AI and machine learning for improved aquaculture with Cermaq’s iFarm

by Cermaq, Norway

The iFarm five-year project is the first of its kind and will allow for an individualised fish approach to salmon farming. Now, the first fish have been transferred in Cermaq’s iFarm.

By using artificial intelligence and machine learning, Cermaq will be able to identify each fish in a net pen, allowing for targeted health interventions if required and individualised health records for each individual fish. The iFarm five-year project is the first of its kind and will allow for an individualised fish approach to salmon farming. Now, the first fish have been transferred in Cermaq’s iFarm.
 

Last December, Cermaq Norway was awarded four development licenses for iFarm, and preparation work started in January. Since then, thanks to the efforts and support of many people across Cermaq, BioSort, the developer of the technology, and ScaleAQ, who has supported the delivery of the system, the various components of iFarm are taking shape and they have been able to successfully install the system.

First smolt ever in iFarm
In mid-September, the project rounded a big milestone when the first smolt was transferred in the iFarm pens.

“This is a very exciting and important phase in the project; now we will see how the fish behave in the actual iFarm environment, and whether our modelling and predicted outcomes for behaviour are accurate,” said Karl Fredrik Ottem, Cermaq's project manager for iFarm.

In iFarm, the fish are kept lower in the system using a net roof. When the fish rise to the surface to refill their airbladders, they are guided through a portal, or chamber, where a sensor can quickly scan, recognise and record data on that specific fish using recognition data based on each fish’s unique markings and structure.

“A prototype of the sensor itself will not be in place until November, allowing the fish to become used to their new environment over the coming eight weeks. Until then, we will spend time observing the fish's behaviour in the cage, how they move and how they eat, so that we can make any adjustments before we install the sensor. In addition, this time will allow us to develop and implement good operating practices as this is a new farm installation and we know we will need to adapt our practices,” added Mr Ottem.

Read more, HERE.

The Aquaculturists

---