<ul><li>Land surface temperature (LST) retrieval from remote sensing data is pivotal for analyzing climate processes and surface energy budgets.</li><li>A deeply coupled framework integrating mechanistic modeling and machine learning is proposed to enhance the accuracy and generalizability of single-channel LST retrieval.</li><li>Global validation demonstrated a 30% reduction in root-mean-square error versus standalone methods, and a 53% improvement in mean absolute error under extreme humidity.</li><li>Continental-scale tests across five continents confirmed the superior generalizability of this model.</li></ul>

A Mechanism-Learning Deeply Coupled Model for Remote Sensing Retrieval of Global Land Surface Temperature

Discover more