Three prominent maritime companies in Southeast Asia have collaborated to leverage artificial intelligence (AI) for verifying reductions in fuel consumption and greenhouse gas (GHG) emissions in shipping. The partnership includes ClassNK, an international classification society from Japan, Evergreen Marine Corporation, a Taiwanese container shipping firm, and Samsung Heavy Industries, a South Korean shipbuilder. They are joined by Weathernews Inc., a leading private weather information provider based in Japan.
The group has signed a memorandum of understanding to create a framework aimed at assessing how AI-driven autonomous navigation systems can contribute to lowering GHG emissions from vessels. This initiative aligns with the maritime sector’s broader decarbonization goals, as member states of the International Maritime Organization (IMO) have collectively set a target for net-zero emissions by 2050, alongside a commitment to increase the use of zero or near-zero GHG emission fuels to at least 10% of shipping energy consumption by 2030.
ClassNK has expressed its ongoing commitment to support innovative projects that facilitate the decarbonization of the maritime industry, focusing on the practical application of advanced technologies and the establishment of updated safety standards for alternative fuels. The project will utilize Evergreen’s commercial vessel, incorporating Samsung Heavy Industries’ Samsung Autonomous Ship (SAS) technology, while Weathernews will provide crucial meteorological and oceanographic data.
In practical terms, Evergreen will supply the demonstration vessel, operational data, and crew support. Samsung Heavy Industries will manage the speed optimization algorithm and oversee real-time vessel control, while Weathernews will develop voyage routes and provide detailed weather forecasts. ClassNK will perform a technical review and independent evaluation of the project’s outcomes, ultimately aiming to validate the effectiveness of AI-based voyage optimization technology through real operational data analysis.
