Weather-Related Crash Risk Forecasting: A Deep Learning Approach for Heterogenous Spatiotemporal Data

TL;DR

This paper presents a deep learning ensemble framework using ConvLSTM models to forecast weather-related traffic crash risks across heterogeneous spatiotemporal data, outperforming traditional models especially in high-risk zones.

Contribution

It introduces an ensemble of ConvLSTM models that effectively captures spatial and temporal dependencies in crash risk forecasting, addressing heterogeneity in weather and traffic data.

Findings

Ensembled ConvLSTM outperforms baseline models in MSE and RMSE.

The approach is particularly effective in high-risk, volatile areas.

Model improves crash risk prediction accuracy across diverse weather conditions.

Abstract

This study introduces a deep learning-based framework for forecasting weather-related traffic crash risk using heterogeneous spatiotemporal data. Given the complex, non-linear relationship between crash occurrence and factors such as road characteristics, and traffic conditions, we propose an ensemble of Convolutional Long Short-Term Memory (ConvLSTM) models trained over overlapping spatial grids. This approach captures both spatial dependencies and temporal dynamics while addressing spatial heterogeneity in crash patterns. North Carolina was selected as the study area due to its diverse weather conditions, with historical crash, weather, and traffic data aggregated at 5-mi by 5-mi grid resolution. The framework was evaluated using Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and spatial cross-K analysis. Results show that the ensembled ConvLSTM significantly outperforms baseline models, including linear regression, ARIMA, and standard ConvLSTM, particularly in high-risk zones. The ensemble approach effectively combines the strengths of multiple ConvLSTM models, resulting in lower MSE and RMSE values across all regions, particularly when data from different crash risk zones are aggregated. Notably, the model performs exceptionally well in volatile high-risk areas (Cluster 1), achieving the lowest MSE and RMSE, while in stable low-risk areas (Cluster 2), it still improves upon simpler models but with slightly higher errors due to challenges in capturing subtle variations.