Scaling Laws for Geospatial Foundation Models: A case study on PhilEO Bench

TL;DR

This study investigates how dataset size, model architecture, and scale influence the performance of geospatial foundation models, providing insights into optimal configurations for Earth Observation tasks.

Contribution

It systematically explores the impact of dataset size, architecture, and scale on GFMs, introducing the FastTOM dataset and benchmarking multiple models on a new comprehensive benchmark.

Findings

CNN models excel in low-shot settings.

ViT-UPerNet performs best on large datasets.

Mamba models show potential efficiency advantages.

Abstract

Foundation Models (FMs) have achieved state-of-the-art performance across domains by leveraging large-scale pretraining. In Earth Observation (EO), the availability of petabyte-scale satellite archives has recently enabled the development of GeoSpatial Foundation Models (GFMs). Yet, fundamental questions remain regarding how dataset size, model architecture, and size interact to determine downstream performance. In this work, we systematically explore this design space by pretraining and fine-tuning models on three dataset scales: PhilEO Globe (0.5TB), FastTOM (2TB, introduced here), and MajorTOM (23TB). We evaluate three architectural families: Geo-Aware U-Net (CNN), ViT-UPerNet (Transformer), and Mamba (State-Space Model); across model sizes ranging from 44M to 300M parameters. All models are benchmarked on the PhilEO Bench, covering: road density and building density regression, and land cover segmentation, and are compared against existing GFMs such as TerraMind and Prithvi-EO-2.0. Our results show that CNN-based models remain highly competitive in low-shot settings, with a 200M-parameter Geo-Aware U-Net outperforming larger architectures on regression tasks. However, when scaling to multi-terabyte datasets, ViT-UPerNet achieves the best performance, particularly for semantic segmentation on MajorTOM (23TB). Finally, we provide the first extensive evaluation of Mamba models in EO, highlighting their potential efficiency advantages, though further large-scale pretraining is required to fully match CNNs and ViTs. All code, pretrained models, and the FastTOM dataset are released publicly, enabling reproducibility and further exploration of scaling laws for GFMs.