From Perceptions to Decisions: Wildfire Evacuation Decision Prediction with Behavioral Theory-informed LLMs

2025-02-24

AI Summary

This study addresses the challenge of predicting individual evacuation decisions during wildfires. We propose FLARE, a novel framework that— for the first time—systematically integrates behavioral theory into the chain-of-thought (CoT) reasoning process of large language models (LLMs), explicitly modeling psychological states and preference conflicts. FLARE further couples a memory-augmented reinforcement learning module to jointly achieve dynamic adaptability and interpretability. By bridging theoretical constructs with empirical data, it mitigates theory–data mismatch and supports cross-event generalization. Evaluated on three real-world post-wildfire survey datasets, FLARE achieves an average 20.47% improvement in prediction accuracy over conventional theory-driven models. Its interpretable, individual-level decision support capability advances emergency management with both high fidelity and transparency.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning
• Knowledge Representation and Reasoning: Preferences

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

Evacuation decision prediction is critical for efficient and effective wildfire response by helping emergency management anticipate traffic congestion and bottlenecks, allocate resources, and minimize negative impacts. Traditional statistical methods for evacuation decision prediction fail to capture the complex and diverse behavioral logic of different individuals. In this work, for the first time, we introduce FLARE, short for facilitating LLM for advanced reasoning on wildfire evacuation decision prediction, a Large Language Model (LLM)-based framework that integrates behavioral theories and models to streamline the Chain-of-Thought (CoT) reasoning and subsequently integrate with memory-based Reinforcement Learning (RL) module to provide accurate evacuation decision prediction and understanding. Our proposed method addresses the limitations of using existing LLMs for evacuation behavioral predictions, such as limited survey data, mismatching with behavioral theory, conflicting individual preferences, implicit and complex mental states, and intractable mental state-behavior mapping. Experiments on three post-wildfire survey datasets show an average of 20.47% performance improvement over traditional theory-informed behavioral models, with strong cross-event generalizability. Our complete code is publicly available at https://github.com/SusuXu-s-Lab/FLARE

Problem

• Predict wildfire evacuation decisions
• Integrate behavioral theories with LLMs
• Improve traditional evacuation prediction methods

Innovation

• LLM integrates behavioral theories
• Memory-based Reinforcement Learning module
• Chain-of-Thought reasoning enhancement