Freight Volume Modeling on Major Highway Links

One of the most challenging problems in urban transportation planning is the lack of fine grain data on freight movements. Cities and regions do not know how many trucks operate in the region and have only limited information on freight flows. A particularly important information problem is the absence of a consistent and current source for freight volume and origin-destination data. Without such information, it is difficult to manage or plan for freight in metropolitan areas. This research seeks to develop a method for generating freight (truck) volume and origin-destination estimations at the traffic analysis zone level from streamed data so that estimations can be constantly updated. We propose research to model freight volume information on major highways from existing freight data sources. Specifically, we intend to study the feasibility of freight traffic modeling from precise and localized but sparse freight data and build machine learning (ML) models that can predict freight volume on highway segments, and ultimately the origin-destination matrix associated with the predicted flows. The proposed initial effort will validate the feasibility of freight volume estimation on links from accurate but sparse data sources (e.g., WIMS, CCTV), as well as less accurate but more plentiful data sources (e.g. NPMRDS), on a restricted control area in the Los Angeles metropolitan area where freight volume is most relevant. We will consider an area covering approximately 12 square miles around the Ports of Los Angeles and Long Beach to develop ML models that allows for estimating the freight volume on the highways using available data sources, then use the same data sources to: Validate the feasibility of freight volume modeling. This will be achieved by excluding specific data sources from the sources used to model and comparing those data sources counts with the model estimates. In addition, we can validate the model predictions against existing aggregate truck volume data available as part of vehicle census data. Finally, we will study model performance in relation to the number and location of data sources to provide guidance on minimum viable configuration. Validate the feasibility of automating freight modeling. For this we will study the feasibility of automating truck data extraction and formatting, e.g., using Caltrans CCTV cameras, and scaling, and updating the models. The outcomes of this effort can provide a valuable tool for transportation planning: a low cost, always current best estimate of freight flows on the highway and arterial systems. The model can be leveraged for various purposes, e.g., the ones outlined in the PSR call to examine impacts of e-commerce or changes in spatial patterns of economic activity. If successful, we will examine how the model can be implemented and scaled on a larger area and how it can be improved with the addition of other available sources. Eventually this freight volume flow can be made available in the USC METRANS/IMSC Archived Data Management System (ADMS) for the larger Los Angeles area and/or in PeMS for California.


    • English


    • Status: Completed
    • Funding: $99,980.00
    • Sponsor Organizations:

      Department of Transportation

      1200 New Jersey Avenue, SE
      Washington, DC  United States  20590
    • Managing Organizations:

      METRANS Transportation Center

      University of Southern California
      Los Angeles, CA  United States  90089-0626
    • Project Managers:

      Brinkerhoff, Cort

    • Performing Organizations:

      University of Southern California, Los Angeles

      University Park Campus
      Los Angeles, CA  United States  90089
    • Principal Investigators:

      Shahabi, Cyrus

    • Start Date: 20200816
    • Expected Completion Date: 20210815
    • Actual Completion Date: 0
    • USDOT Program: University Transportation Centers
    • Source Data:

    Subject/Index Terms

    Filing Info

    • Accession Number: 01745027
    • Record Type: Research project
    • Source Agency: METRANS Transportation Center
    • Files: RIP
    • Created Date: Jul 13 2020 8:02PM