AI and Digital Twinning for Decarbonisation

AI and Digital Twinning to achieve carbon reduction on-board RRS Sir David Attenborough (SDA)

Project Summary:

The RRS SDA provides an opportunity to revolutionise ship management using AI. The project will develop and integrate AI algorithms that exploit the diverse range of sensor measurements and remote sensing available on-board. The resulting AI systems will provide automated decision support to SDA masters in delivering optimal fuel economy and minimising carbon emissions.

BAS has committed to achieve Net Zero carbon emissions by 2040, aligning with NERC and UKRI sustainability commitments. Part of the BAS implementation plan comprises the reduction of shipping emissions through the development of AI-based operations for the RRS Sir David Attenborough. Automating ship and sea-state interpretation and forecasting, and using these to inform automated passage-planning, will help us reduce fuel use and carbon emissions.

A large ship and a digital projection of it
A Digital Twin of the RRS Sir Davide Attenborough (SDA)

A team of scientists has been appointed as part of the BAS AI lab to develop an adaptive passage-planning capability to advise ship Masters. This will comprise a fundamental component of a Digital Twin of the SDA, utilising the numerous data streams available on the SDA as well as weather and ice forecasts and models of some of the most important oceanographic processes underway in the Antarctic. The route-planning capability of the SDA will form part of a Digital Twin of the combined operation of the ship and its Master, and will both contribute to, and benefit from, the wider digital twinning of the Antarctic.

The project will provide initial demonstrators of the key components:

  • In phase 1 (ending March 2023): an automated decision-making tool to optimise passage planning and overall carbon efficiency.
  • In phase 2: A machine-learning system to analyse the performance of the vessel, under a range of environmental conditions, and to learn how to optimise its performance locally when encountering these conditions on a voyage.

The route planner will use live forecasts of meteorological and oceanographic conditions to inform automated passage-planning constrained by the presence and dynamics of sea ice and ice bergs, predicted weather conditions and fuel, power and crew comfort requirements.  The route-planning tool will provide ship masters with proposed routes and live updates that can advise them in their expert decision-making. Route planning objectives will include optimising carbon footprint over the journey and reducing passage time to maximise ship time available for science.

Map
A collection of routes (white lines) planned for the SDA, shown against summer sea ice.

Planned routes will be displayed via digital dashboards that enable proposed courses and parameter settings to be visualised in tandem with existing information services on the Bridge. Routes will be evaluated by the Master and other navigation officers.

This project will enable the first steps in the development of a Digital Twin of the SDA. In the first phase of the project, we will focus mainly on external data sources for modelling the environment and informing decision-making.  In phase 2 and beyond, we will use underway data (such as speeds and fuel requirements in different sea states, performance in ice, etc) to refine our models of how the vessel responds in different conditions. Initial demonstrators of the route-planning capability will be delivered which will form the foundations of further work to complete the Digital Twin of the vessel.

The initial budget of the project is £365,000 funded by NERC and it will run until the end of March 2023. Full development and integration of a Digital Twin tool on the RRS SDA is subject to further funding.