A Prescriptive Framework for Determining Optimal Days for Short-Term Traffic Counts

2025-12-05

AI Summary

This study addresses the subjectivity and inefficiency in selecting short-term traffic counting days for Annual Average Daily Traffic (AADT) estimation on roads lacking continuous monitoring, which leads to substantial estimation bias. We propose the first machine learning–based iterative framework for selecting statistically representative counting days. Our method simulates 24-hour short-term counts using continuous traffic flow data and constructs daily traffic representations via leave-one-out feature engineering; it then iteratively optimizes the selection of the most representative days. Experiments demonstrate that the top five selected days consistently outperform all baselines, with the optimal day (Day 186) achieving an RMSE of 7,871.15 and an R² of 0.9756. This work pioneers the systematic integration of machine learning into short-term counting-day selection, simultaneously improving estimation accuracy and reducing operational costs—establishing a novel paradigm for standardizing traffic surveys.

Technology Category

• Planning, Routing, and Scheduling: Model-Based Reasoning
• Machine Learning: Learning Preferences or Rankings
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Security and Privacy: Large-scale security measurements

Abstract

The Federal Highway Administration (FHWA) mandates that state Departments of Transportation (DOTs) collect reliable Annual Average Daily Traffic (AADT) data. However, many U.S. DOTs struggle to obtain accurate AADT, especially for unmonitored roads. While continuous count (CC) stations offer accurate traffic volume data, their implementation is expensive and difficult to deploy widely, compelling agencies to rely on short-duration traffic counts. This study proposes a machine learning framework, the first to our knowledge, to identify optimal representative days for conducting short count (SC) data collection to improve AADT prediction accuracy. Using 2022 and 2023 traffic volume data from the state of Texas, we compare two scenarios: an 'optimal day' approach that iteratively selects the most informative days for AADT estimation and a 'no optimal day' baseline reflecting current practice by most DOTs. To align with Texas DOT's traffic monitoring program, continuous count data were utilized to simulate the 24 hour short counts. The actual field short counts were used to enhance feature engineering through using a leave-one-out (LOO) technique to generate unbiased representative daily traffic features across similar road segments. Our proposed methodology outperforms the baseline across the top five days, with the best day (Day 186) achieving lower errors (RMSE: 7,871.15, MAE: 3,645.09, MAPE: 11.95%) and higher R^2 (0.9756) than the baseline (RMSE: 11,185.00, MAE: 5,118.57, MAPE: 14.42%, R^2: 0.9499). This research offers DOTs an alternative to conventional short-duration count practices, improving AADT estimation, supporting Highway Performance Monitoring System compliance, and reducing the operational costs of statewide traffic data collection.

Problem

• Develops a machine learning framework to select optimal days for short-term traffic counts.
• Aims to improve Annual Average Daily Traffic (AADT) prediction accuracy for unmonitored roads.
• Reduces operational costs and supports compliance with traffic monitoring requirements.

Innovation

• Machine learning framework identifies optimal short count days
• Leave-one-out technique generates unbiased daily traffic features
• Methodology outperforms baseline with lower errors and higher R-squared