Author(s): James Kuo; Ying-Yi Wang; Wu-Seng Lung; Clark C. K. Liu; Nian She

Linked Author(s):

Keywords: Water quality modeling; Feitsui Reservoir; WASP/EUTRO model; Eutrophication control; NN and GA models

Abstract: This paper presents a combined neural network (NN) and genetic algorithms (GAs) approach for real-time eutrophication management of a reservoir, applied to the Feitsui Reservoir in northern Taiwan as a case study. First, a simplified water quality model based on NN was developed and applied to predict chlorophyll a concentrations in Feitsui Reservoir. The performance and validity of the proposed NN model was evaluated using a sophisticated eutrophication model (WASP/EUTRO). Further, a GA with water quality prediction produced by the NN model was used to optimize the control of watershed nutrient loads. The GA was applied to address the problem in reservoir water quality management and to provide an alternative when searching for an optimal control strategy. Finally, the time-variable control schemes derived from the NN-GA method were applied to the WASP/EUTRO model to assess the impact on eutrophication in Feitsui Reservoir following phosphorus load reductions in its watershed. In practice, the time-varying reductions in phosphorus loads for controlling reservoir eutrophication can be achieved by way of the combined reduction of point and nonpoint source pollution loads.

DOI:

Year: 2013