Deep Learning, Machine Learning, or Statistical Models for Weather-Related Crash Severity Prediction [Research Brief]

Ogungbire, Abimbola; Kalambay, Panick; Gajera, Hardik; Pulugurtha, Srinivas S.

i

Deep Learning, Machine Learning, or Statistical Models for Weather-Related Crash Severity Prediction [Research Brief]

2023-12-01
By Ogungbire, Abimbola ; Kalambay, Panick ; Gajera, Hardik

File Language:

English

Details

Creators:

Ogungbire, Abimbola ; Kalambay, Panick ; Gajera, Hardik ; Pulugurtha, Srinivas S.
Corporate Creators:

Mineta Transportation Institute ; San Jose State University. College of Business ; University of North Carolina at Charlotte
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:

2320
Resource Type:

Brief
Geographical Coverage:

United States
Edition:

Research Brief
Corporate Publisher:

Mineta Transportation Institute
Abstract:

In the realm of traffic safety, weather-related road traffic crashes pose a significant public health concern, leading to numerous injuries and fatalities. Past research has explored crash severity prediction using statistical machine learning (ML) and deep learning (DL)models, each with its strengths and limitations. This study strategically selected a diverse set of models, including ordered logit and ordered probit models (OLM and OPM), random forest (RF),XGBoost, multi-layer perceptron neural network(MLP), and TabNet, to comprehensively assess their effectiveness in predicting crash severity while considering weather conditions. By including this array of models, this research offers valuable insights for traffic safety professionals to predict crash severity levels, enabling them to make informed decisions and allocate resources effectively to reduce the impact of weather-related crashes on road safety.
Format:

PDF
Download URL:

https://rosap.ntl.bts.gov/view/dot/73168/dot_73168_DS1.pdf
File Type:

[PDF - 944.09 KB]
Collection(s):

Artificial Intelligence Deployment Center of Excellence (AI COE) ; University Transportation Centers
Main Document Checksum:

urn:sha-512:591096c088a10fd4d3e03000b9b7609c46c95782fa119463adb08b2388c937c8f1846d3d4cad7f65792915c195d777923ecea3fc98eb202a2050761ad931b02f

File Language:

English

ON THIS PAGE

Details Related Documents

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.