Skip to content

Sign up to the Port Tech Daily News for free to keep up to date with the latest industry news

CTAC 2021: Experts bearish on data democratisation unlocking Machine Learning

Vast Container Terminal in the Port of Long Beach at Sunset
Share on twitter
Twitter
Share on facebook
Facebook
Share on linkedin
LinkedIn
Share on email
Email

Data democratisation is a key hurdle to overcome if terminals are to unlock the potential of Artificial Intelligence (AI) and Machine Learning (ML).

AI and ML can provide significant returns for terminals seeking efficiencies in operations: ranging from enhanced container stacking ability to predictive analysis for vessel scheduling.

Yet sharing data across enterprises like terminal and warehouse operators and shipping stakeholders, which has traditionally been hampered by business interests, is a mentality that has to creep into the industry, said Ramana Kampala, Co-founder and CEO of Avlino.

During Container Terminal Automation Conference 2021’s session AI/Machine Learning: From Concept to Real Results, Kampala said port communities need to take an ecosystem-centric approach to fully harness ML.

“One challenge has to be overcome: data democratisation,” Kampala argued.

“Unless enterprises are willing to share their data, ensuring that across the value chain efficiencies can be realised, that mentality has to creep in. Otherwise, business units hold onto information [to monetise].

“You need to take an ecosystem-centric approach to fully take advantage of things like AI. It’s a win-win for everyone in the supply chain.”

Beyond the terminal

Alex Van Winckel, Senior Consultant at INFORM was similarly passionate about looking beyond just the terminal complex.

“From a port perspective, the terminal within the construction of the port is an important role. But we have learnt to look beyond the fence of the port,” explained Van Winckel.

“[This means] improving Port Community Systems (PCSs). As a company, we are touching on how we can improve PCSs, and the interests of ports by means of ML.”

Frederik Stork, Senior Director of Optimisation and Analytics Services at Navis, offered a key example where sharing information through ML could provide an impact.

Stork said a warehouse distribution centre close to a terminal could log a standard order for a container from a terminal.

“That distribution centre could share more data on inventory – asking if it drops below a certain level, the system could request a new container,” Stork explained.

“Then they share a more data, allowing the terminal to leverage the degrees of freedom to bring that container within a window of time.”

Stork suggested that warehouses adjacent to an intermodal site, for example, “could see these points coming up more and more”.

However, Anders Dommestrup, CEO at the Manila International Container Terminal, says that data sharing is not the issue.

“At this point with the technology, it’s a bit of a leap to think [we can integrate] data,” he said.

“Sharing isn’t the problem. It’s done through the PCSs. But the decision-making processes have different companies with different drivers. Various stakeholders in the supply chain have competing interests.

“It takes time, it needs to be proven, and [the industry believes] you are trying to take money out of other people’s pocket when it comes to collaborating fully when sharing data.

“The vision and the scalability and capability within the tech is there, but I just don’t think we as humans are there yet.”

Want to stay up to date with the latest industry news? Sign up to the Port Tech Daily News and receive stories like this directly to your inbox for free.

Latest Journal

Cookie Policy. This website uses cookies to ensure you get the best experience on our website.