The food system is a social determinant of health and a leverage point for reducing diet-related racial inequities. Yet, food system interventions have not resulted in sustained improvement in dietary outcomes for underrepresented minorities living in neighborhoods with a history of disinvestment. Research is needed to illuminate the dynamics structuring food systems in racialized neighborhoods to inform intervention development. To conduct participatory research examining the complexity and inequity of food systems in historically redlined neighborhoods to identify feedback mechanisms to leverage in efforts to transform system outcomes for racial equity. We conducted a mixed-methods study in Cleveland, Ohio, USA from 2018 to 2021 using participatory system dynamic modeling with 30 academic and community partners, in-depth qualitative interviews with 22 key stakeholders, and public convenings with 250 local food policy council affiliates. Data were synthesized into causal loop diagrams depicting feedback mechanisms reinforcing or balancing neighborhood-level food system dynamics. We identified 10 feedback mechanisms structuring nutrition equity, which was identified as a meta-goal for food systems in racialized neighborhoods. Feedback mechanisms were organized in 3 domains: 1) meeting basic food needs with dignity (i.e., side hustle, government benefits, emergency food assistance, stigma, and stereotypes); 2) local food supply and demand dynamics (i.e., healthy food retail, job security, food culture, and norms); and 3) community empowerment and food sovereignty (i.e., community power, urban agriculture, risk of gentrification). Five exogenous factors moderate feedback dynamics: neighborhood crisis, neighborhood investments, household costs, government benefit funding, and voter participation. We identified nutrition equity as an overarching goal for local food systems, which reflects a state of having freedom, agency, and dignity in food traditions resulting in people and communities healthy in body, mind, and spirit. It is a transformative goal designed to spur system-level interventions that further racial equity through improved local food system dynamics.

Agriculture ranks as one of the top contributors to global warming and nutrient pollution. Quantifying life cycle environmental impacts from agricultural production serves as a scientific foundation for forming effective remediation strategies. However, methods capable of accurately and efficiently calculating spatially explicit life cycle global warming (GW) and eutrophication (EU) impacts at the county scale over a geographic region are lacking. The objective of this study was to determine the most efficient and accurate model for estimating spatially explicit life cycle GW and EU impacts at the county scale, with corn production in the U.S.’s Midwest region as a case study. This study compared the predictive accuracies and efficiencies of five distinct supervised machine learning (ML) algorithms, testing various sample sizes and feature selections. The results indicated that the gradient boosting regression tree model built with approximately 4000 records of monthly weather features yielded the highest predictive accuracy with cross-validation (CV) values of 0.8 for the life cycle GW impacts. The gradient boosting regression tree model built with nearly 6000 records of monthly weather features showed the highest predictive accuracy with CV values of 0.87 for the life cycle EU impacts based on all modeling scenarios. Moreover, predictive accuracy was improved at the cost of simulation time. The gradient boosting regression tree model required the longest training time. ML algorithms demonstrated to be one million times faster than the traditional process-based model with high predictive accuracy. This indicates that ML can serve as an alternative surrogate of process-based models to estimate life-cycle environmental impacts, capturing large geographic areas and timeframes.