Development of an Artificial Neural Network Model for Hydrologic and Water Quality Modeling of Agricultural Watersheds

Agriculture is the leading source of non-point source pollution on a national scale. The driving force of non-point source pollution is the rainfall-runoff process, which is the transformation of rainfall to direct streamflow. This is a complex, nonlinear, time-varying, and space-distributed process on the watershed scale that is difficult to effectively model by conventional, deterministic means. Artificial neural networks (ANNs) offer a new approach to forecasting the hydrologic and water quality response of a watershed system. The goal of this work is to develop an ANN model as a long-term forecasting tool for predicting the hydrology and water quality of agricultural watersheds. The chosen form of neural network is a flexible mathematical structure, which is capable of identifying complex nonlinear relationships between input and output data sets. In this paper, a multi-layer, feed forward ANN model was developed and tested using historical daily rainfall, streamflow, and nitrate information. Using observed rainfall, stream flow, and water quality data from the Vermilion River and Little Vermilion River watersheds in Illinois; the ANN was applied to predict daily stream flow and nutrient loads based on rainfall. The results show highly accurate performance of the ANN model (R 2 values > 0.90) in predicting daily stream flow and nitrate loads.