Identifying High-Risk Areas for Traffic Collisions in Montgomery, Maryland Using KDE and Spatial Autocorrelation Analysis

TL;DR

This study uses KDE and spatial autocorrelation to identify high-risk traffic collision areas in Montgomery, Maryland, providing insights for targeted safety interventions to reduce injuries and fatalities.

Contribution

It introduces a novel combination of KDE and spatial autocorrelation analysis for precise hotspot detection in Montgomery County.

Findings

Significant spatial clustering of collisions identified

Distinct patterns in urban and rural areas observed

Hotspot areas can inform targeted safety policies

Abstract

Despite a global decline in motor vehicle crash fatalities due to improved research and road safety policies, road traffic injuries remain a significant public health concern. The World Health Organization 2023 report highlights that road traffic injuries are the leading cause of death among individuals aged 5-29, with over half of fatalities involving pedestrians, cyclists, and motorcyclists. This study addresses this critical issue by identifying high-risk areas in Montgomery County, Maryland, contributing to the global goal of halving road traffic deaths and injuries by 2030. Using Kernel Density Estimation (KDE) and spatial autocorrelation analysis, we estimate collision densities and identify hotspots for targeted interventions. Our findings reveal significant spatial clustering of traffic collisions, with distinct patterns in densely populated urban areas and rural regions, offering valuable insights for policymakers to enhance road safety.