| 内容提要: |
The water quality of rivers in many places is deteriorated because of external pollution sources such as rainwater runoff, industrial discharges, domestic wastewater, agricultural run-off and irrigation. Rainwater runoff was found to be a major pollutant source. However, the previous studies rarely paid attention to the dynamic changes of mainstream water quality in rainstorm periods. The purpose of this study is to develop a dynamic prediction of mainstream water quality by the method of radial basis function neural network. The results show that the flow and water quality can be well predicted by the well-trained radial basis function neural network. Present approach is shown to be an useable tool to predict mainstream water quality when the tributary flow into the mainstream in a rainstorm period.
|