# Towards Scalable and Generalizable Earth Observation Data Mining via Foundation Model Composition

Source: [Towards Scalable and Generalizable Earth Observation Data Mining via Foundation Model Composition](<https://www.sota2.com/research/paper/68fa79a21e209131cea7e933>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T05:02:45.345Z

Authors: Man Duc Chuc

Published: 2025-06-25T07:02:42.000Z

## Abstract

Foundation models are rapidly transforming Earth Observation data mining by enabling generalizable and scalable solutions for key tasks such as scene classification and semantic segmentation. While most efforts in the geospatial domain have focused on developing large models trained from scratch using massive Earth Observation datasets, an alternative strategy that remains underexplored is the reuse and combination of existing pretrained models. In this study, we investigate whether foundation models pretrained on remote sensing and general vision datasets can be effectively combined to improve performance across a diverse set of key Earth Observation tasks. Using the GEO-Bench benchmark, we evaluate several prominent models, including Prithvi, Hiera, and DOFA, on eleven datasets covering a range of spatial resolutions, sensor modalities, and task types. The results show that feature-level ensembling of smaller pretrained models can match or exceed the performance of much larger models, while requiring less training time and computational resources. Moreover, the study highlights the potential of applying knowledge distillation to transfer the strengths of ensembles into more compact models, offering a practical path for deploying foundation models in real-world Earth Observation applications.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2506.20174>)

[PDF](<https://arxiv.org/pdf/2506.20174.pdf>)
