When the technology that’s all around just works, the world works.

Q&A | March 11, 2022

How Port of Montreal is managing supply chain pressures

Port executive Daniel Olivier is using AI and other technologies to create efficiencies and increase resilience in turbulent times

The Port of Montreal sees $80 billion of goods pass through its docks each year. As director of business intelligence and innovation for the port, Daniel Olivier has a ringside view of the global supply chain crisis.

Olivier spoke with Workflow about the roles of metrics in predicting disruptions and of digital technologies in solving those problems. The following interview has been edited for length and clarity.

For us, a lot of the adversity wasn’t actually related to the pandemic. Our biggest issue was labor strikes. Elsewhere in Canada, there were climate issues. The Port of Vancouver had tremendous disruptions related to flooding all across British Columbia that shut out critical rail lines and access to the port.

So, whether it’s a pandemic, climate change events, or labor issues, I would say that over the last two years, we’ve shifted our mindset into resilience being the new normal. We used to measure supply chain performance in terms of transit time, reliability, vessel weight, et cetera.

I think the new metrics post-pandemic will be about better predicting supply chain behavior and implementing measures to get back to normal more rapidly.

You can’t predict the unpredictable, but you can be better prepared to respond.

You can’t predict the unpredictable, but you can be better prepared to respond. Let me give you an example.

When the pandemic hit, we had been working with several startup partners on predictive AI projects. We then quickly developed an algorithm that could basically scan the contents of an inbound vessel to identify the containers on board that had critical medical supplies in it, such as PPE. Once that container hit the ground, we could track and trace it and make sure it was fast-tracked out of the gate and into the market ASAP.

So we couldn’t predict the pandemic, of course, but we were equipped to react quickly because we had the digital maturity to implement a project at short notice.

We started this program, CargO2ai, as a non-revenue-generating project focused on medical supplies and other humanitarian needs, but there’s definitely a phase two to the project. We’re basically able to enter any commodity code into the application, so tomorrow it could be auto parts, microchips, or hazardous materials.

There could be a scenario where General Motors or Ford or John Deere comes to us and says, “I want to accelerate the delivery of vehicles or parts or microchips, and I’m willing to pay extra to get that box out of there very quickly.”

It’s an important role, using data and machine learning, for example, to streamline operations.

Over the last two years, we have been working on an artificial intelligence program to better predict and synchronize vessel and train arrivals. Imagine a ship leaving Rotterdam and a train leaving Winnipeg. In an ideal world, they’d arrive at the same time. Vessels are notoriously late, especially in the last two years, and I don’t mean two hours late, more like 10 days or two weeks.

Our algorithm will better predict vessel arrivals and simulate all sorts of scenarios. Then we can have rail cars delivered on time and labor dispatched properly. We’re just starting deployment, and it’s a kind of a dashboard that becomes a single source of truth.

The entire ecosystem of the port, the terminal operators, the rail carriers, everyone will be looking at the same metrics and recommendations to help them make decisions.

We launched a trucking portal in 2016 after surveying our truckers about the maximum time they thought was acceptable for their transaction, from the moment they enter the port, pick up or drop off a container, and then leave the port. They told us that 60 minutes was the threshold. With the trucker portal, we’re monitoring and measuring the whole process in real time and relaying that to the trucking community. A green bar means the trucker can get in and out in 60 minutes or less; a red bar is 75 minutes or over.

We also have machine learning predictions that tell truck drivers how long they’re going to wait if they come now, or how long if they come in, say, 12 hours. We don’t have a reservation system here in Montreal. Truckers are free to come anytime they wish, so that’s why this tool really makes a difference.

We’ve been able to flatten the curve so we don’t have peaks and valleys of traffic. We’re also very proud to now have a quarter of trucks come to us during non-peak hours, from 3 pm to 11 pm.

Decarbonization and net zero is probably going to become the biggest challenge our industry has faced in modern history. The International Maritime Organization’s goal is to reduce the industry’s carbon emissions by 50% by 2050, versus the baseline of 2008.

That’s a tremendous objective, and we’re going to need a lot of creative solutions, digital and otherwise, to help us with this agenda.

Want to Get Ahead and Stay There? Rethink IT Service Delivery.

Related articles

People. Innovation. Connections. They can make an enterprise great.
People. Innovation. Connections. They can make an enterprise great.

What does it take to make an enterprise great? These days, it’s empowering people, innovation, and connections

Upgrading the production line
Upgrading the production line

Optimized manufacturing pairs highly skilled workers with advanced technologies

The future of security is automated
The future of security is automated

There aren’t enough security analysts in the universe to manage a rising tide of threats. Automation can help.

How manufacturers can better digitize their supply chains
How manufacturers can better digitize their supply chains

Industry experts weigh in on solutions to an urgent global problem. Learn how supply chain digitization can help manufacturers meet logistics challenges.