Due to the high level of turbidity in the shrimp farm pond systems that exist worldwide, the detection of animal welfare using artificial intelligence such as automated image recognition is in principle impossible, as stressed or already diseased shrimp cannot be distinguished from healthy animals visually. Unlike in pond production, the water in Oceanloop GmbH’s land-based facilities is clear. This advantage in terms of animal welfare detection and sustainability has already been successfully demonstrated in the previous project; Computer vision allowed the length and number of animals to be determined with an accuracy of over 90% and visual stress indicators (also with 90% accuracy) could be recorded - for the first time in real farming conditions. In the project recently funded for a period of two years (until June 2026), existing AI is to be further developed to market maturity. The aim is to use automated image recognition software to record and validate animal welfare and mortality throughout the entire production chain, from juvenile animals to market-ready shrimp. The project is related to a number of agricultural policy objectives such as competitive agriculture or healthy nutrition and safe food. Such policies will ultimately effect Germany’s consumer behaviour. Shrimps in German supermarkets currently come almost exclusively from shrimp farms in non-EU countries. Proof of the welfare in clear water production systems will provide consumers with guidance when buying and at the same time highlight the advantages of local land-based shrimp farming. At the WAS 2025 we precent latest data generated up until the conference date.
The project partners are the company Oceanloop GmbH Kiel and the Alfred Wegener Institute for Polar and Marine Research Bremerhaven. The project was funded by the German Innovation Partnership for Agriculture (DIP) funding, Federal Ministry of Food and Agriculture (BMEL) on the basis of a decision by the German Bundestag. The project was sponsored by the Federal Office for Agriculture and Food (BLE) as part of the programme to promote innovation. Funding code 281DT10B23.