PGDM: Physically guided diffusion model for land surface temperature downscaling

TL;DR

This paper introduces PGDM, a physically guided diffusion model for land surface temperature downscaling, which leverages geophysical priors and probabilistic inference to improve accuracy and uncertainty estimation in high-resolution temperature mapping.

Contribution

The study develops a novel diffusion-based downscaling model grounded in surface energy balance principles, and provides a comprehensive benchmark dataset for LST downscaling evaluation.

Findings

PGDM outperforms existing methods in accuracy.

The model effectively estimates uncertainty through scene-level standard deviation.

Comprehensive datasets enable robust evaluation of downscaling approaches.

Abstract

Land surface temperature (LST) is a fundamental parameter in thermal infrared remote sensing, while current LST products are often constrained by the trade-off between spatial and temporal resolutions. To mitigate this limitation, numerous studies have been conducted to enhance the resolutions of LST data, with a particular emphasis on the spatial dimension (commonly known as LST downscaling). Nevertheless, a comprehensive benchmark dataset tailored for this task remains scarce. In addition, existing downscaling models face challenges related to accuracy, practical usability, and the capability to self-evaluate their uncertainties. To overcome these challenges, this study first compiled three representative datasets, including one dataset over mainland China containing 22,909 image patches for model training and evaluation, as well as two datasets covering 40 heterogeneous regions worldwide for external evaluation. Subsequently, grounded in the surface energy balance (SEB)-based geophysical reasoning, we proposed the physically guided diffusion model (PGDM) for LST downscaling. In this framework, the downscaling task was formulated as an inference problem, aiming to sample from the posterior distribution of high-spatial-resolution (HR) LST conditioned on low-spatial-resolution (LR) LST observations and a suite of HR geophysical priors. Comprehensive evaluations demonstrate the effectiveness of PGDM, which generates high-quality downscaling results and outperforms existing representative interpolation, kernel-driven, hybrid, and deep learning approaches. Finally, by exploiting the inherent stochasticity of PGDM, the scene-level standard deviation of multiple generations was computed, revealing a strong positive linear correlation with the actual downscaling error...