The Weather Paradox: Why Precipitation Fails to Predict Traffic Accident Severity in Large-Scale US Data

TL;DR

This study evaluates the predictive power of environmental and temporal factors on traffic accident severity in the US, finding limited influence of precipitation and visibility, and highlighting data and modeling challenges.

Contribution

It introduces a large-scale US traffic accident dataset and assesses the effectiveness of machine learning models in predicting accident severity, revealing key predictors and limitations.

Findings

Time of day, location, and weather variables are strong predictors.

Precipitation and visibility have limited predictive power.

Mid-level severity accidents dominate the dataset, affecting model learning.

Abstract

This study investigates the predictive capacity of environmental, temporal, and spatial factors on traffic accident severity in the United States. Using a dataset of 500,000 U.S. traffic accidents spanning 2016-2023, we trained an XGBoost classifier optimized through randomized search cross-validation and adjusted for class imbalance via class weighting. The final model achieves an overall accuracy of 78%, with strong performance on the majority class (Severity 2), attaining 87% precision and recall. Feature importance analysis reveals that time of day, geographic location, and weather-related variables, including visibility, temperature, and wind speed, rank among the strongest predictors of accident severity. However, contrary to initial hypotheses, precipitation and visibility demonstrate limited predictive power, potentially reflecting behavioral adaptation by drivers under overtly hazardous conditions. The dataset's predominance of mid-level severity accidents constrains the model's capacity to learn meaningful patterns for extreme cases, highlighting the need for alternative sampling strategies, enhanced feature engineering, and integration of external datasets. These findings contribute to evidence-based traffic management and suggest future directions for severity prediction research.