Back to search

Hosted by Utah State University Libraries

Network-Wide Pedestrian and Bicycle Crash Analysis with Statistical and Machine Learning Models in Utah

Abstract

dc:description.abstract

Recent trends in crashes indicate a dramatic increase in both the number and share of pedestrian and bicyclist injuries and fatalities nationally and in many states. Crash frequency modeling was undertaken to identify crash prone characteristics of segments and non-signalized intersections and explore possible non-linear associations of explanatory variables with crashes. Crowdsourced “Strava” app data was used for bicycle volume, and pedestrian counts estimated from nearby signalized intersections were used as pedestrian volume. Multiple negative binomial models investigated crashes at different spatial scales to account for different levels of data availability and completeness. The models showed high traffic volume, steeper vertical grades on roads, frequent bus and rail stations, greater driveway density, more legs at intersections, streets with high large truck presence, greater residential and employment density, as a larger share of low-income households and non-white race/ethnicity groups are indicators of locations with more pedestrian and bicycle crashes. Crash severity model results showed that crashes occurring at mid-blocks and near vertical grades were more severe compared to crashes at intersections. High daily temperature, driving under influence, and distracted driving also increases injury severity in crashes. This study suggests potential countermeasures, policy implications, and the scope of future research for improving pedestrian and bicycle safety at segments and at non-signalized intersections.

Degree

thesis:*
Name thesis:degree_name
Master of Science (MS)
Level thesis:degree_level
Thesis
Discipline thesis:degree_discipline
Civil and Environmental Engineering
Grantor dc:publisher
Hosted by Utah State University Libraries

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Rahman, Md Rafiur
Contributors dc:contributor
  • Patrick Singleton
  • Ziqi Song
  • Michelle Mekker

Subjects

dc:subject × 6

Identifiers

dc:identifier.*

Chain of custody

source
Harvested from
Utah State University
Base URL
digitalcommons.usu.edu/do/oai/
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Rahman, Md Rafiur. Network-Wide Pedestrian and Bicycle Crash Analysis with Statistical and Machine Learning Models in Utah. Thesis thesis, Hosted by Utah State University Libraries, https://digitalcommons.usu.edu/etd/8423