AI Business is part of the Informa Tech Division of Informa PLC

This site is operated by a business or businesses owned by Informa PLC and all copyright resides with them. Informa PLC's registered office is 5 Howick Place, London SW1P 1WG. Registered in England and Wales. Number 3099067.

Supply Chain

German port first to adopt ML in shipping container management

by Rachel England
Article Image

The solution aims to reduce dwell time, which is a major challenge for port operators

German port operator Hamburger Hafen und Logistik (HHLA) says it’s the first port operator in the world to use machine learning (ML) to improve shipping container logistics and handling at its terminals.

Inform’s SyncroTESS module has been integrated into the IT systems at container terminals Altenwerder (CTA) and Burchardkai (CTB).

The software is being used to predict and therefore reduce the average dwell time of each container that arrives on site.

Excessive dwell time is an ongoing challenge for those in the logistics and supply chain industry, contributing to inefficient terminal operations, inflated storage fees and higher inventory holding costs. Inability to predict pickup times also means containers are often unnecessarily stacked and re-stacked, leading to increased costs and carbon emissions.

Predicting dwell time

Inform’s solution calculates the probable container dwell time using an algorithm based on historic data which continually optimizes itself using machine learning. The module has been trained with data from CTB’s container handling operations and is therefore tailor-made for the company. The system also predicts a container’s outbound mode of transport, which helps reduce unnecessary re-handling.

The tech emerged from a study by Inform undertaken in 2018, when the company set out to determine whether similar efficiencies were possible across a range of industries, including finance and aviation. In 2019, it published a paper suggesting that its ML module could result in a relative improvement in prediction accuracy of 26% for dwell time predictions, and 33% for outbound mode of transport predictions.

Port efficiency

It’s still too early to say whether such results will be replicated in the German ports, but those behind the initiative are confident of its success. Angela Titzrath, chairwoman of the executive board of HHLA, touched on the new technology during her opening address at this year’s World Artificial Intelligence Conference in Shanghai.

Advancing digitalization is changing the logistics industry and our port business with it,” she said. “Machine learning solutions provide us with many opportunities to increase productivity and capacity rates at the terminals.” She added that further cargo-based uses for machine learning were “on the horizon.”

EBooks

More EBooks

Latest video

More videos

Upcoming Webinars

More Webinars
AI Knowledge Hub

Research Reports

More Research Reports

Infographics

Smart Building AI

Infographics archive

Newsletter Sign Up


Sign Up