Western Transportation Institute

Permanent URI for this communityhttps://scholarworks.montana.edu/handle/1/35

The Western Transportation Institute is the country's largest National University Transportation Center focused on rural transportation issues. Because we live and work in rural communities, we understand the critical roles rural transportation plays in the lives of people, in the environment and in the economy. We draw from our eight integrated research groups to create solutions that work for our clients, sponsors and rural transportation research partners. WTI focuses on rural issues, but some of our program areas also address the concerns of the urban environment. Whatever the objective, we bring innovation and expertise to each WTI transportation research project. WTI's main facility with its state-of-the-art labs is adjacent to the Montana State University campus in Bozeman, Montana. We have additional offices in Alberta, Canada, and central Washington, and a large testing facility in rural Montana near Lewistown. Contact us to find out how to address your rural transportation research needs.

Browse

search.filters.applied.f.department: search.filters.department.Engineering

Search Results

Now showing 1 - 1 of 1
  • Thumbnail Image
    Item
    Risk mapping of wildlife–vehicle collisions across the state of Montana, USA: a machine-learning approach for imbalanced data along rural roads
    (Oxford University Press, 2024-05) Bell, Matthew; Wang, Yiyi; Ament, Rob
    Wildlife–vehicle collisions (WVCs) with large animals are estimated to cost the USA over 8 billion USD in property damage, tens of thousands of human injuries and nearly 200 human fatalities each year. Most WVCs occur on rural roads and are not collected evenly among road segments, leading to imbalanced data. There are a disproportionate number of analysis units that have zero WVC cases when investigating large geographic areas for collision risk. Analysis units with zero WVCs can reduce prediction accuracy and weaken the coefficient estimates of statistical learning models. This study demonstrates that the use of the synthetic minority over-sampling technique (SMOTE) to handle imbalanced WVC data in combination with statistical and machine-learning models improves the ability to determine seasonal WVC risk across the rural highway network in Montana, USA. An array of regularized variables describing landscape, road and traffic were used to develop negative binomial and random forest models to infer WVC rates per 100 million vehicle miles travelled. The random forest model is found to work particularly well with SMOTE-augmented data to improve the prediction accuracy of seasonal WVC risk. SMOTE-augmented data are found to improve accuracy when predicting crash risk across fine-grained grids while retaining the characteristics of the original dataset. The analyses suggest that SMOTE augmentation mitigates data imbalance that is encountered in seasonally divided WVC data. This research provides the basis for future risk-mapping models and can potentially be used to address the low rates of WVCs and other crash types along rural roads.
Copyright (c) 2002-2022, LYRASIS. All rights reserved.