Improving extreme hydrologic events forecasting using a new criterion for artificial neural network selection

被引：74

作者：

Coulibaly, P ^{[1
]}

Bobée, B ^{[1
]}

Anctil, F ^{[1
]}

机构：

[1] Inst Natl Rech Sci, INRS Eau, Alcan Chair Stat Hydrol, NSERCH,Hydro Quebec, Ste Foy, PQ G1V 4C7, Canada

来源：

HYDROLOGICAL PROCESSES | 2001年 / 15卷 / 08期

关键词：

extreme hydrologic events; artificial neural networks; forecast;

D O I：

10.1002/hyp.445

中图分类号：

TV21 [水资源调查与水利规划];

学科分类号：

081501 ;

摘要：

The issue of selecting appropriate model input parameters is addressed using a peak and low flow criterion (PLC). The optimal artificial neural network (ANN) models selected using the PLC significantly outperform those identified with the classical root-mean-square error (RMSE) or the conventional Nash-Sutcliffe coefficient (NSC) statistics. The comparative forecast results indicate that the PLC can help to design an appropriate ANN model to improve extreme hydrologic events (peak and low flow) forecast accuracy, Copyright (C) 2001 John Wiley & Sons, Ltd.

引用

页码：1533 / 1536

页数：4

共 17 条

[1] [Anonymous], 1970, J Hydrol, V10, DOI [DOI 10.1016/0022-1694(70)90255-6, 10.1016/0022-1694(70)90255-6]
[2] Daily reservoir inflow forecasting using artificial neural networks with stopped training approach
Coulibaly, P
Anctil, F
Bobée, B
[J]. JOURNAL OF HYDROLOGY, 2000, 230 (3-4) : 244 - 257
[3] Coulibaly P, 2000, HYDROL PROCESS, V14, P2755, DOI [10.1002/1099-1085(20001030)14:15&lt
[4] 2755::AID-HYP90&gt
[5] 3.0.CO
[6] 2-9, 10.1002/1099-1085(20001030)14:15<2755::AID-HYP90>3.0.CO
[7] 2-9]
[8] Neural network-based long-term hydropower forecasting system
Coulibaly, P
Anctil, F
Bobée, B
[J]. COMPUTER-AIDED CIVIL AND INFRASTRUCTURE ENGINEERING, 2000, 15 (05) : 355 - 364
[9] Gupta HV, 2000, WTR SCI TEC LIBR, V36, P7
[10] River flow prediction using artificial neural networks: generalisation beyond the calibration range
Imrie, CE
Durucan, S
Korre, A
[J]. JOURNAL OF HYDROLOGY, 2000, 233 (1-4) : 138 - 153

← 1 2 →