Explainable machine learning with multi-source data for community fire risk prediction
Proceedings of the Institution of Civil Engineers - Engineering Sustainability · 19.11.2026 · 1-29
DOI: 10.1680/jensu.26.00118 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the Institution of Civil Engineers - Engineering Sustainability, online erschienen am 19.11.2026. Verfasst von Huiyu Cheng und 6 weiteren Autor:innen. Die Arbeit nennt 48 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Fires pose a significant threat to citizens’ lives, property, and overall urban safety. While research has extensively focused on forest fire risk assessment and prediction, comparatively little attention has been given to evaluating fire danger in large metropolitan areas. This study integrates data from Yuncheng City, China – including building characteristics, road networks, population distribution, fire occurrence records, and meteorological parameters to facilitate a geographically informed analysis. Various machine learning models were trained to assess fire risk throughout the city. The findings demonstrate that the XGBoost model exhibits high predictive accuracy and strong spatial correlation, rendering it suitable for geographic analysis. This research identifies potential fire risks within urban areas, offering a scientific basis for the strategic deployment of firefighting resources and informed urban planning to mitigate losses of life and property.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Cheng, H., Chen, M., Yue, T., Wan, H., Wang, D., Feng, Y., & Xu, S. (2026). Explainable machine learning with multi-source data for community fire risk prediction. Proceedings of the Institution of Civil Engineers - Engineering Sustainability, 1-29. https://doi.org/10.1680/jensu.26.00118
Vancouver
Cheng H, Chen M, Yue T, Wan H, Wang D, Feng Y, et al. Explainable machine learning with multi-source data for community fire risk prediction. Proceedings of the Institution of Civil Engineers - Engineering Sustainability. 2026:1-29. doi:10.1680/jensu.26.00118
BibTeX
@article{Cheng2026,
author = {Cheng, Huiyu and Chen, Mengyu and Yue, Tian and Wan, Hengshao and Wang, Ding and Feng, Yue and Xu, Shan},
title = {Explainable machine learning with multi-source data for community fire risk prediction},
journal = {Proceedings of the Institution of Civil Engineers - Engineering Sustainability},
year = {2026},
pages = {1--29},
doi = {10.1680/jensu.26.00118}
}
EUVIMED