AI-Driven Fire Forecast and Smart Firefighting
We propose a SureFire System that adopts the complex data generating networks that enable real-time monitoring of the evolution of urban environments and hazards. We gathered a multi-disciplinary team with leading local and international researchers and research laboratories (NIST, SKLFS), Fire Services Department, and multiple high-tech companies (Huawei, Arup, Ehang) to develop the technology and standard for a Smart Firefighting System. SureFire.
The proposed smart firefighting system adopts the complex data generating networks that enable real-time monitoring of the evolution of urban environments and hazards. Proper analysis of this data based on artificial intelligence can deliver information that continuously determines the state and evolution of systems and diagnoses emergent pathologies and support the decision making. Implementation of such a system for smart firefighting will help Hong Kong achieve the status of the world's leading smart city.
-
Super real-time fire forecasting
-
Fast communication
-
Data-driven science-based tactics
-
Information-rich decision making
Funding:
-
Smart Forecast of Backdraft Risk and Explosion Hazards Driven by Sensor Data and Fire Images, RGC GRF, HK$1.2M, PI, 2026 - 28
-
Key Technologies for Intelligent Firefighting and Emergency Management in Confined Urban Transportation Infrastructure, National Key R&D Program of China + ITC, HK$2.2M, PI, 2025 - 27;
-
A Digital Twin Intelligent Platform for Aged Building Digitalization and Fire Safety Management, Innovation and Technology Fund, HK$4.1M, co-PI, 2025 - 27.
-
Intelligent Emergency Digital Twin System in Metro Station for Fire Evacuation, MTR Research Funding Scheme, HK$1.4M, PI, 2024 - 26
-
SureFire: Smart Urban Resilience and Firefighting, RGC Theme-based Research Scheme, HK$33M, 2020 - 25;
-
Smart Firefighting System for the Sustainable Development of the Greater Bay Area, RISUD Emerging Frontier Area Fund, HK$1.2M, 2020 - 22;
Collaborators: Asif Usmani, Fu Xiao (BSE), Qixin Wang (COMP), Heng Li (BRE), John Shi (LSGI), George Huang; Stephen Welch (Edinburgh), Jose Torero (UCL), Xinzheng Lu (Tsinghua), Andy Tam (NIST), Arup, Ehang, Sichuan Fire Research Institute, University of Science and Technology of China.
Project Members
Zilong Wang
Yifei Ding
Xiaoning Zhang
Wai Kit Cheung
Ho Yin Wong
Yanfu Zeng
Tianhang Zhang
Yizhou Li
5 Representative publications:
-
W. Xie, Y. Zhang*, T. Lu, X. Huang, J. Shi*, X. Huang*, F. Xiao, A. Usmani (2026) Integrating Smart Fire Forecast with LLM-Powered Emergency Response, Engineering, doi: 10.1016/j.eng.2026.02.023
-
X. Zhang, X. Chen, Y. Ding, Y. Zhang*, Z. Wang, J. Shi, N. Johansson*, X. Huang* (2024) Smart real-time evaluation of tunnel fire risk and evacuation safety via computer vision, Safety Science, 106563. doi: 10.1016/j.ssci.2024.106563
-
T. Zhang, Z. Wang, H.Y. Wong, W.C. Tam, X. Huang, F. Xiao (2022) Real-time Forecast of Compartment Fire and Flashover based on Deep Learning, Fire Safety Journal, 129, 103579.
-
Z. Wang, T. Zhang, X. Huang (2022) Predicting Real-time Fire Heat Release Rate based on Flame Images and Deep Learning, Proceedings of the Combustion Institute, 39.
-
L. Su, X. Wu, X. Zhang, X. Huang (2021) Smart Performance-Based Design for Building Fire Safety: Prediction of Smoke Motion via AI, Journal of Building Engineering, 43, 102529.