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.

Assessing the environmental impacts of food donation systems is necessary to support food donation policy and management. Few life cycle assessment (LCA) studies have investigated the environmental impacts of food donation systems. This comparative LCA study analyzed the environmental impacts of eight different donation scenarios reflecting diverse supply chain configurations and operational management options, using 391.8 kg of redistributed food over two weeks as the functional unit. Each of the eight scenarios presented net environmental benefits for all five life cycle environmental impact categories: 132~233 kg CO₂-eq for global warming potential, 2.30~5.24 kg SO₂-eq for acidification potential, 1.13~2.04 kg N-eq for eutrophication potential, 1791~3140 MJ for cumulative energy demand, and 3.7 × 10⁷~5.8 × 10⁷ m³ for water resource depletion. The highest magnitudes of environmental benefits were achieved when intermediary organizations collected and gleaned the surplus food from donors and then transported it to food pantries (the eighth scenario). Improving the quality of donated food, augmenting the sorting capacities of emergency organizations, and shortening transportation distances could increase the environmental benefits of food donation systems. The environmental impact intensities of production and waste management choices for food waste generated during the redistribution of the surplus food ranked as the top influential factors for the five environmental impacts. Rescuing surplus food from donors who landfilled the wasted food tended to yield larger environmental benefits than from donors who composted it. Overall, this study finds that improving donation quality and increasing the capacities of emergency food organizations are crucial for maximizing the environmental benefits of the fresh produce donation system.

Food policies that respond to shocks and support nutritious diets for vulnerable populations can enhance resilience, support social equity, and reduce environmental damage. Using a simulation model, we evaluated the effectiveness of two food redistribution policies—Nourish New York, a program providing funds to food rescue organizations to purchase food directly from farmers, and the Food Donation and Food Scraps Recycling Law (an organics “waste ban”)—in response to a shock such as the COVID-19 pandemic. We assessed policy based on recovered food and life cycle carbon and water footprints over 10 years. Both policies improved produce donations during post-shock. The waste ban increased waste at feeding organizations; diverting unavoidable food waste to composting and anaerobic digestion mitigated its carbon footprint. Enhanced coordination and partnerships within the food redistribution network were crucial for ensuring that produce reached those in need, ultimately reducing long-term environmental impacts. Implementing multiple strategies that enhance recovery from farms and retail, while strengthening the organizational capacity of the food redistribution network, can simultaneously advance food security and environmental goals.