Artificial neural network ensembles and their application in pooled flood frequency analysis

[1] Recent theoretical and empirical studies show that the generalization ability of artificial neural networks can be improved by combining several artificial neural networks in redundant ensembles. In this paper, a review is given of popular ensemble methods. Six approaches for creating artificial neural network ensembles are applied in pooled flood frequency analysis for estimating the index flood and the 10-year flood quantile. The results show that artificial neural network ensembles generate improved flood estimates and are less sensitive to the choice of initial parameters when compared with a single artificial neural network. Factors that may affect the generalization of an artificial neural network ensemble are analyzed. In terms of the methods for creating ensemble members, the model diversity introduced by varying the initial conditions of the base artificial neural networks to reduce the prediction error is comparable with more sophisticated methods, such as bagging and boosting. When the same method for creating ensemble members is used, combining member networks using stacking is generally better than using simple averaging. An ensemble size of at least 10 artificial neural networks is suggested to achieve sufficient generalization ability. In comparison with parametric regression methods, properly designed artificial neural network ensembles can significantly reduce the prediction error.

[1]  Yoav Freund,et al.  Experiments with a New Boosting Algorithm , 1996, ICML.

[2]  Anders Krogh,et al.  Neural Network Ensembles, Cross Validation, and Active Learning , 1994, NIPS.

[3]  Armando Freitas da Rocha,et al.  Neural Nets , 1992, Lecture Notes in Computer Science.

[4]  Michael Y. Hu,et al.  Explaining consumer choice through neural networks: The stacked generalization approach , 2003, Eur. J. Oper. Res..

[5]  Robert J. Abrahart,et al.  Multi-model data fusion for river flow forecasting: an evaluation of six alternative methods based on two contrasting catchments , 2002 .

[6]  R Govindaraju,et al.  ARTIFICIAL NEURAL NETWORKS IN HYDROLOGY: II, HYDROLOGIC APPLICATIONS , 2000 .

[7]  Alex J. Cannon,et al.  Downscaling recent streamflow conditions in British Columbia, Canada using ensemble neural network models , 2002 .

[8]  D. Thomas,et al.  Generalization of streamflow characteristics from drainage-basin characteristics , 1970 .

[9]  Thomas G. Dietterich.  An Experimental Comparison of Three Methods for Constructing Ensembles of Decision Trees: Bagging, Boosting, and Randomization , 2000, Machine Learning.

[10]  David H. Wolpert,et al.  Stacked generalization , 1992, Neural Networks.

[11]  null null,et al.  Artificial Neural Networks in Hydrology. II: Hydrologic Applications , 2000 .

[12]  Amanda J. C. Sharkey,et al.  Combining Artificial Neural Nets: Ensemble and Modular Multi-Net Systems , 1999 .

[13]  Darrel E. Bostow,et al.  An experimental comparison of three methods of instruction in health education for cancer prevention: traditional paper prose text, passive non-interactive computer presentation and overt-interactive computer presentation , 1992 .

[14]  Limsoon Wong,et al.  DATA MINING TECHNIQUES , 2003 .

[15]  T.,et al.  Training Feedforward Networks with the Marquardt Algorithm , 2004 .

[16]  V. Nguyen,et al.  A comparative study of regression based methods in regional flood frequency analysis , 1999 .

[17]  J. R. Wallis,et al.  Regional Frequency Analysis: An Approach Based on L-Moments , 1997 .

[18]  Evon M. O. Abu-Taieh,et al.  Comparative Study , 2020, Definitions.

[19]  Donald H. Burn,et al.  Flood frequency analysis for ungauged sites using a region of influence approach , 1994 .

[20]  Jie Zhang,et al.  A comparison of different methods for combining multiple neural networks models , 2002, Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290).

[21]  Leo Breiman,et al.  Stacked regressions , 2004, Machine Learning.

[22]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[23]  Ewa M. Bielihska,et al.  COMPARISON OF DIFFERENT METHODS , 1994 .

[24]  L. Cooper,et al.  When Networks Disagree: Ensemble Methods for Hybrid Neural Networks , 1992 .

[25]  A. K. Pujari,et al.  Data Mining Techniques , 2006 .

[26]  Donald H. Burn,et al.  A comparison of index flood estimation procedures for ungauged catchments , 2002 .

[27]  R. Schapire.  The Strength of Weak Learnability , 1990, Machine Learning.

[28]  D. Opitz,et al.  Popular Ensemble Methods: An Empirical Study , 1999, J. Artif. Intell. Res..

[29]  R. Beverton,et al.  Institute of Hydrology , 1972, Nature.

[30]  Walter Cedeño,et al.  On the Use of Neural Network Ensembles in QSAR and QSPR , 2002, J. Chem. Inf. Comput. Sci..

[31]  Roy W. Koch,et al.  Bias in Hydrologic Prediction Using Log-Transformed Regression Models , 1986 .

[32]  Padraig Cunningham,et al.  The NeuralBAG algorithm: optimizing generalization performance in bagged neural networks , 1999, ESANN.

[33]  Donald H. Burn,et al.  The use of flood regime information in regional flood frequency analysis , 2002 .

[34]  Jie Zhang,et al.  Developing robust non-linear models through bootstrap aggregated neural networks , 1999, Neurocomputing.

[35]  Amanda J. C. Sharkey,et al.  Boosting Using Neural Networks , 1999 .

[36]  Peggy A. Johnson,et al.  Problems with Logarithmic Transformations in Regression , 1990 .

[37]  Robert J. Abrahart,et al.  Multi-model data fusion for hydrological forecasting , 2001 .

[38]  Harris Drucker,et al.  Improving Regressors using Boosting Techniques , 1997, ICML.

[39]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[40]  D J Mayer,et al.  Reducing the risk of corneal graft rejection. A comparison of different methods. , 1987, Cornea.

[41]  Yoshua Bengio,et al.  Pattern Recognition and Neural Networks , 1995 .