NutriTwin seeks to enhance nutrient efficiency in pig production by developing data-driven feeding strategies that reduce the carbon, nitrogen, and phosphorus footprints. More specifically, the project proposes to research how dietary nutrient flows on a pig farm can be modelled into a dynamic digital representation of the production process, i.e. a digital twin. By continuously feeding up-to-date, farm-specific training data into a generic digital twin architecture, the system evolves into a digital twin tailored to that specific farm, accurately capturing its respective nutrient requirements and utilization efficiencies. The knowledge can be used to better understand the ideal composition of different feeds used on the farm, reducing nutrient waste, lowering the environmental footprint, and achieving significant cost savings. By integrating life cycle analysis (LCA) tools within the digital twin, NutriTwin enables farm-specific scenario testing to effectively reduce pork's carbon and environmental footprint. NutriTwin will be designed from the ground up with scalability in mind, ensuring the approach can expand to an industry-wide application while maintaining flexibility for diverse farm operations. Additionally, the project will address critical concerns about data ownership and sharing by using secure, decentralized data frameworks, removing barriers to improve industry collaboration and future knowledge discovery.