Beta Distribution Learning for Reliable Roadway Crash Risk Assessment

TL;DR

This paper presents a geospatial deep learning framework that uses satellite imagery to estimate crash risk as a Beta distribution, providing uncertainty-aware predictions that improve safety assessments and decision-making.

Contribution

It introduces a novel model that captures spatial risk factors and estimates a full Beta distribution, enhancing reliability and interpretability over traditional point-estimate methods.

Findings

Achieves 17-23% improvement in recall over baselines

Provides calibrated, uncertainty-aware risk predictions

Enables scalable, cost-effective safety assessments using satellite imagery

Abstract

Roadway traffic accidents represent a global health crisis, responsible for over a million deaths annually and costing many countries up to 3% of their GDP. Traditional traffic safety studies often examine risk factors in isolation, overlooking the spatial complexity and contextual interactions inherent in the built environment. Furthermore, conventional Neural Network-based risk estimators typically generate point estimates without conveying model uncertainty, limiting their utility in critical decision-making. To address these shortcomings, we introduce a novel geospatial deep learning framework that leverages satellite imagery as a comprehensive spatial input. This approach enables the model to capture the nuanced spatial patterns and embedded environmental risk factors that contribute to fatal crash risks. Rather than producing a single deterministic output, our model estimates a full Beta probability distribution over fatal crash risk, yielding accurate and uncertainty-aware predictions--a critical feature for trustworthy AI in safety-critical applications. Our model outperforms baselines by achieving a 17-23% improvement in recall, a key metric for flagging potential dangers, while delivering superior calibration. By providing reliable and interpretable risk assessments from satellite imagery alone, our method enables safer autonomous navigation and offers a highly scalable tool for urban planners and policymakers to enhance roadway safety equitably and cost-effectively.