CS-A: Generation of new data sets on animal health and welfare
Countries: the Netherlands,
Germany Partners: WU, WR, TI
Case Study A aims to digitize and interlink animal welfare data in the Netherlands and Germany, thua creating a digital animal welfare assessment and a data-oriented Welfare Quality (WQ) framework for broilers and pigs. The framework addresses welfare comprehensively, integrating sensor data and market insights. This approach enables industry advancements and value creation and enhances transparency and empowers regulatory bodies. The methodology, emphasizing the integration of data sources, has the potential to be replicated across species and geographical regions.
CS-B: Resilience and transparency
Partners: IGBZ, DTI
Case Study B focuses on the EU’s TRACES system, which facilitates online issuance of certificates, controls, and route planning and displacement of animals and animal products. Its direct benefits to farmers and food processors are unclear, and it burdens them administratively. To address this challenge, we propose novel digital solutions, including automation in livestock management and transport logs, through studies and workshops in Denmark and Poland. The case study aims at automating data management, enhancing welfare and environmental impacts’ control, promoting transparency, and empowering TRACES. This solution has the potential for EU-wide scalability, applicability across species, and integration into diverse contexts, paving the way for broader exploitation in the public and private sector.
CS-C: Robust AI methods for sensor based animal tracking
Countries: France, Belgium
Partners: Idele, KUL
Case Study C tackles challenges in automated animal tracking and welfare assessment when using embedded sensors and artificial intelligence (AI). It utilizes multi-farm datasets to examine technologies tailored for pigs (computer vision) and dairy cows (GPS sensors used for cows on the pasture). By leveraging animal-level data from diverse dairy farms, a web application called the Smart Labeling Loop algorithm is created to train robust AI algorithm. In pigs, video data from pig farms will be used. Digi4Live aims to demonstrate technology performance, develop prediction models, and establish guidelines for AI training, with a methodology designed for replicability across different applications.
CS-D: Integration of different technologies, including animal breeding
Countries: France, Belgium
Partners: INRAE, EFFAB, KUL
Text for the first page:
Case Study D, livestock systems face challenges which necessitate a re-evaluation of animal breeding objectives. The breeding goals shall take into consideration of social dynamics between animals and digitally-driven herd management methods. Exploring digital technologies, with literature reviews and stakeholder engagement guiding the integration of sensor measurements and promising technologies like electronic nesting, computer vision and genomic tools. The integration of new, technology-measured traits into breeding objectives can lead to superior genetic resources that are better suited to various farming systems and environments. These data acquisition and exchanges concepts are applicable across diverse agricultural landscapes in Europe.
CS-E: Data digitalization for environmental impact assessments using LCA
Partners: AUA, Luke
Case Study E will digitalize the necessary on-farm primary data gathering from pig and poultry farming to enable environmental life cycle assessments (LCA). It will develop user-friendly web-based farm-level primary data import templates and attempt to integrate available sensor and farm management data for this purpose. In addition, CS-E will developm a prototype software using the imported primary data to derive farm-level life cycle inventory datasets and estimate environmental performance for products of intensive pig and poultry farms, compliant with the EU-PEF method.
CS-F: Policy monitoring, policy impact and administration, EU-wide
Partners: Luke, FFA, VTT, DTI
Case Study F looks at agricultural and rural policy monitoring, which faces challenges due to manual documentation processes and scattered databases, requiring substantial resources from both farmers and authorities. To tackle this, a digitalized data-sharing strategy is proposed. Case study F involves collaborative sessions with stakeholders, evaluation of reported data, comparison with existing information, and establishment of a dataspace based on IDSA standards. This approach aims to enhance monitoring efficiency, leading to more reliable compliance assessment and policy impact evaluation. Its replicability across the EU is ensured through openly published components, fostering widespread adoption and adaptation by interested parties, thereby improving transparency and accountability across the agricultural value chain.