Analyzing NPMRDS Using Advanced Machine Learning to Enhance Road Safety, Public Health and System Performance

Details

• Creators:
  Faezipour, Miad ; Park, Sangho ; Wu, Shuju
• Corporate Creators:
  Central Connecticut State University ; Purdue University
• Corporate Contributors:
  Connecticut Department of Transportation ; United States. Department of Transportation. Federal Highway Administration
• Subject/TRT Terms:
  • Machine learning
  • Traffic speed
  • Datasets
  • Highway safety
  • Public health
  • Performance
  • Implementation
  • Data collection
  • National Performance Management Research Data Set (NPMRDS}
• Publication/ Report Number:
  CT-2337-F-25-4
• Resource Type:
  Tech Report
• Geographical Coverage:
  United States
• Edition:
  Final Report: 2004-2025
• Corporate Publisher:
  Connecticut. Department of Transportation
• Abstract:
  This project aims to leverage NPMRDS data and machine learning techniques to analyze the relationships between speed variations, crash occurrences, weather conditions, and road geometry. The goal is to identify patterns that can measure the performance of road segments and inform targeted safety interventions and infrastructure improvements. The project progressed in an organized sequence We began with systematic data collection and the selection of study segments, followed by rigorous data processing and feature engineering to support both speed prediction and roadway reliability assessment. Multiple modeling approaches are developed, validated, and refined to ensure robustness, while exploratory analyses are conducted to assess crash-related and health-related impacts, extending the scope of insights beyond prediction alone. The findings are carefully examined, leading to actionable recommendations for practice and policy. Implementation activities further demonstrate the practical applicability of the developed methods.
• Format:
  PDF
• Funding:
  SPR-2337
• Download URL:
  https://rosap.ntl.bts.gov/view/dot/88826/dot_88826_DS1.pdf
• File Type:
  [PDF - 768.89 KB]
• Collection(s):
  Artificial Intelligence Deployment Center of Excellence (AI COE) ; US Transportation Collection
• Main Document Checksum:
  urn:sha-512:6f5a8840f0d6a9bb09ff9d6a14ebfd7a2f9c986f665909ae79e4027a33a47909e1b533aef4a36f4dd2ae8c5834aec9576597bf6ea11823a267a1270900e9fe1f