AI-driven voyage optimisation project completed

Artificial intelligence developer, DeepSea Technologies, dry bulk shipowner G2 Ocean – a joint venture of Gearbulk and Grieg Maritime Group - and Norwegian research firm SINTEF, have announced completion of an artificial intelligence (AI)-optimised voyage efficiency project supported by EEA Grants.

Using automatic identification system (AIS) and noon report data, together with high-frequency data from other vessels, DeepSea has run trials to develop AI-based software to optimise voyages. The company claims that the new setup is available to every shipowner who has access to AIS data and noon reports.

The system works on the basis of ‘transfer learning’ where high-frequency data models from hundreds of ships already held in DeepSea’s databases are transferred to low-frequency data vessels of the same type and further adapted to available data. The result is improved operational efficiency through optimised navigation, reducing fuel consumption and corresponding emissions.

The software, called Pythia Augment, has been used in the bulk carrier market during the project. However, DeepSea claims that it can be applied to other vessel types too. DeepSea and G2 Ocean applied the software to five Grieg Star bulkers with the aim of reducing fuel consumption and achieving the highest possible timecharter equivalent rate for any given voyage.

DeepSea Technologies co-founder and CEO, Konstantinos Kyriakopoulos, said: “Shipowners need to be taking action now to deliver on the maritime industry’s long-term goal to decarbonise. A mature market for the low-carbon fuels that will drive large-scale decarbonisation of marine energy remains some way away. In the meantime, owners and operators should focus on reducing energy consumption through operational efficiencies. With the delivery of Pythia Augment using low-frequency data to optimise voyage planning, we are creating a new and innovative way for bulkers to effectively drive down carbon emissions in their operations.”