EarthAlign: Learning Language-Aligned Representations of Earth System Data
EarthAlign and MeteoLIP provide a foundation for learning and evaluating language-aligned representations of Earth system data and improve upon the corresponding CLIP and SigLIP baselines across three downstream tasks: cross-modal retrieval, weather-condition classification, and physical variable estimation.
F. Maani, N. Saeed, Jia-Qi W. Ma et al.
· 0 citations