What question did this study set out to answer?

This research aims to create predictive models to improve truck parking utilization forecasts.

February 2, 2026Open Access

Predictive Modeling for Enhanced Truck Parking Information Systems Using Machine Learning

Key Points

This research aims to create predictive models to improve truck parking utilization forecasts.
Developed hybrid machine learning and deep learning models
Tested a gradient boosting model for pretrip parking performance
Created a long short-term memory model for en-route parking predictions
Designed a 'Popular Times' visualization tool
The gradient boosting model achieved an average RMSE of 0.154 for pretrip predictions
The long short-term memory model provided an RMSE of 0.0429 for en-route predictions
The visualization tool enhances usability with color-coded charts

Abstract

The growing demand for truck freight in the United States has intensified the shortage of truck parking, posing safety and operational challenges. While real‐time Truck Parking Information and Management Systems (TPIMSs) offer current availability, predictive insights remain limited. This study develops hybrid machine learning and deep learning models to forecast truck parking utilization for both pretrip and en‐route decision‐making. A site‐specific gradient boosting model achieved the best pretrip performance (average root mean square error RMSE = 0.154), while a long short–term memory–based truck parking site utilization prediction (TPSUP) model provided accurate en‐route predictions (RMSE = 0.0429) with a one‐hour horizon. To enhance usability, a “Popular Times” panel was designed to visualize predictions through intuitive, color‐coded charts. These tools support safer and more efficient parking decisions, laying the groundwork for a more robust and predictive TPIMS.

Read Full Paperexternally

Demander à l'IA

Bookmark

View Full Paper