---
title: "PhyRE-Net: A Physics-Anchored Network with Active Spatial Gating for Industrial Infrared Thermal Forecasting"
authors:
  - "Shuotong Yang"
  - "Haitao Zhang"
doi: "10.24963/ijcai.2026/577"
url: "https://ijcai.org/proceedings/2026/577"
pdf: "https://ijcai.org/proceedings/2026/0577.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "5182-5190"
track: "Main Track"
keywords:
  - "Machine Learning: Reinforcement learning"
  - "Machine Learning: Applications"
  - "Machine Learning: Time series and data streams"
---

# PhyRE-Net: A Physics-Anchored Network with Active Spatial Gating for Industrial Infrared Thermal Forecasting

Shuotong Yang, Haitao Zhang

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 5182-5190. DOI: [10.24963/ijcai.2026/577](https://doi.org/10.24963/ijcai.2026/577)

## Abstract

Spatiotemporal forecasting of infrared thermal fields is a critical technology for the predictive maintenance of industrial electrical control equipment. However, many existing methods are designed under index-based temporal representations and global regression objectives, which are not well aligned with schedule-driven, non-stationary industrial regimes and the long-tailed spatial distribution of safety-critical hotspots. To address these issues, this paper proposes PhyRE-Net, a physical-time-anchored network architecture featuring active spatial gating. Specifically, we first design the multi-period resolution rotary positional embeddings mechanism within the backbone, which injects absolute temporal features into attention geometry to align predicted phases with non-stationary production schedules. We then devise a reinforcement learning-driven spatial gating mechanism to dynamically modulate feature responses, actively shifting the computational focus from the dominant background to sparse but critical thermal anomalies. Extensive experiments on a large-scale real-world dataset covering seven types of heterogeneous electrical equipment show that PhyRE-Net achieves consistent improvements over strong baselines across all evaluated metrics. The source code is available at https://github.com/YST-10/PhyRE-Net.