A traditional Japanese diet primarily features fish in large quantities. While it is good for Japan’s health, high demand has led to overfishing and hence decline in species. In order to support conservation efforts, researchers at Kindai University’s Aquaculture Research Institute have turned to fish farms with a new solution.

The artificial intelligence (AI) and Internet of Things (IoT) solution frees up highly skilled workers in the fish farming sector from a highly time-consuming task.

To ensure supplies, researchers hatch red sea bream and raise them to a juvenile stage, known as fingerlings. Every year, it sells around 12 million fingerlings to fish farms that grow them to adult size for the market.

It is worth mentioning here that the university approached its long-term partner company, Toyota Tsusho, which in turn brought in Microsoft Japan to help with ways of automating a number of processes.

Microsoft Azure Machine Learning Studio created the new automated transfer system using image analysis technology. It helps with the recognition of the changing ratio of fish shapes and vacant areas within a pump’s pipes. From this, the system machine-learned how expert human operators adjust flows optimally.