Predicting Salmonella prevalence associated with meteorological factors in pastured poultry farms in southeastern United States

Consumer demand has increased for pastured poultry products as the drive for sustainable farming practices and ethical treatments of livestock have become popular in the press. It is necessary to identify the important meteorological factors associated with the prevalence of Salmonella in the pastured poultry settings since the presence of Salmonella in the environment could lead to contamination of the final product. The objective of this study was to develop a model to describe the relationship between meteorological factors and the presence of Salmonella on the pastured poultry farms. The random forest method was used to develop a model where 83 meteorological factors were included as the predicting variables. The soil model identified humidity as the most important variable associated with Salmonella prevalence, while high wind gust speed and average temperature were identified as important meteorological variables in the feces model. The developed models were robust in predicting the prevalence of Salmonella in pastured poultry farms with the area under receiver operating characteristic (ROC) curve values of 0.884 and 0.872 for the soil model and feces model, respectively. The predictive models developed in this study can provide users with practical and effective tools to make informed decisions with scientific evidence regarding the meteorological parameters that are important to monitor for increased on-farm Salmonella prevalence. (C) 2020 Elsevier B.V. All rights reserved.