Mitigating the risk of atrazine exposure: Identifying hot spots and hot times in surface waters across Nebraska, USA.

Atrazine, one of the most widely used herbicides in the world, threatens human health along with terrestrial and aquatic biota. Recent reports have found atrazine in drinking water to be associated with increased birth defects and incidences of Non-Hodgkin's Lymphoma, with higher levels of significance from exposure to both atrazine and nitrate-N. The Midwest region of the United States, which includes Nebraska, is one of the leading regions for high nitrate-N concentrations and agrochemicals, including atrazine, in surface waters. Therefore, the objective of this study was to provide a case study for completing an environmental risk analysis for the potential exposure of atrazine and nitrate-N to ecosystems and humans through interaction with surface waters using two approaches: (1) Identify watersheds across Nebraska that were at risk for exceeding atrazine and nitrate-N maximum contaminant limits (MCLs) in surface water; and (2) Determine the specific times of year where risks were greatest. Factors were then analyzed using Geographic Information System (GIS) software to identify areas of high risk. Impairments for both nitrate-N and atrazine in the surface water were found predominately during the early growing season in the southeastern region of Nebraska, in watershed areas with the highest amount of corn production and annual precipitation. Further, the methodology developed in this study has the potential for application in regions with higher dependency on surface water to determine multiple agrochemical load influxes from upstream regions and evaluate other surface water contaminants during the same time periods.

Predicting Escherichia coli loads in cascading dams with machine learning: An integration of hydrometeorology, animal density and grazing pattern.

Accurate prediction of Escherichia coli contamination in surface waters is challenging due to considerable uncertainty in the physical, chemical and biological variables that control E. coli occurrence and sources in surface waters. This study proposes a novel approach by integrating hydro-climatic variables as well as animal density and grazing pattern in the feature selection modeling phase to increase E. coli prediction accuracy for two cascading dams at the US Meat Animal Research Center (USMARC), Nebraska. Predictive models were developed using regression techniques and an artificial neural network (ANN). Two adaptive neuro-fuzzy inference system (ANFIS) structures including subtractive clustering and fuzzy c-means (FCM) clustering were also used to develop models for predicting E. coli. The performances of the predictive models were evaluated and compared using root mean squared log error (RMSLE). Cross-validation and model performance results indicated that although the majority of models predicted E. coli accurately, ANFIS models resulted in fewer errors compared to the other models. The ANFIS models have the potential to be used to predict E. coli concentration for intervention plans and monitoring programs for cascading dams, and to implement effective best management practices for grazing and irrigation during the growing season.