SPyCer: Semi-Supervised Physics-Guided Contextual Attention for Near-Surface Air Temperature Estimation from Satellite Imagery

TL;DR

SPyCer is a semi-supervised, physics-guided neural network that estimates near-surface air temperature from satellite imagery by integrating physical models and attention mechanisms, improving accuracy and physical consistency.

Contribution

It introduces a novel semi-supervised, physics-informed deep learning framework for continuous near-surface air temperature estimation from satellite data, incorporating physical constraints and land cover information.

Findings

SPyCer outperforms existing methods in accuracy and generalization.

The model produces spatially coherent and physically consistent temperature maps.

Incorporating physical models enhances the reliability of satellite-based temperature estimation.

Abstract

Modern Earth observation relies on satellites to capture detailed surface properties. Yet, many phenomena that affect humans and ecosystems unfold in the atmosphere close to the surface. Near-ground sensors provide accurate measurements of certain environmental characteristics, such as near-surface air temperature (NSAT). However, they remain sparse and unevenly distributed, limiting their ability to provide continuous spatial measurements. To bridge this gap, we introduce SPyCer, a semi-supervised physics-guided network that can leverage pixel information and physical modeling to guide the learning process through meaningful physical properties. It is designed for continuous estimation of NSAT by proxy using satellite imagery. SPyCer frames NSAT prediction as a pixel-wise vision problem, where each near-ground sensor is projected onto satellite image coordinates and positioned at the center of a local image patch. The corresponding sensor pixel is supervised using both observed NSAT and physics-based constraints, while surrounding pixels contribute through physics-guided regularization derived from the surface energy balance and advection-diffusion-reaction partial differential equations. To capture the physical influence of neighboring pixels, SPyCer employs a multi-head attention guided by land cover characteristics and modulated with Gaussian distance weighting. Experiments on real-world datasets demonstrate that SPyCer produces spatially coherent and physically consistent NSAT estimates, outperforming existing baselines in terms of accuracy, generalization, and alignment with underlying physical processes.