2026-09-19T15:44:24Zhttps://ecommons.cornell.edu/server/oai/requestoai:ecommons.cornell.edu:1813/1144842026-05-15T19:43:36Zcom_1813_35col_1813_47
Wilson, Jeswin
Zhang, Ke
Ault, Toby
Orr, David
2024-04-05T18:36:31Z
2024-04-05T18:36:31Z
2023-08
ProQuest Submission ID: 11922
ProQuest Publication ID: 30630973
https://hdl.handle.net/1813/114484
https://doi.org/10.7298/mw3f-sb57
16219244
105 pages
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.
en
Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/
computer vision
machine learning
road surface temperatures
road weather information system
winter road conditions
FORECASTING WINTER ROAD CONDITIONS: A DATA-DRIVEN APPROACH
dissertation or thesis
https://newcatalog.library.cornell.edu/catalog/16219244
application/pdf
Mechanical Engineering
Cornell University
Master of Science
M.S., Mechanical Engineering
https://hdl.handle.net/1813/59810.2
Publication
Cornell Theses and Dissertations
Wilson, Jeswin
5893a6ea-7af3-41d7-abc6-04bcd26ab5df
open.access
open.access
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="08ae9478-d8f2-4440-8242-19de382464e0">
<Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type>
<Language>en</Language>
<Title>FORECASTING WINTER ROAD CONDITIONS: A DATA-DRIVEN APPROACH</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2023-08</PublicationDate>
<DOI>https://doi.org/10.7298/mw3f-sb57</DOI>
<Authors>
<Author>
<DisplayName>Wilson, Jeswin</DisplayName>
<Affiliation>
<OrgUnit>
</OrgUnit>
</Affiliation>
</Author>
</Authors>
<Editors>
</Editors>
<Publishers>
<Publisher>
<OrgUnit />
</Publisher>
</Publishers>
<License>https://creativecommons.org/licenses/by/4.0/</License>
<Keyword>computer vision</Keyword>
<Keyword>machine learning</Keyword>
<Keyword>road surface temperatures</Keyword>
<Keyword>road weather information system</Keyword>
<Keyword>winter road conditions</Keyword>
<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.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>