2026-07-16 ヒューストン大学
A University of Houston engineer is using AI to connect transportation data, uncovering patterns that could improve road safety.
＜関連情報＞
- https://www.uh.edu/news-events/stories/2026/july/gao-road-crash-ai.php
- https://www.sciencedirect.com/science/article/abs/pii/S0001457526002186
舗装路面の状態記録とLLMベースの事故状況分析を統合した舗装路面の安全性評価 Integrating pavement condition records with LLM-based crash narrative analysis for pavement safety assessment
Sarayu Varma Gottimukkala, Lu Gao, Nasir Gharaibeh, Yussuf Tarnini, Mohammad Talebzadeh, Boni Kutela, Tejaswini Sanjay Katale
Accident Analysis & Prevention Available online 31 May 2026
DOI:https://doi.org/10.1016/j.aap.2026.108609
Highlights
- We label crash narratives by pavement mechanism using a prompted LLM.
- We link narrative labels to pavement condition, friction, and texture data.
- We estimate pavement factor effects with quantile regression.
- A 24,000-narrative case study links friction and texture to wet crashes.
- The workflow connects crash narratives to pavement maintenance screening.
Abstract
This paper proposes an integrated framework that couples Large Language Models (LLMs)-based crash narrative analysis with quantile regression to identify and quantify pavement-related crash risk. The LLM component converts unstructured police narratives into structured, mechanism-specific labels (e.g., hydroplaning, curve-related loss of control), which enables outcomes that are directly linked to pavement and roadway-surface conditions that are often missing from conventional structured crash fields. These LLM-derived mechanism labels are then matched to segment-level pavement condition, friction, texture, traffic exposure, and geometric characteristics and modeled using quantile regression to characterize how covariate effects vary across the full distribution of crash risk rather than only at the mean. A case study using over 24,000 police crash narratives linked to a pavement management dataset of approximately 180,000 data records demonstrates strong associations between friction/texture measures and wet-pavement crash mechanisms. These results can help transportation agencies select candidate pavement-safety projects by identifying pavement conditions associated with elevated crash risk and prioritizing targeted, cost-effective countermeasures.
