River flood forecasting with a neural network model

被引:338
作者
Campolo, M
Andreussi, P
Soldati, A
机构
[1] Univ Udine, Ctr Fluidodinam & Idraul, I-33100 Udine, Italy
[2] Univ Udine, Dipartimento Sci & Tecnol Chim, I-33100 Udine, Italy
关键词
D O I
10.1029/1998WR900086
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
A neural network model was developed to analyze and forecast the behavior of the river Tagliamento, in Italy, during heavy rain periods. The model makes use of distributed rainfall information coming from several rain gauges in the mountain district and predicts the water level of the river at the section closing the mountain district. The water level at the closing section in the hours preceding the event was used to characterize the behavior of the river system subject to the rainfall perturbation. Model predictions are very accurate (i.e., mean square error is less than 4%) when the model is used with a 1-hour time horizon. Increasing the time horizon, thus making the model suitable for flood forecasting, decreases the accuracy of the model. A limiting time horizon is found corresponding to the minimum time lag between the water level at the closing section and the rainfall, which is characteristic of each flooding event and depends on the rainfall and on the state of saturation of the basin. Performance of the model remains satisfactory up to 5 hours. A model of this type using just rainfall and water level information does not appear to be capable of predicting beyond this time limit.
引用
收藏
页码:1191 / 1197
页数:7
相关论文
共 18 条
[1]   RAINFALL-BASED REAL-TIME FLOOD FORECASTING [J].
BERTONI, JC ;
TUCCI, CE ;
CLARKE, RT .
JOURNAL OF HYDROLOGY, 1992, 131 (1-4) :313-339
[2]   NEURAL NETWORKS AND THEIR APPLICATIONS [J].
BISHOP, CM .
REVIEW OF SCIENTIFIC INSTRUMENTS, 1994, 65 (06) :1803-1832
[3]   Runoff components simulated by rainfall-runoff models [J].
Buchtele, J ;
Elias, V ;
Tesar, M ;
Herrmann, A .
HYDROLOGICAL SCIENCES JOURNAL-JOURNAL DES SCIENCES HYDROLOGIQUES, 1996, 41 (01) :49-60
[4]   FORECASTING THE BEHAVIOR OF MULTIVARIATE TIME-SERIES USING NEURAL NETWORKS [J].
CHAKRABORTY, K ;
MEHROTRA, K ;
MOHAN, CK ;
RANKA, S .
NEURAL NETWORKS, 1992, 5 (06) :961-970
[5]   A DISTRIBUTED MODEL FOR REAL-TIME FLOOD FORECASTING USING DIGITAL ELEVATION MODELS [J].
GARROTE, L ;
BRAS, RL .
JOURNAL OF HYDROLOGY, 1995, 167 (1-4) :279-306
[6]  
Haykin S.S., 1995, Neural networks. A comprehensive foundation
[7]   ARTIFICIAL NEURAL-NETWORK MODELING OF THE RAINFALL-RUNOFF PROCESS [J].
HSU, KL ;
GUPTA, HV ;
SOROOSHIAN, S .
WATER RESOURCES RESEARCH, 1995, 31 (10) :2517-2530
[8]   Neural network model of rainfall-runoff using radial basis functions [J].
Mason, JC ;
Price, RK ;
Temme, A .
JOURNAL OF HYDRAULIC RESEARCH, 1996, 34 (04) :537-548
[9]   Artificial neural networks as rainfall-runoff models [J].
Minns, AW ;
Hall, MJ .
HYDROLOGICAL SCIENCES JOURNAL-JOURNAL DES SCIENCES HYDROLOGIQUES, 1996, 41 (03) :399-417
[10]  
Mukherjee D, 1996, J HYDRAUL ENG-ASCE, V122, P130, DOI 10.1061/(ASCE)0733-9429(1996)122:3(130)