Geospatial foundation models (GeoFMs) are enabling increasingly large-scale applications across Earth observation and the geosciences. Leveraging advances in representation learning, GeoAI, and the growing volume of satellite observations available for pre-training, recent models transfer knowledge across regions, sensors, spatial and temporal scales, and downstream tasks. Since the previous EGU session on remote sensing geospatial foundation models (ESSI1.11), research in model development and applications has expanded, with models increasingly evaluated across diverse regions and Earth science disciplines.

This session focuses on large-scale, satellite-based foundation models built from image-based Earth observation modalities, including multispectral, optical, synthetic aperture radar (SAR), hyperspectral, and related remote sensing data. We distinguish this scope from foundation models primarily developed for climate and weather data, numerical weather prediction, or atmospheric modelling. Our focus is on models that learn generalizable representations from large-scale Earth observation imagery and their applications to mapping, monitoring, and understanding Earth’s surface.

We aim to investigate challenges shaping the scientific and practical impact of these models, including transferability across regions and datasets, real-world downstream performance, scaling with data and computational resources, and the uncertainty, interpretability, and reliability of foundation-model predictions.

We invite contributions covering, but not limited to:

* New geospatial foundation models
* Novel pre-training and representation-learning strategies
* Large-scale datasets and benchmarks
* Multimodal and multisensor learning
* Model evaluation and transferability
* Geospatial embeddings as data
* Applications of GeoFMs to Earth observation and Earth science

Relevant applications include:

* Natural and anthropogenic disaster mapping and monitoring
* Crop and agricultural monitoring
* Natural ecosystem monitoring
* Forest and biodiversity monitoring
* Built environment mapping and monitoring
* Environmental monitoring and Earth system science

The session brings together researchers developing GeoFMs and applying them to scientific and societal challenges, with the aim of identifying emerging opportunities, methodological gaps, and future directions for large-scale Earth observation foundation models.