Developing a foundation model for high-resolution remote sensing data of the Netherlands

TL;DR

This paper presents a foundation model for high-resolution Dutch satellite imagery that combines CNN and Vision Transformer, leveraging temporal data to improve land-cover understanding and generalize well globally.

Contribution

The study introduces a novel multi-modal model that captures both spatial and temporal features, achieving competitive results with fewer parameters and limited data.

Findings

Model improves vegetation monitoring accuracy with temporal data.

Achieves competitive performance on global benchmarks.

Uses fewer parameters and less data than state-of-the-art models.

Abstract

We develop a foundation model using 1.2m high resolution satellite images of the Netherlands. By combining a Convolutional Neural Network and a Vision Transformer, the model captures both low- and high-frequency landscape features, such as fine textures, edges, and small objects as well as large terrain structures, elevation patterns, and land-cover distributions. Leveraging temporal data as input, the model learns from broader contextual information across time, allowing the model to exploit the temporal dependencies, such as topographic features, land-cover changes, and seasonal dynamics. These additional constraints reduce feature ambiguity, improve representation learning, and enable better generalization with fewer labeled samples. The foundation model is evaluated on multiple downstream tasks, ranging from use cases within the Netherlands to global benchmarking datasets. On the vegetation monitoring dataset of the Netherlands, the model shows clear performance improvements by incorporating temporal information instead of relying on a single time point. Despite using a smaller model and less pretraining data limited to the Netherlands, it achieves competitive results on global benchmarks when compared to state-of-the-art models. These results demonstrate that the model can learn rich, generalizable representations from limited data, achieving competitive performance on global benchmarks while using a fraction of the parameters of larger state-of-the-art remote sensing models. To maximize reproducibility and reuse, we made the scripts and the model accessible on GitHub.