As outlined in an article published in IOPscience, the research team built a series of machine-learning-based metamodels that can almost perfectly mimic a well-tested crop model at much faster speeds. Using the metamodels, they generated millions of scenario simulations and investigated two fundamental sustainability questions -- where are the mitigation hotspots, and how much mitigation can be expected under different management scenarios.
"We synthesized four simulated indicators of agroecosystem sustainability -- yield, N2O emissions, nitrogen leaching, and changes in soil organic carbon -- into economic net societal benefits as the basis for identifying hotspots and infeasible land for mitigation," said Taegon Kim, CFANS research associate in the BBE department. The societal benefits include cost savings from GHG mitigation, as well as improved water and air quality.
"By providing key sustainability indicators related to upstream crop production, our metamodels can be a useful tool for food companies to quantify the emissions in their supply chain and distinguish mitigation options for setting sustainability goals," said Timothy Smith, professor of Sustainable Systems Management and International Business Management in CFANS's BBE department.
Click here to see more...