Artificial neural networks for streamflow prediction

被引:72
作者
Dolling, OR [1 ]
Varas, EA
机构
[1] Univ Nacl San Juan, Dept Hydraul, San Juan, Argentina
[2] Pontificia Univ Catolica Chile, Sch Engn, Santiago, Chile
关键词
D O I
10.1080/00221680209499899
中图分类号
TU [建筑科学];
学科分类号
0813 ;
摘要
This paper presents monthly streamflow prediction using artificial neural networks (ANN) on mountain watersheds. The procedure addresses the selection of input variables, the definition of model architecture and the strategy of the learning process. Results show that spring and summer monthly streamflows can be adequately represented, improving the results of calculations obtained using other methods. Better streamflow prediction methods should have significant benefits for the optimal use of water resources for irrigation and hydroelectric energy generation.
引用
收藏
页码:547 / 554
页数:8
相关论文
共 35 条
[1]  
ABRAHART RJ, 1998, NEW TOOLS NEUROHYDRO
[2]  
ABRAHART RJ, 1998, NEURAL NETWORKS VS A
[3]  
ACEITUNO P, 1995, REV SOC CHILENA HIDR, V10, P63
[4]  
ANDREAS Z, 1995, 695 U STUTTG I PAR D
[5]   CLUSTERING CHARACTERIZATION OF ADAPTIVE RESONANCE [J].
BURKE, LI .
NEURAL NETWORKS, 1991, 4 (04) :485-491
[6]  
CRAWFORD NH, 1962, 39 STANF U STANFORD
[7]  
DANDY G, 1996, P INT C WAT RES ENV, V2
[8]  
DEAN T, 1995, ARTIF INTELL, P179
[9]   On the encapsulation of numerical-hydraulic models in artificial neural network [J].
Dibike, YB ;
Solomatine, D ;
Abbott, MB .
JOURNAL OF HYDRAULIC RESEARCH, 1999, 37 (02) :147-161
[10]  
ELAINE R, 1996, INTELIGENCIA ARTIFIC, P537