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

2026-03-05

AI Summary

This study addresses the challenge of generating high-precision, spatially continuous estimates of near-surface air temperature (NSAT) given the sparsity and uneven distribution of observational stations. To this end, the authors formulate NSAT estimation as a pixel-level vision task and propose a semi-supervised learning framework that integrates physical priors with data-driven modeling. Specifically, they incorporate a physics-based regularizer derived from surface energy balance principles and a convection–diffusion–reaction partial differential equation. Furthermore, they design a multi-head attention mechanism guided by land cover information and weighted by Gaussian distance to enhance the physical consistency of spatial predictions. Experiments on real-world datasets demonstrate that the proposed method significantly outperforms existing approaches in terms of estimation accuracy, generalization capability, and adherence to physical constraints.

Technology Category

• Computer Vision: Remote Sensing / Geospatial AI
• Machine Learning: Semi-Supervised Learning
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

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.

Problem

• near-surface air temperature
• satellite imagery
• spatial estimation
• sensor sparsity
• Earth observation

Innovation

• semi-supervised learning
• physics-guided attention
• near-surface air temperature
• satellite imagery
• multi-head attention