Automating salmon feeding using machine vision and artificial intelligence (RD023)

Project Outcome:

The automatic feeding solution was implemented without adding any extra pen equipment to site. After initial trials with farmers, they grew in confidence to feed more pens at once and allow a more objective standardisation. It is clear from initial feedback that this product will provide vital feed cost standardisation and growth opportunities for the industry.

Observe are excited to use the developed solution as a foundation to rapidly grow their automatic capabilities to provide further benefit in precision farming.

Project Background:

Aquaculture feed management has a critical role to play in supporting the development of a sustainable aquaculture industry. Observe Technologies aims to convert aquaculture feeding processes from an art to a science by using Artificial Intelligence to identify measurable patterns in feeding activities and strategies to present to farmers. The system is built to be adaptable and empowering for farmers by seamlessly tapping into the existing sensors, feed systems and cameras on site. We collect this data through a multitude of AI algorithms to optimise the farm’s performance; from the cost efficient use of feed to maintaining fish welfare. 

Past innovations have focused on hardware and data collection; however the problem is not a lack of data, but the rigour and overwhelming pressure on farmers to consistently interpret that data and apply correlations with fish activity, feeding patterns, sensory data, food particles and other historical information in real time. The aim of this project is to use our propriety AI algorithms to provide actionable insights to sites. It will help will stimulate the development of new and transformative technological innovation and support the UK to become an international example of good practice in aquaculture.