Toward Global Multimodal High-Resolution Land Surface Temperature Forecasting and Nowcasting

This paper introduces deep learning methods for high-resolution (30-meter) land surface temperature (LST) forecasting, addressing a critical gap in climate science and urban planning. We propose novel architectures, including DeepSatNet, which combines transfer learning from pre-trained networks with attention mechanisms. By fusing Landsat imagery and meteorological data, our models achieve significant improvements over baseline methods, with DeepSatNet demonstrating a 85.7% reduction in Root Mean Square Error compared to a persistence baseline. Our approach outperforms theoretical best-case scenarios for lower-resolution models, such as GraphCast, highlighting the importance of high-resolution modeling for accurate LST prediction. The models’ effectiveness across diverse environments suggests strong generalization capabilities, opening new avenues for urban heat management, energy grid optimization, and climate adaptation strategies. This research demonstrates that high-resolution LST forecasting is both achievable and essential for addressing urgent climate challenges