Predicting Human Mobility in Disasters via LLM-Enhanced Cross-City Learning
This work addresses the need for accurate mobility predictions in disasters to aid early warnings and resource allocation, representing a domain-specific incremental advance.
The paper tackles the problem of predicting human mobility in disaster scenarios, where existing models fail due to pattern shifts, and achieves a 32.8% improvement in Acc@1 and a 35.0% improvement in F1-score for predicting immobility compared to baselines.
The vulnerability of cities to natural disasters has increased with urbanization and climate change, making it more important to predict human mobility in the disaster scenarios for downstream tasks including location-based early disaster warning and pre-allocating rescue resources, etc. However, existing human mobility prediction models are mainly designed for normal scenarios, and fail to adapt to disaster scenarios due to the shift of human mobility patterns under disaster. To address this issue, we introduce \textbf{DisasterMobLLM}, a mobility prediction framework for disaster scenarios that can be integrated into existing deep mobility prediction methods by leveraging LLMs to model the mobility intention and transferring the common knowledge of how different disasters affect mobility intentions between cities. This framework utilizes a RAG-Enhanced Intention Predictor to forecast the next intention, refines it with an LLM-based Intention Refiner, and then maps the intention to an exact location using an Intention-Modulated Location Predictor. Extensive experiments illustrate that DisasterMobLLM can achieve a 32.8\% improvement in terms of Acc@1 and a 35.0\% improvement in terms of the F1-score of predicting immobility compared to the baselines. The code is available at https://github.com/tsinghua-fib-lab/DisasterMobLLM.