Measuring Nonlinear Relationships and Spatial Heterogeneity of Influencing Factors on Traffic Crash Density Using GeoXAI

2025-12-16

AI Summary

This study addresses the spatial heterogeneity and nonlinear driving mechanisms underlying traffic crash density in Florida. We propose the first analytical framework integrating Geographic eXplainable Artificial Intelligence (GeoXAI) with our novel GeoShapley method—synergistically coupling XGBoost, Multiscale Geographically Weighted Regression (MGWR), and SHAP—to simultaneously disentangle nonlinear effects and spatial heterogeneity, producing block-level risk attribution maps. Results reveal distinct regional drivers: road and intersection density dominate in urban areas (e.g., Miami), whereas rural regions exhibit threshold effects driven by educational attainment and neighborhood compactness. Moreover, the four major metropolitan areas exhibit significantly stronger contributions from key risk factors compared to rural counterparts. The framework delivers interpretable, geographically tailored insights, enabling evidence-based, location-specific traffic safety interventions.

Technology Category

• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Humans and AI: Explainable AI (XAI) for Human Understanding
• Reasoning under Uncertainty: Causality

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

This study applies a Geospatial Explainable AI (GeoXAI) framework to analyze the spatially heterogeneous and nonlinear determinants of traffic crash density in Florida. By combining a high-performing machine learning model with GeoShapley, the framework provides interpretable, tract-level insights into how roadway characteristics and socioeconomic factors contribute to crash risk. Specifically, results show that variables such as road density, intersection density, neighborhood compactness, and educational attainment exhibit complex nonlinear relationships with crashes. Extremely dense urban areas, such as Miami, show sharply elevated crash risk due to intensified pedestrian activities and roadway complexity. The GeoShapley approach also captures strong spatial heterogeneity in the influence of these factors. Major metropolitan areas including Miami, Orlando, Tampa, and Jacksonville display significantly higher intrinsic crash contributions, while rural tracts generally have lower baseline risk. Each factor exhibits pronounced spatial variation across the state. Based on these findings, the study proposes targeted, geography-sensitive policy recommendations, including traffic calming in compact neighborhoods, adaptive intersection design, speed management on high-volume corridors such as I-95 in Miami, and equity-focused safety interventions in disadvantaged rural areas of central and northern Florida. Moreover, this paper compares the results obtained from GeoShapley framework against other established methods (e.g., SHAP and MGWR), demonstrating its powerful ability to explain nonlinearity and spatial heterogeneity simultaneously.

Problem

• Analyzes nonlinear relationships between road and socioeconomic factors and crash density
• Examines spatial heterogeneity of crash risk factors across Florida regions
• Proposes geography-sensitive traffic safety policies using explainable AI insights

Innovation

• Combines machine learning with GeoShapley for interpretable insights
• Analyzes nonlinear relationships between road features and crash density
• Captures spatial heterogeneity of factors across urban and rural areas