Big Data

Data science helps Norway’s fish farmers keep salmon populations healthy

Share this post:

Aquaculture is one of Norway’s most important industries. Our fish farms produce 65 percent of the world’s supply of Atlantic salmon and employ thousands of people in coastal communities.

At the Seafood Innovation Cluster, our mission is to help the industry grow and flourish while ensuring that fish stocks are managed responsibly, thereby protecting Norway’s sensitive marine ecosystems.

You might expect to find a tension between these economic and ecological goals, but the truth is that aquaculture’s long-term success depends on its sustainability. In many cases, what is good for the industry is good for wild salmon populations, too.

Meet the sea louse

Commercial fish farming in open net cages leads to increased numbers of susceptible hosts, and represents a potential risk of increased reproduction and spread of parasites. This poses a threat to the affected fish farms and to wild fish populations living in coastal areas.

Because salmon farms contain large numbers of potential host fish, they can be an ideal breeding ground for sea lice. If farmers don’t take the right actions to contain an outbreak, then the lice can spread to wild salmon populations, too. Looking at the economics alone, the direct cost of managing sea lice amounts to billions of dollars every year.

Introducing AquaCloud

To solve the sea lice problem, the Seafood Innovation Cluster’s  leadership decided to work with IBM and seven of the leading aquaculture companies in Norway to build a solution called AquaCloud.

Aquacloud is a cloud-based platform built on IBM Db2 Warehouse on Cloud, IBM Watson Studio and IBM Cognos Analytics on Cloud. It automatically captures sea lice counts and other relevant data from the aquaculture companies’ enterprise resource planning (ERP) systems and passes it into a predictive model that can accurately forecast sea lice outbreaks over a two-week horizon.

The predictions are recalculated daily and presented to the farm managers through an intuitive dashboard, helping them understand the risks and take preventative actions to address the problem before an outbreak occurs.

For example, if there is a high probability of an outbreak, the farm manager could introduce larger numbers of cleaner fish into its salmon enclosures to eat the parasites. Alternatively, they could use use mechanical cleaning techniques.

Parasites lost

The initial results from Aquacloud’s predictive model have been very encouraging, providing a 70 percent accurate prediction of sea lice swarms.

The next step is to move ahead with a series of field trials to verify that the model is an effective aid for real-world sea lice management. We’re eager to work with the farmers to improve the accuracy of the model even further and build their confidence in using the model to guide day-to-day decision making.

Besides the technical achievements, we’re delighted that working with IBM has helped to bring the industry together and create a united response to the sea lice problem. IBM expertise in information governance and security enables farmers to be confident that their sensitive commercial data won’t be leaked to competitors. That’s an essential guarantee to build trust between the biggest players in the aquaculture sector, and hopefully it’s an example that other industries can learn from, too.

Read the case study for more details.

More Big Data stories

New IBM Aspera updates help media and entertainment companies push boundaries

Across the world today, there’s no denying that the technologies underlying the media and entertainment industry are undergoing some massive transformations. The availability and volume of video content is expanding exponentially as the line between streaming and file-based content blurs and multicloud becomes the reality of modern IT infrastructures. For more than 15 years, IBM […]

Continue reading