融合物理机制与深度学习，提升单波段遥感地表温度反演精度
A Mechanism-Learning Deeply Coupled Model for Remote Sensing Retrieval of Global Land Surface Temperature
- 将物理辐射传输方程嵌入机器学习流程，约束模型优化
- 全球验证下均方根误差降低30%，极端湿度下误差减少53%
- 适用于多大陆、跨气候区的地表温度反演，泛化能力强
从遥感数据反演地表温度（LST）对分析气候过程和地表能量平衡至关重要。然而，当仅可用单波段数据时，该问题属于病态逆问题，难度显著增加。本文提出一种深度融合机制建模与机器学习的耦合框架，以提升单通道LST反演的准确性和泛化能力。训练样本基于物理辐射传输模型及全球5810个大气廓线生成。提出的物理信息机器学习框架系统性地将经典物理反演模型的基本原理融入学习流程，优化过程受辐射传输方程约束。全球验证表明，相比独立方法，均方根误差降低30%；在极端湿度条件下，平均绝对误差由4.87 K降至2.29 K（改善53%）。五大洲的大陆尺度测试证实了该模型的卓越泛化性能。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。