SPyCer: Semi-Supervised Physics-Guided Contextual Attention for Near-Surface Air Temperature Estimation from Satellite Imagery
#SPyCer #satellite imagery #temperature estimation #semi-supervised learning #physics-guided #contextual attention #near-surface air
📌 Key Takeaways
- SPyCer is a new method for estimating near-surface air temperature from satellite data.
- It uses a semi-supervised learning approach to reduce reliance on labeled data.
- The model incorporates physics-guided constraints to improve accuracy and physical consistency.
- It employs a contextual attention mechanism to better capture spatial relationships in imagery.
📖 Full Retelling
arXiv:2603.05219v1 Announce Type: cross
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 b
🏷️ Themes
Remote Sensing, Machine Learning, Climate Science
Entity Intersection Graph
No entity connections available yet for this article.
Original Source
--> Computer Science > Computer Vision and Pattern Recognition arXiv:2603.05219 [Submitted on 5 Mar 2026] Title: SPyCer: Semi-Supervised Physics-Guided Contextual Attention for Near-Surface Air Temperature Estimation from Satellite Imagery Authors: Sofiane Bouaziz , Adel Hafiane , Raphael Canals , Rachid Nedjai View a PDF of the paper titled SPyCer: Semi-Supervised Physics-Guided Contextual Attention for Near-Surface Air Temperature Estimation from Satellite Imagery, by Sofiane Bouaziz and 3 other authors View PDF HTML 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 . 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 cohe...
Read full article at source