Machine learning-based life cycle assessment for environmental sustainability optimization of a food supply chain

Abstract Effective resource allocation in the agri-food sector is essential in mitigating environmental impacts and moving toward circular food supply chains. The potential of integrating life cycle assessment (LCA) with machine learning has been highlighted in recent studies. This hybrid framework is valuable not only for assessing food supply chains but also for improving them toward a more sustainable system. Yet, an essential step in the optimization process is defining the optimization boundaries, or minimum and maximum quantities for the variables. Usually, the boundaries for optimization variables in these studies are obtained from the minimum and maximum values found through interviews and surveys. A deviation in these ranges can impact the final optimization results. To address this issue, this study applies the Delphi method for identifying variable optimization boundaries. A hybrid environmental assessment framework linking LCA, multilayer perceptron artificial neural network, the Delphi method, and genetic algorithm was used for optimizing the pomegranate production system. The results indicated that the suggested framework holds promise for achieving substantial mitigation in environmental impacts (potential reduction of global warming by 46%) within the explored case study. Inclusion of the Delphi method for variable boundary determination brings novelty to the resource allocation optimization process in the agri-food sector. Integr Environ Assess Manag 2024;20:1759–1769. © 2024 SETAC Key Points Integrating life cycle assessment (LCA) with machine learning offers a robust method for optimizing food supply chains. The novel use of the Delphi methodology to define optimization bounds improves the accuracy of environmental impact reduction strategies. Applying a combination of LCA, machine learning, and Delphi can potentially reduce global warming potential (by 46%) in case of pomegranate production.