Research

The project will focus on developing automated algorithms to recognize damaging behaviors in pigs. Pigs will be continuously video recorded for 10 weeks post-weaning to label behaviors like ear and tail biting. This data will help train computer vision algorithms using skeleton-based behavior recognition, which is advantageous due to its focus on body language and efficiency in detecting specific actions. The study will use advanced algorithms for object detection and behavior recognition, starting with YOLOv10 for identifying pigs based on ear tags. The detected pigs will then be analyzed using ViTPose, a model known for high accuracy in pose estimation, to map their skeletons with 22 key points. The applied method is effective at learning spatiotemporal features and is robust against pose estimation errors. To facilitate the transfer of these algorithms to the Austrian pig industry, photorealistic models of pigs and their environments will be generated using synthetic data techniques, ensuring a robust training dataset. An advanced model will be implemented for tracking individual pigs within a group, using both visual detection and RFID tags for continuous identity updates. Modeling and estimation of genetic parameters for new behavioral traits, calculation of genetic and phenotypic correlations among them and with important production traits will be also done. This comprehensive approach aims to enhance behavior monitoring and improve welfare in pig farming.

The development of innovative husbandry systems for pig farms in Austria is gaining importance against the backdrop of growing interest in animal welfare among consumers and, in particular, farmers. In this context, raising pigs under conditions that are as close to nature as possible (e.g., as part of crop rotation in the field) is a top priority. However, challenges often arise during the development and implementation of animal-welfare-promoting husbandry systems, such as ensuring compliance with legal requirements, including groundwater protection. The “Ackerschweine” project aims to create the conditions for implementing an innovative form of pig husbandry on arable land. This rearing system involves keeping pigs on unpaved farmland, with part of the area available to the animals covered by temporary tents. The nutrients excreted by the animals are to be bound by large amounts of bedding and subsequently applied in a controlled manner as farm manure on the farm’s arable land. The project is to be carried out in two phases. At the outset (Phase 1), the goal is, in particular, to develop the groundwater protection requirements for this rearing method to ensure that there is no increased nitrate leaching into the groundwater. Through (i) preliminary trials on paved surfaces (WP 2.2), (ii) Studies of the sorption capacity of various bedding materials (WP 2.4) and (iii) modeling of excreta production, substance quantities, and their dynamics under different environmental conditions and stocking densities (WP 2.3) will provide the basic prerequisites for ensuring the minimization of nutrient input into the soil. In the second project phase, the optimized systems will be implemented on pilot farms (WP 2.5), and sustainable groundwater protection will be validated through accompanying monitoring of nitrogen dynamics (WP 2.6). Through the established pilot systems on farmland, interested pig farmers will be informed about the prerequisites and management requirements for the “farmland pigs” system. Furthermore, thanks to scientific monitoring, material flows will be documented in the context of a “sustainable circular economy that safeguards groundwater quality.” The project will result in a comprehensive guide for establishing the “field-raised pigs” farming system as an alternative, animal-welfare-promoting system while simultaneously ensuring compliance with groundwater regulations in Austria.

To address climate change, resource limitations and society's demands for more sustainable forms of production, ENSURE aims to develop strategies, pathways, transformation pathways, recommendations for action, breeding strategies and tools that contribute to future-proof, sustainable cattle farming. Scenarios and strategies will be modeled and developed to proactively shape cattle management through improved resource utilization, feeding optimization, improved animal health, reduced environmental impact, and improved resilience at the system, farm, and animal levels. This is expected to contribute to improved farm profitability and future-proofing, food security, environmental impact and consumer acceptance. The project is divided into two Areas, Area 1 Scenarios and strategies and Area 2, Optimisation Solutions. Within Area 1 the 3 projects "Future-proofing dairy and beef production networks in Austria", "AlPTouR - Alpine Pastures, Tourism and Resilience of cattle management" and "Ensure better breeding to enhance resilience and sustainability" will be worked on and BOKU is involved in all projects. Area 2 includes 5 projects, "Ensure better reproduction, animal health and wellbeing", "Ensure better feeding and reduced emissions: A sustainable approach", "Ensure resilient cows", "Ensure calf health and welfare in sustainable dairy production systems" and "ALMSURE - Ensure animal and environmental health in alpine dairy farming systems", BOKU is involved in all projects but project 8, ALMSURE.