AI-enhanced energy efficiency measures for optimal ship operations to reduce GHG emissions

Purpose and goal:

Ship operation-related energy efficiency measures (EEMs) can help reach the IMO 2030 emission goals. However, today, their benefits have not been fully realized. Through the digital transformation in shipping, vast amounts of vessel data are being collected, enabling activation of AI-powered solutions to further improve vessel performance.

Our purpose is to support the shipping industry to achieve greener ship operations. Our goal is to develop an operational support solution strengthened by AI on taking EEMs into account for enhanced energy efficiency. Expected results and effects:

This project aims at about 20% emissions reduction by implementing AI-enhanced EEMs. Its results will be verified through extensive pilot testing in real shipping environments. This testing will involve project partners, shipping companies, and DNV that will check the effectiveness of the AI-EEMs and our verification process.

The final product will be offered to shipping companies worldwide, benefiting them both economically and environmentally. This project will contribute to reducing shipping carbon intensity as aimed in the IMO 2030 and 2050 emission targets. Approach and implementation:

This project will have four steps: (1) design wave correlation models via machine learning models, (2) develop hybrid quasi-static ship energy models to estimate a ship´s emissions at stationary sea conditions (3) develop dynamic models based on AI technology to predict dynamic energy performance which will be implemented on board the EEM, to facilitate optimal planning and decision-making; (4) test AI-powered EEMS on board to verify emission reduction levels and commercialization.