Insights

We surveyed maritime operators across the industry and uncovered the fact that optimisation is widely adopted at the planning level, but only 21% believe it is well understood. This insight shares the survey’s key findings, including which factors operators identify as the biggest constraint on optimisation performance, and why automation is gaining ground despite limited familiarity with it.

Why optimised voyages don't always deliver: the Maritime Execution Gap

From bunker savings to regulatory compliance and chartering competitiveness, vessel performance now sits at the centre of commercial strategy. But traditional performance monitoring methods offer only snapshots of reality. Machine Learning enables a continuous, data-driven view of vessel efficiency, unlocking smarter decisions across the entire lifecycle.

A Q&A with DeepSea’s Director of AI Research, Antonis Nikitakis Q: What is your most exciting piece of AI research at the moment ? Explainability is critical for building trust in AI systems. Therefore, our most exciting AI research currently involves researching methods that improve models’ explainability – to enable ever-greater trust to be built amongst stakeholders. AI can be seen as a “black box” whose input and operations may not be transparent and understandable to ou

Marilena Apostolidou, Eurobulk’s Environmental & Performance Compliance Manager, shares her views on sustainability and decarbonisation in shipping. Q: What does it mean to be a Performance & Environmental Compliance Manager? Environmental compliance means adopting and implementing environmental requirements – national and international environmental rules, laws, and regulations. Environmental concerns have raised compliance standards across the globe. Especially in the Shi

A Q&A with Konstantinos Kyriakopoulos, CEO and Co-founder of DeepSea Technologies There’s been a lot of news recently about “sentient” artificial intelligence. Will DeepSea’s AI be sentient any time soon? Sentience is the ability to experience emotions and sensations. Machine learning algorithms are trained on data – pairs of inputs and outputs – and they learn how to reconstruct the outputs from inputs by themselves. A lot of AI nowadays is trained on inputs and outputs tha

Have you heard of distributional shift? Are you involved in shipping? If the answers are (no) and (yes), you need to read this! Unless you happen to be one of the small (but increasing) number of data scientists in the shipping domain, chances are you haven’t heard of this phenomenon. But, in fact, it’s one of the greatest obstacles to using data really effectively – not only in maritime, but across every industry. As our co-founder Konstantinos says, Robustness to distribut

Traditional weather routing solutions do exactly what their name implies: they create a route for a ship with the weather in mind. But they do not take into consideration a critical element – the vessel itself. Imagine starting your day knowing with 99% accuracy what it will entail. The exact time that you should leave your house, the best route to take to work (adjusted to changing traffic and weather conditions in real-time), and the driving speed to optimise your car’s fue

The maritime industry’s adoption of data-driven methodologies to enhance fleet performance is still a very recent phenomenon. In addition, the International Maritime Organization (IMO) has gradually introduced long-term strategies in an attempt to reduce the environmental footprint of maritime operations – thereby intensifying commercial competition. Hence, the maritime industry has now to create and instill a culture of energy efficiency amongst all its participants, if they

Improving operational efficiency and reducing CO2 emissions represent major challenges for the shipping industry. This requires that organisations diligently monitor vessel performance and emissions and report this data in various ways and formats, depending on each company’s policies and priorities. However, the manual collection of critical data by shipboard staff utilising noon reports, sensors located on the ship and AIS as data sources among others, as well as the analys