Prof. Xinyan HUANG, member of The State Key Laboratory of Climate Resilience for Coastal Cities and Associate Professor of the Department of Building Environment and Energy Engineering (BEE), alongside PhD candidate Weikang XIE, has developed an innovative LLM-AI self-driven emergency response agent framework.
Integrating ChatGPT-4o with the ConvLSTM-Fire prediction model via AIoT technology, the newly developed system autonomously conducts situational awareness, data analysis, and task execution under natural language prompts. Remarkably, the system maintains over 97% temperature field prediction accuracy even during sensor failures, representing a significant technological leap forward for smart firefighting and emergency management in complex urban environments.
This remarkable achievement has garnered online media coverage, including by Sciencenet, highlighting our laboratory's commitment to leveraging artificial intelligence to enhance urban safety and climate resilience.
We look forward to Prof. HUANG and his team continued contributions to smart urban safety and disaster mitigation!
Online coverage (Chinese Only):
https://news.sciencenet.cn/htmlnews/2026/9/570800.shtm