Author(s)

K.Hiramatsu, E.Ichion, T.Kawachi, J.Takeuchi

Abstract

ANN and GA methods to identify the non-point contamination flux to groundwater K. Hiramatsu*, E. Ichion^, T. Kawachi*, & J. Takeuchi* 'Division of Environmental Science and Technology, Kyoto University, Japan * Department of Agricultural Engineering, Ishikawa Agricultural College, Japan Abstract Contamination of groundwater due to non-point source, e.g., excessive fer- tilizer use in farming, is becoming a serious problem in many parts of the world. Quality of groundwater is often monitored at wells for its appro- priate management. However, methodologies to identify the incoming flux values, inversely from the monitored data, are not completely established yet and still developing. In this research, two types of the identification methods, i.e., artificial neural network (ANN) and genetic algorithm (GA) methods are presented. ANN and GA are similarly employed to identify the incoming flux of contamination, combined with numerical solute trans- port simulations. Their applicabil

Keywords