable Development Goals with extremely diverse tasks ranging from asset wealth prediction to environmental hazard detection. This study provides a rigorous, interdisciplinary assessment of geospatial FMs and offers critical insights into their role in attaining sustainability goals. Our findings show: (1)…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
