Application of WNN model for Flood Forecasting in Nanjing Section of Chuhe River Basin
In the small watershed of Nanjing section of the Chuhe River Basin,there is a flood intrusion in the upper reaches,and a river tide rising in the lower reaches.Generally,the accuracy of flood forecasting is low.The neural network is widely used in the field of flood forecasting,so the BP neural netw...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Office of Pearl River
2021-01-01
|
| Series: | Renmin Zhujiang |
| Subjects: | |
| Online Access: | http://www.renminzhujiang.cn/thesisDetails#10.3969/j.issn.1001-9235.2021.01.007 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | In the small watershed of Nanjing section of the Chuhe River Basin,there is a flood intrusion in the upper reaches,and a river tide rising in the lower reaches.Generally,the accuracy of flood forecasting is low.The neural network is widely used in the field of flood forecasting,so the BP neural network (BPNN) model and the wavelet neural network (WNN) model are used to simulate the flood forecasting of Nanjing section of the Chuhe River Basin.From the simulation indicators of the WNN model,it can be seen that the relative error of the total flow and the peak flow are less than 10%,the relative error of the peak time is less than 2 h,the root mean square error is less than 100,and the correlation coefficient is greater than 0.90,which are better than those of the BPNN model.The results show that the WNN model has higher simulation accuracy and faster convergence speed than the BPNN model,and can provide reference for subsequent flood forecasting in Nanjing section of Chuhe River Basin. |
|---|---|
| ISSN: | 1001-9235 |