Simulation-based assessment of incentives for food loss and waste reduction in agri-food supply chains using a digital twin approach

Food loss and waste remain the most pressing global sustainability challenges with enormous environmental, social, and economic consequences. Addressing this issue requires not only technological innovation but also a deeper understanding of how innovations diffuse and interact across supply chains. This study develops a multi-agent diffusion simulation model, calibrated with empirical data and stakeholder inputs, to assess three innovations across different product chains from 2025 to 2050. Innovations such as smart packaging for meat, AI-driven demand forecasting for fish, and AI-based quality for fruit, enabling the quantification of waste, costs, and greenhouse gas emissions under varying adoption pathways. The results show that innovation's impacts are powerfully context dependent. Smart packaging in the meat chain brings steady waste reductions of 10–15% in 2050, primarily by extending shelf life and reducing expiries. AI demand forecasting for fish achieves the most transformative outcomes, reducing waste by up to 27% together with marked decreases in costs and emissions. AI quality recognition for fruit offers smaller yet valuable gains, shifting consumer acceptance and improving retailer sell-through imperfect produce. Faster and broader adoption leads to larger benefits, highlighting the need for supportive policies, incentives, and consumer engagement to improve diffusion. By integrating diffusion theory with supply chain simulation, this study offers methodological and applied insights, serving as a decision-support tool for stakeholders to strategically deploy innovations and inform policy design. It contributes to the evidence required to achieve the EU's 2030 food waste reduction targets and promote sustainable food systems.