A Mechanism-Learning Deeply Coupled Model for Remote Sensing Retrieval of Global Land Surface Temperature
This work addresses a critical bottleneck in climate and energy analysis by improving the accuracy and generalizability of land surface temperature retrieval for remote sensing applications, though it is incremental as it builds on existing physical models and machine learning techniques.
The paper tackles the ill-posed problem of retrieving land surface temperature from single-band remote sensing data by integrating mechanistic modeling and machine learning, resulting in a 30% reduction in root-mean-square error and a 53% improvement in mean absolute error under extreme humidity conditions.
Land surface temperature (LST) retrieval from remote sensing data is pivotal for analyzing climate processes and surface energy budgets. However, LST retrieval is an ill-posed inverse problem, which becomes particularly severe when only a single band is available. In this paper, we propose a deeply coupled framework integrating mechanistic modeling and machine learning to enhance the accuracy and generalizability of single-channel LST retrieval. Training samples are generated using a physically-based radiative transfer model and a global collection of 5810 atmospheric profiles. A physics-informed machine learning framework is proposed to systematically incorporate the first principles from classical physical inversion models into the learning workflow, with optimization constrained by radiative transfer equations. Global validation demonstrated a 30% reduction in root-mean-square error versus standalone methods. Under extreme humidity, the mean absolute error decreased from 4.87 K to 2.29 K (53% improvement). Continental-scale tests across five continents confirmed the superior generalizability of this model.