Save It for the “Hot” Day: An LLM-Empowered Visual Analytics System for Heat Risk Management
- 7 July 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 31 (10) , 8928-8943
Abstract
The escalating frequency and intensity of heat-related climate events, particularly heatwaves, emphasize the pressing need for advanced heat risk management strategies. Current approaches, primarily relying on numerical models, face challenges in spatial-temporal resolution and in capturing the dynamic interplay of environmental, social, and behavioral factors affecting heat risks. This has led to difficulties in translating risk assessments into effective mitigation actions. Recognizing these problems, we introduce a novel approach leveraging the burgeoning capabilities of Large Language Models (LLMs) to extract rich and contextual insights from news reports. We hence propose an LLM-empowered visual analytics system, Havior, that integrates the precise, data-driven insights of numerical models with nuanced news report information. This hybrid approach enables a more comprehensive assessment of heat risks and better identification, assessment, and mitigation of heat-related threats. The system incorporates novel visualization designs, such as “thermoglyph” and news glyph, enhancing intuitive understanding and analysis of heat risks. The integration of LLM-based techniques also enables advanced information retrieval and semantic knowledge extraction that can be guided by experts’ analytics needs. We conducted an experiment on information extraction, a case study on the 2022 China Heatwave, and an expert survey & interview collaborated with six domain experts, demonstrating the usefulness of our system in providing in-depth and actionable insights for heat risk management.Keywords
All Related Versions
Funding Information
- Hong Kong Research Grants Council (AoE/P601/23N)
- Theme-based Research Scheme of the Hong Kong Special Administrative Region, China (T31-603/21-N)
- National Science Foundation (IIS-2427770)
This publication has 64 references indexed in Scilit:
- CafeLLM: Context-Aware Fine-Grained Semantic Clustering Using Large Language Models2024
- The extreme heat wave in China in August 2022 related to extreme northward movement of the eastern center of SAHAtmospheric Research, 2023
- Mortality burden attributable to high and low ambient temperatures in China and its provinces: Results from the Global Burden of Disease Study 2019The Lancet Regional Health - Western Pacific, 2022
- A downscaling approach for constructing high-resolution precipitation dataset over the Tibetan Plateau from ERA5 reanalysisAtmospheric Research, 2021
- Understanding the evolutions of public responses using social media: Hurricane Matthew case studyInternational Journal of Disaster Risk Reduction, 2020
- The ERA5 global reanalysisQuarterly Journal of the Royal Meteorological Society, 2020
- Record-breaking heat wave in southern China and delayed onset of South China Sea summer monsoon driven by the Pacific subtropical highClimate Dynamics, 2020
- Impacts of heat waves and corresponding measures: a reviewJournal of Cleaner Production, 2015
- Effects of temperature on mortality in Hong Kong: a time series analysisInternational Journal of Biometeorology, 2014
- Avoiding the avoidable: Towards a European heat waves risk governanceInternational Journal of Disaster Risk Science, 2011