The Development and Evaluation of Artificial Neural Networks for Modeling Indicator Organism Concentrations

Introduction Nonpoint source pollution from pathogens is a leading cause of water quality impairment in the United States. Consequently, there is a need for effective methods of modeling pathogen and pathogen indicator organism concentrations in surface waters in order to both predict concentrations and gain insight into the underlying causes of water quality impairment. While many process-based, statistical, and empirical models exist for water quality prediction, artificial neural network (ANN) models are increasingly being used for forecasting of water resources variables because ANNs are often capable of modeling complex systems for which behavioral rules or underlying physical processes are either unknown or difficult to simulate. Relatively few applications of ANNs involving indicator organism or pathogen modeling are reported in the literature.