Enhancing Heavy Vehicle Crash Prevention in North Dakota through Machine Learning and Weather Data Integration

Heavy vehicle crashes continue to be a persistent safety concern across the Midwest, with several states reporting disproportionately high rates of incidents involving large trucks. According to the National Safety Council, in 2023, North Dakota recorded 18% of its fatal crashes involving large trucks, placing it among the highest in the nation. Neighboring states, such as Nebraska (16%) and Iowa, also face elevated risks. Illinois reported 7,509 truck accidents in 2022, ranking among the top five states nationwide. In North Dakota, the risks are especially pronounced during the winter months. In 2023, 64% of heavy vehicle crashes occurred between October and March, with 81% of these crashes taking place in rural areas. These figures highlight how weather conditions and geography amplify the risk associated with large-truck travel in the region. Further, crashes in rural areas in challenging weather conditions poses immense issues for first responders and their ability to provide timely medical care to crash victims.   Traditional safety strategies have struggled to account for the dynamic, real-time factors that contribute to crash risk. Static approaches often fall short when adverse weather, road conditions, and traffic volume interact in unpredictable ways. This gap highlights the urgent need for predictive, data-driven solutions.  This proposal aims to investigate the application of machine learning (ML) models, combined with weather and crash data, to predict high-risk scenarios before accidents occur, to support planning for safety and emergency response needs. By leveraging predictive analytics, North Dakota could enhance resource allocation, deploy preventive interventions, and reduce the frequency and severity of heavy vehicle crashes. The high incidence of winter crashes and the limitations of conventional methods make North Dakota an ideal proving ground for an innovative, ML-driven approach to roadway safety.  The study will utilize historical crash records for heavy vehicles in North Dakota, including crash type, severity, date, and time, combined with corresponding weather data such as temperature, precipitation, snowfall, and visibility. Feature engineering will create representations of temporal and weather conditions relevant to crash severity. Machine learning models, including Random Forest, XGBoost, and Neural Networks, will be trained to predict crash severity. To ensure interpretability, SHAP (SHapley Additive exPlanations) will be applied to quantify the contribution of each feature to individual predictions and overall model behavior. This analysis will reveal which weather or temporal factors most strongly influence severe crashes, both globally across the dataset and locally for specific incidents. High-risk periods and conditions identified by the model, along with explanations provided via SHAP, will be visualized both temporally and geographically, offering actionable insights to support targeted preventive measures and inform DOT decision-making. 

Language

• English

Project

• Status: Active
• Funding: $204,084.00
• Contract Numbers:

  69A3552348329

• Sponsor Organizations:

  Office of the Assistant Secretary for Research and Technology

  University Transportation Centers Program
  Department of Transportation
  Washington, DC  United States  20590
• Managing Organizations:

  Center for Efficient Mobility

  1111 Rellis Parkway
  Bryan, Texas  United States  77807
• Project Managers:

  Ocon, Monica

• Performing Organizations:

  North Dakota State University

  P.O. Box 6050
  Fargo, ND  United States  58108-60050
• Principal Investigators:

  Godavarthy, Ranjit

• Start Date: 20260220
• Expected Completion Date: 20270731
• Actual Completion Date: 0
• USDOT Program: University Transportation Centers
• Source Data: 03-16-NDSU

Subject/Index Terms

• TRT Terms: Crash data; Crash risk forecasting; Machine learning; Predictive models; Rural highways; Traffic safety; Truck crashes; Weather conditions
• Geographic Terms: North Dakota
• Subject Areas: Data and Information Technology; Highways; Safety and Human Factors;

Filing Info

• Accession Number: 01983767
• Record Type: Research project
• Source Agency: Center for Advancing Research in Transportation Emissions, Energy, and Health (CARTEEH)
• Contract Numbers: 69A3552348329
• Files: UTC, RIP
• Created Date: Mar 24 2026 2:09PM