LLMs as World Models: Data-Driven and Human-Centered Pre-Event Simulation for Disaster Impact Assessment

TL;DR

This paper explores using large language models combined with multimodal data to simulate earthquake impacts, providing a data-driven, human-centered approach that improves pre-disaster planning accuracy.

Contribution

It introduces a novel framework leveraging LLMs and multimodal datasets for proactive earthquake impact simulation, demonstrating high correlation with real impact reports.

Findings

High correlation (0.88) with actual impact reports

Visual inputs significantly improve simulation accuracy

Techniques like RAG and ICL enhance performance

Abstract

Efficient simulation is essential for enhancing proactive preparedness for sudden-onset disasters such as earthquakes. Recent advancements in large language models (LLMs) as world models show promise in simulating complex scenarios. This study examines multiple LLMs to proactively estimate perceived earthquake impacts. Leveraging multimodal datasets including geospatial, socioeconomic, building, and street-level imagery data, our framework generates Modified Mercalli Intensity (MMI) predictions at zip code and county scales. Evaluations on the 2014 Napa and 2019 Ridgecrest earthquakes using USGS ''Did You Feel It? (DYFI)'' reports demonstrate significant alignment, as evidenced by a high correlation of 0.88 and a low RMSE of 0.77 as compared to real reports at the zip code level. Techniques such as RAG and ICL can improve simulation performance, while visual inputs notably enhance accuracy compared to structured numerical data alone. These findings show the promise of LLMs in simulating disaster impacts that can help strengthen pre-event planning.