eCommons

 

FORECASTING WINTER ROAD CONDITIONS: A DATA-DRIVEN APPROACH

Other Titles

Abstract

Annually, 24% of weather-related vehicle crashes happen on snowy, slushy, or icy roads in the United States. Accurate prediction of road surface temperatures and conditions is crucial for ensuring safe and efficient transportation, especially during winter. In this study, we developed machine learning and computer vision models for predicting road surface temperatures and conditions using historical meteorological and road surface sensor data and images. We implemented machine learning algorithms to build models that can predict road surface temperatures and conditions with high accuracy. We also developed computer vision models to detect real-time road surface conditions, including dry, wet, ice, snow, and slush, based on real-time road surface image data. Integration of temperature prediction models, surface condition prediction models, and computer vision models into existing road weather information system (RWIS) networks has the potential to provide accurate predictive information on road surface temperatures and conditions, enhancing the safety and efficiency of transportation systems, especially in rural communities where there are limited RWIS resources.

Journal / Series

Volume & Issue

Description

105 pages

Sponsorship

Date Issued

2023-08

Publisher

Keywords

computer vision; machine learning; road surface temperatures; road weather information system; winter road conditions

Location

Effective Date

Expiration Date

Sector

Employer

Union

Union Local

NAICS

Number of Workers

Committee Chair

Zhang, Ke

Committee Co-Chair

Committee Member

Ault, Toby
Orr, David

Degree Discipline

Mechanical Engineering

Degree Name

M.S., Mechanical Engineering

Degree Level

Master of Science

Related Version

Related DOI

Related To

Related Part

Based on Related Item

Has Other Format(s)

Part of Related Item

Related To

Related Publication(s)

Link(s) to Related Publication(s)

References

Link(s) to Reference(s)

Previously Published As

Government Document

ISBN

ISMN

ISSN

Other Identifiers

Rights

Attribution 4.0 International

Types

dissertation or thesis

Accessibility Feature

Accessibility Hazard

Accessibility Summary

Link(s) to Catalog Record