A recent METRANS funded research paper studied the feasibility of freight traffic modeling from precise and localized but sparse freight data and built machine learning models that can predict freight volumes on highway segments.

One of the biggest challenges in freight transportation planning is the lack of data on truck movements. Effective freight planning requires information on the origin, destination, and route of truck trips. GPS is traditionally considered the best available data source, however most GPS data is private and unavailable to government agencies.

METRANS focused on a restricted area in Los Angeles where freight volume is most relevant. Their team developed a research strategy that proceeds with limited data by (1) generating synthetic datasets on the area of interest that can be used to train and verify different freight volume estimation models, and (2) leveraging existing Caltrans CCTV video from public feeds to investigate whether cameras can be used to provide truck observations.

Their findings offer a privacy-preserving, cost-effective approach for estimating truck traffic using existing roadside infrastructure such as CCTV cameras and weigh-in-motion sensors. By enabling accurate freight movement analysis without relying on private GPS data, agencies can establish more informed transportation planning, infrastructure investment, and freight policy decisions.

Read the full report here