Simplifying artificial neural network models of river basin behaviour by an automated procedure for input variable selection

The objective of the present work is to present a simplified and automated method for identifying and excluding unnecessary input variables, with a consequent reduction in dimensionality of ANN-based hydrological models. The proposed method is iterative and computationally efficient: it consists of perturbing the input variables, recording the change in model performance, establishing an index showing the contribution of each variable to the ANN (the relative contribution index, RCI) and excluding the least-influential variables that fall below a threshold. The method was used to simulate mean daily flow for a 20-year period 1989-2009 from four drainage basins nested at different scales ranging from 19.4km? to 9426km?, in the Southern Brazil. The main result of this method of simplifying ANN-based hydrological models was to increase the Nash-Sutcliffe (NS) coefficient and to reduce RMSE in all the simulations undertaken. The potential of ANN models was therefore improved by eliminating unnecessary and/or redundant variables. Simulating the intermediate basin with area 5414km? (Santo i?ngelo), for example, the initial performance (12 inputs; NS=0.894) improved when a simpler and more parsimonious model was used (4 inputs; NS=0.944). To validate the simplification procedure, a comparison was made between the proposed method (RCI) and the well-known methods of Overall Connection Weights (OCW) and Forward Stepwise Addition (FSA). For the comparison between RCI and OCW methods, in most cases, the ordering of selected variables was similar, confirming that the two procedures satisfactorily identify the more important variables, although the RCI is computationally more efficient giving a small advantage in the resulting model performance. In the FSA method, although the performance of the obtained models has also been satisfactory, the computational effort was much greater than with the other two methods because of the excessive number of the neural network training performed (117 training procedures in Combination 2, against only six for the RCI method, for example). An excessive number of input variables can reduce the efficiency of ANN simulation.A criterion was established by which input variables could be selected for exclusion.The proposed method satisfactorily identifies the most important variables.Simplification of the ANN improved performance of hydrological simulations.

[1]  G. David Garson,et al.  Interpreting neural-network connection weights , 1991 .

[2]  Dong Yu,et al.  Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech Recognition , 2012, IEEE Transactions on Audio, Speech, and Language Processing.

[3]  Mehdi Khashei,et al.  A novel hybridization of artificial neural networks and ARIMA models for time series forecasting , 2011, Appl. Soft Comput..

[4]  A. Shamseldin.  Application of a neural network technique to rainfall-runoff modelling , 1997 .

[5]  A. Soldati,et al.  Forecasting river flow rate during low‐flow periods using neural networks , 1999 .

[6]  O. Pedrollo,et al.  Artificial Neural Network Methods Applied to Forecasting River Levels , 2013 .

[7]  W. Pitts,et al.  A Logical Calculus of the Ideas Immanent in Nervous Activity (1943) , 2021, Ideas That Created the Future.

[8]  Russell G. Death,et al.  An accurate comparison of methods for quantifying variable importance in artificial neural networks using simulated data , 2004 .

[9]  Christopher M. Bishop,et al.  Neural networks for pattern recognition , 1995 .

[10]  Sovan Lek,et al.  Improved estimation, using neural networks, of the food consumption of fish populations , 1995 .

[11]  Sevket Durucan,et al.  River flow prediction using artificial neural networks: generalisation beyond the calibration range. , 2000 .

[12]  Rajarshi Guha,et al.  Interpreting Computational Neural Network Quantitative Structure-Activity Relationship Models: A Detailed Interpretation of the Weights and Biases , 2005, J. Chem. Inf. Model..

[13]  Holger R. Maier,et al.  Use of artificial neural networks for modelling cyanobacteria Anabaena spp. in the River Murray, South Australia , 1998 .

[14]  Bernard Widrow,et al.  Adaptive switching circuits , 1988 .

[15]  P. Chevallier,et al.  Land use change effects on runoff and erosion from plot to catchment scale on the basaltic plateau of Southern Brazil , 1999 .

[16]  Jinde Cao,et al.  Exponential Synchronization of Linearly Coupled Neural Networks With Impulsive Disturbances , 2011, IEEE Transactions on Neural Networks.

[17]  Kuolin Hsu,et al.  Artificial Neural Network Modeling of the Rainfall‐Runoff Process , 1995 .

[18]  Dervis Karaboga,et al.  Hybrid Artificial Bee Colony algorithm for neural network training , 2011, 2011 IEEE Congress of Evolutionary Computation (CEC).

[19]  A. W. Jayawardena,et al.  Comparison of Multilayer Perceptron and radial Basis Function networks as tools for flood forecasting , 1996 .

[20]  Ashu Jain,et al.  Hybrid neural network models for hydrologic time series forecasting , 2007, Appl. Soft Comput..

[21]  Julian D. Olden,et al.  Illuminating the “black box”: a randomization approach for understanding variable contributions in artificial neural networks , 2002 .

[22]  Jing Shi,et al.  On comparing three artificial neural networks for wind speed forecasting , 2010 .

[23]  Holger R. Maier,et al.  Neural networks for the prediction and forecasting of water resource variables: a review of modelling issues and applications , 2000, Environ. Model. Softw..

[24]  K. P. Sudheer,et al.  A data‐driven algorithm for constructing artificial neural network rainfall‐runoff models , 2002 .

[25]  Adam Slowik,et al.  Application of an Adaptive Differential Evolution Algorithm With Multiple Trial Vectors to Artificial Neural Network Training , 2011, IEEE Transactions on Industrial Electronics.

[26]  Holger R. Maier,et al.  Input determination for neural network models in water resources applications. Part 1—background and methodology , 2005 .

[27]  I. Dimopoulos,et al.  Application of neural networks to modelling nonlinear relationships in ecology , 1996 .

[28]  Holger R. Maier,et al.  Determining Inputs for Neural Network Models of Multivariate Time Series , 1997 .

[29]  H. Maier,et al.  The Use of Artificial Neural Networks for the Prediction of Water Quality Parameters , 1996 .

[30]  Yannis Dimopoulos,et al.  Use of some sensitivity criteria for choosing networks with good generalization ability , 1995, Neural Processing Letters.

[31]  Adam P. Piotrowski,et al.  Optimizing neural networks for river flow forecasting – Evolutionary Computation methods versus the Levenberg–Marquardt approach , 2011 .

[32]  Michele Scardi,et al.  Developing an empirical model of phytoplankton primary production: a neural network case study , 1999 .

[33]  Robert W. Blanning,et al.  An empirical measure of element contribution in neural networks , 1998, IEEE Trans. Syst. Man Cybern. Part C.

[34]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[35]  Christian W. Dawson,et al.  An artificial neural network approach to rainfall-runoff modelling , 1998 .

[36]  M. Gevrey,et al.  Review and comparison of methods to study the contribution of variables in artificial neural network models , 2003 .

[37]  A. T. C. Goh,et al.  Back-propagation neural networks for modeling complex systems , 1995, Artif. Intell. Eng..

[38]  Daniel Rivero,et al.  Automatic epileptic seizure detection in EEGs based on line length feature and artificial neural networks , 2010, Journal of Neuroscience Methods.

[39]  B. S. Thandaveswara,et al.  A non-linear rainfall–runoff model using an artificial neural network , 1999 .

[40]  K. P. Sudheer,et al.  Identification of physical processes inherent in artificial neural network rainfall runoff models , 2004 .

[41]  Mansour Talebizadeh,et al.  Uncertainty analysis for the forecast of lake level fluctuations using ensembles of ANN and ANFIS models , 2011, Expert Syst. Appl..

[42]  Chandranath Chatterjee,et al.  Uncertainty assessment and ensemble flood forecasting using bootstrap based artificial neural networks (BANNs) , 2010 .

[43]  H. Akaike.  A new look at the statistical model identification , 1974 .