An Iterative Algorithm to Impute Truck Information over Nationwide Traffic Networks

TL;DR

This paper introduces an iterative algorithm that combines multiple traffic datasets to accurately impute hourly truck volumes and vehicle class distributions across the US traffic network, aiding traffic management and policy.

Contribution

The study presents a novel method integrating diverse traffic datasets to improve temporal and spatial truck activity estimation over nationwide networks.

Findings

Effective imputation of truck volumes and classes across scales

Improved accuracy over existing methods

Potential applications in emission and resilience modeling

Abstract

Understanding the dynamics of truck volumes and activities across the skeleton traffic network is pivotal for effective traffic planning, traffic management, sustainability analysis, and policy making. Yet, relying solely on average annual daily traffic volume for trucks cannot capture the temporal changes over time. Recently, the Traffic Monitoring Analysis System dataset has emerged as a valuable resource to model the system by providing information on an hourly basis for thousands of detectors across the United States. Combining the average annual daily traffic volume from the Highway Performance Monitoring System and the Traffic Monitoring Analysis System dataset, this study proposes an elegant method of imputing information across the traffic network to generate both truck volumes and vehicle class distributions. A series of experiments evaluated the model's performance on various spatial and temporal scales. The method can be helpful as inputs for emission modeling, network resilience analysis, etc.