POLA’s New Data Module Forecasts Cargo Movement Up To Six Months Out

SAN PEDRO — Adding to its growing digital technology platform, the Port of Los Angeles has launched “Horizon,” a long-term cargo volume predictive feature of its Port Optimizer™ Control Tower data tool. The new module offers cargo owners, terminal operators, truckers and other supply chain stakeholders the capability to gauge movement of containers — imports, exports and empties — at the Port up to six months in advance.

Developed in partnership with Wabtec, the Horizon predictive technology uses an algorithm based on historical and trending volume data collected by the Port Optimizer, the cloud-based secure digital portal of maritime shipping data created by the Port in 2017 to facilitate more efficient cargo flow through its terminals. Continually taking into account changing conditions at the Port, the algorithm constantly updates cargo volumes, allowing the Horizon to improve forecasting over time and issue six-month-ahead volume updates every month.

 “Data is a critical resource in moving goods across the supply chain and into the hands of consumers,” said Nalin Jain, Wabtec’s President of Digital Electronics. “This is one more step in our journey to connect railroads, chassis providers, truckers, warehouse operators, and others across the supply chain with the insights they need to seamlessly move cargo in and out of ports.”

The Control Tower was launched in February 2021 to help Port stakeholders better predict and plan cargo flows. The Control Tower serves as a one-stop virtual dashboard with multiple data points, including real-time views of truck turn times and other truck capacity management information; the Signal, which gives a daily, three-week look at incoming cargo; and the Return Signal, which lets the trucking community know when and where to return empty containers to Port cargo terminals. The Control Tower also features recent and future trending volume data, as well as historical volumes and trends dating back to 2017, segmented by mode and specificity.