The full potential of AI for ports is yet to come

An era when artificial intelligence will help ports manage berth allocation and congestion management may not be far off – but to make the most of algorithms in environments as safety-critical as ports and shipping operations, we need to make sure they’re compatible Train carefully, writes Grant Ingram, CEO of Innovez One for the UK and EMEA.

The launch of ChatGPT has given millions of people around the world the opportunity to experience dialogue with AI first-hand. Reactions ranged from awe at the chatbot’s remarkable potential, to concern over its potential impact, to ridicule at some of its glaring flaws.

Beyond the hype on social media, the advent of conversational algorithms has also fueled interest in AI in corporate boardrooms, and many in our industry are wondering how best to approach technology that will change the way how we work, act and create, should change.

Artificial Intelligence is already proven to be making breakthroughs in areas as diverse as finance and drug discovery – but what exactly can it do for the maritime sector? When it comes to ports and shipping companies, there is no room for error. Unlike conversational algorithms, we cannot experiment with port efficiency and security at will. Nevertheless, this new era offers an opportunity that should be seized.

New challenges require new solutions, and AI can be an invaluable asset at a time when ports are reinventing themselves to support decarbonization across supply chains at a time of increasingly frequent supply chain disruptions. We know that AI can transform port operations to increase efficiency and sustainability, as it is already doing so in several ports, including key hubs like Tanjung Priok and Tanjung Pelepas.

The right question is therefore not whether or not we should use AI in shipping, but how we can make the right decisions to ensure that AI-enabled solutions are adapted to our sector, safe and reliable. Much of the answer lies in the way algorithms are developed and trained.

reality checks

One area in which AI is already playing a role today is the automation and optimization of port, tugboat and pilotage operations. Using machine learning, a subset of AI, algorithms can “learn” from a port’s data to predict the duration of each upcoming job depending on the type of ship and the different jobs required. Using these predictions, they can allocate resources such as tugboats and pilot boats in the most efficient manner, solving complex puzzles well beyond what humans and spreadsheets can accomplish.

This may seem like a small step in the grand decarbonization program, but it’s important to ensure that all moving parts fit together seamlessly to welcome ships precisely when they arrive at ports, which has a noticeable impact on incoming ships’ idle times affects. Congestion and the port’s total emissions. For example, at Tanjung Priok, our AI-powered MarineM system has reduced the total distance traveled during towing and piloting operations by 20% and reduced the average waiting time for incoming vessels from 2.4 hours to 30.6 minutes.

Proper training is essential to achieve these reliable results. In port operations, we can be objective and teach the algorithm what a good answer is with a carefully curated dataset and clear parameters. In practice, an important part of the training is a “reality check” where the algorithm checks its predictions and schedules against real-world durations – helping it to refine its responses and adapt them to the port’s specific operations and constraints.

A smart future

Going forward, we must continue to focus on solid and reliable outcomes as AI expands to more areas of port operations. For example, machine learning can optimize berth management, which will become even more important in the future as ships are powered by different fuel types and clean technologies, and their port service requirements become more specific.

In addition, we can envision a future where AI-powered algorithms are trained to assess the level of port congestion using, for example, aerial imagery and predict what could help ports identify critical situations and take early action to relieve congestion seize. The potential of artificial intelligence to support smarter and greener supply chains is undeniable, but not all AI is created equal. Therefore, greater use of AI in seafaring should go hand in hand with a better understanding of the technology being developed, to ensure we train and use it wisely.

Related Articles

Back to top button

Subscribe To Our Newsletter

Don't miss new updates on your email