The experimental field "DigiSchwein - Cross Innovation and Digitisation in Animal-Friendly Pig Farming with Consideration of Resource Protection", which was launched at the beginning of 2020 and is funded by the Federal Ministry of Food and Agriculture (BMEL), contributes to the further development of animal-friendly, resource-conserving pig farming. In close cooperation with partners from science and industry, solutions are being developed in the project on the basis of IoT (Internet of Things), Big Data and Machine Learning, which should improve animal welfare, animal health and the efficiency of operating resources and lead to a reduction in the input of nutrients into the environment.
Pig farmers are obliged to inspect their livestock at least twice a day. During their inspections, they must rely on their experience and their subjective impression of their animals. An increased noise level in the barn or wounds on the ears and tails are alarm signs that experienced farmers register in order to subsequently take targeted action. In contrast, early detection of fever, refusal to take in water or developing deviant behaviour of the animals are more difficult or impossible to register.
In order to support farmers in their daily work, an early warning and decision support system is being developed in "DigiSchwein": The focus of this work is on solving current practical problems in the keeping of pigs. These use cases include the keeping of undocked pigs and the associated prevention of tail biting, early disease detection in order to be able to isolate affected animals as early as possible, birth management in order to prevent the crushing of newborn piglets and to minimise the fixation times of the mother sow, as well as the monitoring of nutrient flows in the pig house.
Based on cameras, thermal imaging cameras, climate sensors that measure the ammonia concentration in the air, NIRS sensors to measure the nutrient composition of manure and other sensor technology, the conditions in the barn and the condition of the animals are continuously monitored.
Not only the selection of the appropriate sensor technology that captures the relevant aspects for the use cases is a challenge, but also the sheer mass of data generated primarily by over 50 cameras. The storage and processing of the data is handled by a data management and data analysis platform developed with open source Big Data components. With the help of a data stream management system, sensor data is plausibilised and merged. In addition, events are generated, such as the exceeding of a specified temperature in the barn. On the other hand, Deep Learning is used to develop models that allow the detection of events in videos, such as tail biting. The generated events then form the basis for the creation of specific data products that are integrated into the early warning system in order to derive recommendations for action.
Through continuous exchange with farmers, "DigiSchwein" then supports the transfer of the knowledge and results gained into broad agricultural practice.