Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2506.06355 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912418117976064 |
|---|---|
| author | Li, Lingyao Li, Dawei Ou, Zhenhui Xu, Xiaoran Liu, Jingxiao Ma, Zihui Yu, Runlong Deng, Min |
| author_facet | Li, Lingyao Li, Dawei Ou, Zhenhui Xu, Xiaoran Liu, Jingxiao Ma, Zihui Yu, Runlong Deng, Min |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_06355 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LLMs as World Models: Data-Driven and Human-Centered Pre-Event Simulation for Disaster Impact Assessment Li, Lingyao Li, Dawei Ou, Zhenhui Xu, Xiaoran Liu, Jingxiao Ma, Zihui Yu, Runlong Deng, Min Computers and Society Computational Engineering, Finance, and Science Computation and Language Computer Vision and Pattern Recognition 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. |
| title | LLMs as World Models: Data-Driven and Human-Centered Pre-Event Simulation for Disaster Impact Assessment |
| topic | Computers and Society Computational Engineering, Finance, and Science Computation and Language Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.06355 |