Capability of Artificial Neural Network for Detecting Hysteresis Phenomenon Involved in Hydrological Processes

Abstract

In this paper, artificial neural network (ANN) was applied to model and study the signature of hysteresis phenomena in hydrological processes for the Eel River watershed located in California. Because of the nonlinear and stochastic nature of hysteresis phenomena, it is reasonable to expect ANN to develop a model that efficiently considers hysteretic loops. In this study, hysteretic loops were studied from different aspects such as forms, classification, and effective factors of creation. In rainfall-runoff modeling, counterclockwise loops were mostly observed, whereas in the runoff-sediment process, clockwise loops prevailed. Random or eight-shaped loops were expected in runoff hydrographs with several peaks. A direct relationship was detected between the width of the loops and the area of the subbasin. Larger areas led to wider hysteretic loops. The results showed that ANN efficiently considers hysteresis signs when modeling hydrological processes and can lead to appropriate performance.