A NUMERICAL APPROACH TO UNDERSTANDING RISK FACTORS IN THE FARM-TO-FORK PASTURED POULTRY SUPPLY CHAIN

Specifically, the objectives of this study are to:Construct machine learning models to identify major meteorological factors that are linked to an increased probability of foodborne pathogens (Salmonella, Listeria, and Campylobacter spp.) isolation in preharvest environmental pastured poultry samples,Construct machine learning models to identify major farm practice variables that are linked to an increased probability of foodborne pathogen isolation in preharvest and postharvest pastured poultry samples,Develop a quantitative microbial risk assessment model to characterize and estimate the exposure to bacterial foodborne Salmonella and Campylobacter spp., due to consumption of conventionally and alternatively (organic, pasture-raised etc.) produced poultry in the U.S.