This WP will work towards the development of automatized and optimized process control with zero waste and environmental footprint. To deal with dynamic conditions, autonomous offshore systems must be able both to learn and self-adapt their learning process at runtime.

Objectives

1. Develop automated surveillance intelligence-based tools and digital twins as key enabling technologies to achieve offshore production with minimal GHG emission and ecological footprint.

   • How to enable offshore aquaculture farms that can autonomously self-adapt its production and operation processes towards zero emissions.
   • How can be create machine learning systems that can detect unforeseen conditions, e.g., during feeding and – by themselves – optimize their processes to reduce feeding waste, without any human intervention.

Expected outcome

• A method for automated machine learning process optimization.
• Concepts for autonomous control of offshore operations, leading towards zero waste and low environmental footprint.