**AWARDS ISSUED PRIOR TO JANUARY 20, 2025, WERE FUNDED UNDER PREVIOUS ADMINISTRATIONS AND MAY NOT REFLECT THE PRIORITIES AND POLICIES OF THE CURRENT ADMINISTRATION.** BETWEEN 2012 AND 2015, EAR ROTS OF MAIZE CAUSED A PREVENTABLE LOSS OF MORE THAN $3.1 BILLION FOR U.S. FARMERS. ONE PARTICULARLY PROBLEMATIC EAR ROT PATHOGEN IN THE NORTHERN MIDWEST IS GIBBERELLA EAR ROT (GER), LARGELY BECAUSE THE CAUSAL PATHOGEN, FUSARIUM GRAMINEARUM, CAN CAUSE FURTHER LOSS THROUGH THE DEPOSITION OF MYCOTOXINS IN THE GRAIN. A COMMON CONTROL STRATEGY FOR THE PREVENTION OF GER IS PLANTING RESISTANT MAIZE CULTIVARS.GENOMIC MODELING HAS REVOLUTIONIZED PLANT IMPROVEMENT, ENABLING THE SELECTION OF SUPERIOR CULTIVARS BASED ON GENOMIC DATA ALONE. HOWEVER, MOST AGRICULTURALLY IMPORTANT TRAITS, INCLUDING GER RESISTANCE, ARE SUBJECT TO ENVIRONMENTAL AND GENOTYPE-BY-ENVIRONMENT EFFECTS. BY CONSIDERING ONLY GENOMIC DATA, CURRENT GENOMIC SELECTION MODELS FAIL TO ACCOUNT FOR KNOWN SYSTEM DYNAMICS THAT INFLUENCE THE EXPRESSION OF THESE TRAITS. RATHER THAN RELYING ON GENOMIC DATA ALONE TO DEVELOP SUSTAINABLE STRATEGIES FOR THE PREVENTION OF POSTHARVEST LOSS, WE PROPOSE DEVELOPING HOLISTIC, SYSTEMS-BASED MACHINE LEARNING MODELS USING ENVIRONMENTAL, METABOLIC, AND GENOMIC DATA CONCURRENTLY. WE HYPOTHESIZE THAT THESE MODELS WILL ENABLE THE IDENTIFICATION OF RESISTANT GENETIC RESOURCES AND CAN PREDICT WHEN GER DISEASE PRESSURE WILL BE AN ISSUE FOR GROWERS. THIS RESEARCH WILL PROVIDE THE FOUNDATION FOR NOVEL MODELING METHODOLOGIES THAT CAN IMPROVE THE SUSTAINABILITY OF AGRICULTURAL PRODUCTION SYSTEMS. WE ENVISION THESE METHODS CAN BE EXTENDED TO MODEL OTHER CROPS AS WELL AS OTHER PATHOGEN AND INSECT PESTS.