Highway-Rail Crossing Accident Analysis Using Bayesian Belief Networks

Bernstein, Tyler; Palese, Joseph W; Zarembski, Allan M.

i

Highway-Rail Crossing Accident Analysis Using Bayesian Belief Networks

2021-09-10
By Bernstein, Tyler ; Palese, Joseph W ; Zarembski, Allan M.

File Language:

English

Details

Creators:

Bernstein, Tyler ; Palese, Joseph W ; Zarembski, Allan M.
Corporate Creators:

University of Delaware. Department of Civil and Environmental Engineering ; University Transportation Center on Improving Rail Transportation Infrastructure Sustainability and Durability. USDOT Tier 1
Corporate Contributors:

United States. Department of Transportation. University Transportation Centers (UTC) Program ; United States. Department of Transportation. Office of the Assistant Secretary for Research and Technology
Subject/TRT Terms:
Publication/ Report Number:

RailTEAM UD-11
Resource Type:

Tech Report
Geographical Coverage:

United States
Corporate Publisher:

University of Nevada. University Transportation Center on Improving Rail Transportation Infrastructure Sustainability and Durability
Abstract:

The rate of highway-rail grade crossing collisions has steadily increased year over year since 2009, after a decades long period of decline, beginning in 1972. Several models exist that predict the likelihood and number of collisions at crossings. These models have decreased in accuracy as they have aged. This research employed Bayesian statistics and its graphical representation, Bayesian belief networks, to develop a new model that predicts the probability of a collision at a railway/highway grade crossing, as a function of known characteristics, readily available through open-source data. The final model was found to be a relatively accurate predictor of collision likelihood but showed deficiencies that prevent its use in practical application. Despite these deficiencies, utilizing Bayesian statistics remains a promising method of predicting collision likelihood at a grade crossing, and further study into this application should be conducted.
Format:

PDF
Funding:

69A3551747132
Download URL:

https://rosap.ntl.bts.gov/view/dot/82319/dot_82319_DS1.pdf
File Type:

[PDF - 2.32 MB]
Collection(s):

University Transportation Centers
Main Document Checksum:

urn:sha-512:72c6e1696139a0a01dd4104b156df9b64d2813a254f9035b759c6bfea875f894de8c5e22705c572aa2a83946182b493c1afd45e4056c4aa9de0ad5214a2cf7bb

File Language:

English

ON THIS PAGE

Details

Found an issue?

Send us an email at:

publishinghd@cdc.gov

ROSA P serves as an archival repository of USDOT-published products including scientific findings, journal articles, guidelines, recommendations, or other information authored or co-authored by USDOT or funded partners. As a repository, ROSA P retains documents in their original published format to ensure public access to scientific information.