|
|
NDSU Research Applies Machine Learning to Identify Causes of Rail AccidentsPosted: Apr 26, 2021
Raj Bridgelall, an assistant professor of transportation, logistics and finance, tested 11 different types of machine learning methods and found that a method known as extreme gradient boosting was most effective at predicting accident type. The method showed that derailments were most closely associated with lower track classes, non-signalized areas and rail movement authorizations within areas with restricted weight and speed limits. Bridgelall is a researcher with NDSU's Upper Great Plains Transportation Institute. Denver Tolliver, director of the institute, was co-author of the article, "Railroad Accident Analysis Using Extreme Gradient Boosting." The full article can be read at DOI: 10.1016/j.aap.2021.106126. Railroads lose hundreds of millions of dollars from accidents each year with derailments consistently accounting for more than 70 percent of the U.S. rail industry's average annual accident cost. Bridgelall notes that computer and statistical modeling and machine learning techniques that improve knowledge of factors most closely related to derailments can help railroads develop more cost-effective and impactful strategies for reducing derailments. |
A North Dakota State University researcher tested machine learning techniques to identify key causes of railroad accidents in a study recently published in the Journal Accident Analysis and Prevention.