Estimating Historical Hourly Traffic Volumes via Machine Learning and Vehicle Probe Data: A Maryland Case Study

TL;DR

This study presents a machine learning approach combining neural networks and profiling methods to improve the accuracy of historical hourly traffic volume estimates using vehicle probe data, aiding transportation planning.

Contribution

It introduces a novel neural network-based method that enhances traffic volume estimation accuracy over existing profiling techniques using probe vehicle data.

Findings

Proposed method improves accuracy by 24% over traditional volume profiles.

Estimates achieve about 21% mean absolute percent error with 30-47 probes/hr.

Vehicle probe data significantly enhances traffic volume estimation accuracy.

Abstract

This paper focuses on the problem of estimating historical traffic volumes between sparsely-located traffic sensors, which transportation agencies need to accurately compute statewide performance measures. To this end, the paper examines applications of vehicle probe data, automatic traffic recorder counts, and neural network models to estimate hourly volumes in the Maryland highway network, and proposes a novel approach that combines neural networks with an existing profiling method. On average, the proposed approach yields 24% more accurate estimates than volume profiles, which are currently used by transportation agencies across the US to compute statewide performance measures. The paper also quantifies the value of using vehicle probe data in estimating hourly traffic volumes, which provides important managerial insights to transportation agencies interested in acquiring this type of data. For example, results show that volumes can be estimated with a mean absolute percent error of about 21% at locations where average number of observed probes is between 30 and 47 vehicles/hr, which provides a useful guideline for assessing the value of probe vehicle data from different vendors.