Efficient and Data-Driven Pavement Management System using Artificial Intelligence

Pavement management systems (PMSs) are used by transportation agencies to determine cost-effective strategies for pavement preservation and maintenance at the network level. A large amount of data is collected as part of this process, including road location, climate, geometry, surface/structural characteristics, material properties, traffic level, and others. This information is processed using analytical-based methods to predict future pavement conditions and program treatments. However, this approach does not make complete use of the available information while focusing on a single aspect (e.g., roughness). Moreover, due to the increasing complexity and scale level of collected data, the current methods are unable to provide accurate pavement assessment and optimal intervention strategies. Recently, Artificial Intelligence (AI) has been used, as a powerful tool, to examine large datasets that are often very challenging to be analyzed by conventional methods and derive helpful correlations and models. These can be used to assist scientists and engineers in the decisional process. AI is underutilized in the current PMSs; therefore, this study aims to provide State DOTs in the Pacific Northwest with advanced AI-data-driven solutions to make informed decisions for pavement preservation and rehabilitation strategies. To achieve the main goal of this study, the following tasks are sought: (1) conduct a comprehensive review of the state of the practice on the use of AI in PMSs; (2) collect pavement management data currently available at State DOTs in the Pacific Northwest as well as at the Long-Term Pavement Performance (LTPP) database for pavement conditions at the national level; (3) evaluate the most promising AI approaches based on the findings of the literature search to process the collected data and to be next incorporated into the PMS; (4) develop an AI-based pavement management tool that incorporates engineering, economy, environment/climate, policy, and other information and provide data-driven solutions for optimal, cost-effective, and efficient pavement preservation and rehabilitation strategies; and (5) prepare guidelines on the proposed AI-based PMS to facilitate its implementation at the DOT level. The proposed research is expected to lead to the implementation of an innovative PMS that provides precise and effective selection of intervention strategies ultimately resulting in more sustainable and resilient road infrastructures.

Language

  • English

Project

  • Status: Active
  • Funding: $360000
  • Contract Numbers:

    69A3551747110

  • Sponsor Organizations:

    Pacific Northwest Transportation Consortium

    University of Washington
    More Hall Room 112
    Seattle, WA  United States  98195-2700

    Office of the Assistant Secretary for Research and Technology

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

    Alaska University Transportation Center

    University of Alaska, Fairbanks
    P.O. Box 755900
    Fairbanks, AK  United States  99775-5900
  • Project Managers:

    Connor, Billy

  • Performing Organizations:

    Alaska University Transportation Center

    University of Alaska, Fairbanks
    P.O. Box 755900
    Fairbanks, AK  United States  99775-5900

    National Institute for Advanced Transportation Technology

    University of Idaho, Moscow
    115 Engineering Physics Building
    Moscow, ID  United States  83844-0901
  • Principal Investigators:

    Connor, Billy

    Kassem, Emad

  • Start Date: 20210616
  • Expected Completion Date: 20220615
  • Actual Completion Date: 0
  • USDOT Program: University Transportation Centers Program

Subject/Index Terms

Filing Info

  • Accession Number: 01784894
  • Record Type: Research project
  • Source Agency: Pacific Northwest Transportation Consortium
  • Contract Numbers: 69A3551747110
  • Files: UTC, RIP
  • Created Date: Oct 15 2021 2:19PM