Kong et al. (2026) Synergizing Smoke and Hotspot: A Visible-Infrared Co-Learning Framework with Dataset for Large-Scale Wildfire Detection

Identification

• Journal: IEEE Transactions on Geoscience and Remote Sensing
• Year: 2026
• Date: 2026-01-01
• Authors: Ziyang Kong, Qiang Xu, Youshi Ye, Jianhua Li, Weiwei Li
• DOI: 10.1109/tgrs.2026.3675975

Research Groups

Not available in the provided text.

Short Summary

This paper introduces a visible-infrared co-learning framework and an associated dataset for large-scale wildfire detection, leveraging the synergy between smoke and hotspot features.

Objective

• To develop and evaluate a visible-infrared co-learning framework that synergizes smoke and hotspot information for improved large-scale wildfire detection.

Study Configuration

• Spatial Scale: Large-scale (as indicated by the title). Specific geographical extent not available in the provided text.
• Temporal Scale: Not available in the provided text.

Methodology and Data

• Models used: A "Visible-Infrared Co-Learning Framework" is proposed. Specific model architectures (e.g., neural network types) are not detailed in the provided text.
• Data sources: Visible and infrared imagery data. A new dataset specifically for large-scale wildfire detection is also developed and utilized.

Main Results

Not available in the provided text.

Contributions

• Introduction of a novel visible-infrared co-learning framework designed to synergize smoke and hotspot features for wildfire detection.
• Creation and utilization of a new dataset tailored for large-scale wildfire detection.
• Advancement in wildfire detection methodologies by demonstrating the benefits of a co-learning approach combining different spectral features.

Funding

Not available in the provided text.

Citation

@article{Kong2026Synergizing,
  author = {Kong, Ziyang and Xu, Qiang and Ye, Youshi and Li, Jianhua and Li, Weiwei},
  title = {Synergizing Smoke and Hotspot: A Visible-Infrared Co-Learning Framework with Dataset for Large-Scale Wildfire Detection},
  journal = {IEEE Transactions on Geoscience and Remote Sensing},
  year = {2026},
  doi = {10.1109/tgrs.2026.3675975},
  url = {https://doi.org/10.1109/tgrs.2026.3675975}
}