EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Bidirectional Spatiotemporal Deep Learning Model with Integrated Vegetation–Thermal Features for Wildfire Detection

Han Luo, Ming Wang, Lei He, Bin Liu, Yuxia Li, Dan Tang

Remote Sensing · 29.04.2026 · 18 (9) · 1376

DOI: 10.3390/rs18091376 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 29.04.2026. Verfasst von Han Luo und 5 weiteren Autor:innen. Die Arbeit nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Science and Technology Department of Sichuan Province, Sichuan Academy of Agricultural Sciences.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Quicker identifying abilities are required due to the rising frequency and severity of wildfires. Although polar-orbiting satellites with medium and high resolution can accurately identify wildfires, the majority of available fire detection images originate from such platforms. However, their low temporal revisit rates restrict the potential for early warning. Geostationary satellites provide minute-level, continuous monitoring that corresponds with the quick onset of wildfires; however, their dependence on conventional threshold methods and coarse spatial resolution result in notable detection errors. This study developed an integrated deep learning framework for accurate wildfire detection in low-resolution geostationary imagery in order to get over these restrictions. A novel dynamic index, the Dynamic Normalized Burn Ratio—Thermal (DNBRT), was proposed to characterize wildfire progression by integrating instantaneous thermal anomalies with dynamic vegetation signals. Based on this, a Fire Spatiotemporal Network (FST-Net) was designed, with an efficient residual backbone, a Convolutional Block Attention Module (CBAM) for feature refinement, and a Bidirectional Long Short-Term Memory (BiLSTM) network to capture temporal evolution. Trained and evaluated on an FY-4B-based fire/non-fire dataset, the proposed framework demonstrated superior performance. FST-Net outperformed benchmark models, improving accuracy and recall by averages of 10.30% and 9.32% respectively while achieving faster inference speed. An ablation experiment confirmed the critical role of fusing thermal and vegetation features in DNBRT, with 92.7% accuracy and 94.9% recall. Compared to the FY-4B fire product, the proposed framework enables earlier detection, maintains more complete tracking of fire progression, and exhibits greater robustness under complex burning conditions while achieving sub-hectare (0.36 ha) detection sensitivity at the 2 km resolution. By synergizing a discriminative dynamic index with an efficient spatiotemporal architecture, this work provides an effective solution for operational, real-time monitoring of small and early-stage wildfires from geostationary satellites.

Förderung

  • Science and Technology Department of Sichuan Province
  • Sichuan Academy of Agricultural Sciences

Zitieren

APA

Luo, H., Wang, M., He, L., Liu, B., Li, Y., & Tang, D. (2026). A Bidirectional Spatiotemporal Deep Learning Model with Integrated Vegetation–Thermal Features for Wildfire Detection. Remote Sensing, 18(9), 1376. https://doi.org/10.3390/rs18091376

Vancouver

Luo H, Wang M, He L, Liu B, Li Y, Tang D. A Bidirectional Spatiotemporal Deep Learning Model with Integrated Vegetation–Thermal Features for Wildfire Detection. Remote Sensing. 2026;18(9):1376. doi:10.3390/rs18091376

BibTeX
@article{Luo2026,
  author = {Luo, Han and Wang, Ming and He, Lei and Liu, Bin and Li, Yuxia and Tang, Dan},
  title = {A Bidirectional Spatiotemporal Deep Learning Model with Integrated Vegetation–Thermal Features for Wildfire Detection},
  journal = {Remote Sensing},
  year = {2026},
  volume = {18},
  number = {9},
  pages = {1376},
  doi = {10.3390/rs18091376}
}
Kostenlos starten →