Suspended sediment concentration estimation by stacking the genetic programming and neuro-fuzzy predictions

Display Omitted We present a new approach based on stacking to predict the suspended sediment.A neural network is used as a meta-model of the stacking method.The genetic programming and neuro-fuzzy results are stacked via the meta-model.Streamflow and suspended sediment are used as input data of model.The results indicate that our method greatly improved the prediction accuracy. In the new decade due to rich and dense water resources, it is vital to have an accurate and reliable sediment prediction and incorrect estimation of sediment rate has a huge negative effect on supplying drinking and agricultural water. For this reason, many studies have been conducted in order to improve the accuracy of prediction. In a wide range of these studies, various soft computing techniques have been used to predict the sediment. It is expected that combining the predictions obtained by these soft computing techniques can improve the prediction accuracy. Stacking method is a powerful machine learning technique to combine the prediction results of other methods intelligently through a meta-model based on cross validation. However, to the best of our knowledge, the stacking method has not been used to predict sediment or other hydrological parameters, so far. This study introduces stacking method to predict the suspended sediment. For this purpose, linear genetic programming and neuro-fuzzy methods are applied as two successful soft computing methods to predict the suspended sediment. Then, the accuracy of prediction is increased by combining their results with the meta-model of neural network based on cross validation. To evaluate the proposed method, two stations including Rio Valenciano and Quebrada Blanca, in the USA were selected as case studies and streamflow and suspended sediment concentration were defined as inputs to predict the daily suspended sediment. The obtained results demonstrated that the stacking method greatly improved RMSE and R 2 statistics for both stations compared to use of linear genetic programming or neuro-fuzzy solitarily.

[1]  O. Kisi,et al.  A genetic programming approach to suspended sediment modelling , 2008 .

[2]  Shie-Jue Lee,et al.  Time series forecasting with a neuro-fuzzy modeling scheme , 2015, Appl. Soft Comput..

[3]  Nandita Singh,et al.  ANN modelling of sediment concentration in the dynamic glacial environment of Gangotri in Himalaya , 2015, Environmental Monitoring and Assessment.

[4]  Ozgur Kisi,et al.  River suspended sediment concentration modeling using a neural differential evolution approach , 2010 .

[5]  H. Nagy,et al.  Prediction of Sediment Load Concentration in Rivers using Artificial Neural Network Model , 2002 .

[6]  Joseph R. Harrington,et al.  An assessment of the suspended sediment rating curve approach for load estimation on the Rivers Bandon and Owenabue, Ireland , 2013 .

[7]  Martha Pulido,et al.  Particle swarm optimization of ensemble neural networks with fuzzy aggregation for time series prediction of the Mexican Stock Exchange , 2014, Inf. Sci..

[8]  Peter Ackers,et al.  Sediment Transport: New Approach and Analysis , 1973 .

[9]  Amir Ahmad Dehghani,et al.  Evaluation of suspended load transport rate using transport formulas and artificial neural network models (Case study: Chelchay Catchment) , 2013 .

[10]  Özgür Kisi,et al.  Constructing neural network sediment estimation models using a data-driven algorithm , 2008, Math. Comput. Simul..

[11]  Özgür Kisi,et al.  River suspended sediment estimation by climatic variables implication: Comparative study among soft computing techniques , 2012, Comput. Geosci..

[12]  Zheng Jin-hai,et al.  Estimating suspended sediment loads in the Pearl River Delta region using sediment rating curves , 2012 .

[13]  Najmeh Mahjouri,et al.  Integrating Support Vector Regression and a geomorphologic Artificial Neural Network for daily rainfall-runoff modeling , 2016, Appl. Soft Comput..

[14]  Zaher Mundher Yaseen,et al.  ANN Based Sediment Prediction Model Utilizing Different Input Scenarios , 2015, Water Resources Management.

[15]  Halil Ibrahim Erdal,et al.  Advancing monthly streamflow prediction accuracy of CART models using ensemble learning paradigms , 2013 .

[16]  O. Kisi,et al.  Suspended sediment modeling using genetic programming and soft computing techniques , 2012 .

[17]  D. Walling.  Assessing the accuracy of suspended sediment rating curves for a small basin , 1977 .

[18]  Ozgur Kisi,et al.  Estimation of Daily Suspended Sediment Load by Using Wavelet Conjunction Models , 2012 .

[19]  Yuwu Jiang,et al.  Prediction of sediment transportation in deep bay (Hong Kong) using genetic algorithm , 2010 .

[20]  N. Asselman.  Fitting and interpretation of sediment rating curves , 2000 .

[21]  Bertrand Clarke,et al.  Comparing Bayes Model Averaging and Stacking When Model Approximation Error Cannot be Ignored , 2003, J. Mach. Learn. Res..

[22]  Ozgur Kisi,et al.  Modeling discharge–sediment relationship using neural networks with artificial bee colony algorithm , 2012 .

[23]  Hikmet Kerem Cigizoglu,et al.  Suspended sediment load simulation by two artificial neural network methods using hydrometeorological data , 2007, Environ. Model. Softw..

[24]  H. Einstein,et al.  The Bed-Load Function for Sediment Transportation in Open Channel Flows , 1950 .

[25]  Bimlesh Kumar,et al.  Regression model for sediment transport problems using multi-gene symbolic genetic programming , 2014 .

[26]  Mohammad Taghi Aalami,et al.  Evaluation of total load sediment transport formulas using ANN , 2009 .

[27]  Dina Makarynska,et al.  Combining deterministic modelling with artificial neural networks for suspended sediment estimates , 2015, Appl. Soft Comput..

[28]  Mehmet Özger,et al.  Sediment load prediction by combined fuzzy logic-wavelet method , 2015 .

[29]  R. Bagnold.  An approach to the sediment transport problem from general physics , 1966 .

[30]  Oscar Castillo,et al.  Time series prediction using ensembles of ANFIS models with genetic optimization of interval type-2 and type-1 fuzzy integrators , 2014, Int. J. Hybrid Intell. Syst..

[31]  H. Kerem Cigizoglu,et al.  Suspended sediment forecasting by artificial neural networks using hydro meteorological data , 2003 .

[32]  Oscar Castillo,et al.  A new approach for time series prediction using ensembles of ANFIS models , 2012, Expert Syst. Appl..

[33]  Shingo Mabu,et al.  Ensemble learning of rule-based evolutionary algorithm using multi-layer perceptron for supporting decisions in stock trading problems , 2015, Appl. Soft Comput..

[34]  Mahdi Eftekhari,et al.  A new ensemble learning methodology based on hybridization of classifier ensemble selection approaches , 2015, Appl. Soft Comput..

[35]  Vahid Nourani,et al.  Daily suspended sediment concentration simulation using ANN and neuro-fuzzy models. , 2009, The Science of the total environment.

[36]  Ajai Singh,et al.  Comparison of Artificial Neural Network Models for Sediment Yield Prediction at Single Gauging Station of Watershed in Eastern India , 2013 .

[37]  Abdüsselam Altunkaynak,et al.  Sediment load prediction by genetic algorithms , 2009, Adv. Eng. Softw..

[38]  Sajjad Ahmad,et al.  Suspended sediment load prediction of river systems: An artificial neural network approach , 2011 .

[39]  L. Breiman.  Stacked Regressions , 1996, Machine Learning.

[40]  Ozgur Kisi,et al.  Suspended sediment estimation using neuro-fuzzy and neural network approaches/Estimation des matières en suspension par des approches neurofloues et à base de réseau de neurones , 2005 .

[41]  Ximing Cai,et al.  Prediction of regional streamflow frequency using model tree ensembles , 2014 .

[42]  Oscar Castillo,et al.  Generalized type-2 fuzzy weight adjustment for backpropagation neural networks in time series prediction , 2015, Inf. Sci..

[43]  Narendra Singh Raghuwanshi,et al.  Runoff and Sediment Yield Modeling using Artificial Neural Networks: Upper Siwane River, India , 2006 .

[44]  Chih Ted Yang,et al.  Sediment Transport in the Yellow River , 1996 .

[45]  Ozgur Kisi,et al.  Suspended sediment concentration estimation by an adaptive neuro-fuzzy and neural network approaches using hydro-meteorological data , 2009 .

[46]  Özgür Kisi,et al.  A machine code-based genetic programming for suspended sediment concentration estimation , 2010, Adv. Eng. Softw..

[47]  Jan Adamowski,et al.  Multiscale streamflow forecasting using a new Bayesian Model Average based ensemble multi-wavelet Volterra nonlinear method , 2013 .

[48]  F. Engelund,et al.  A monograph on sediment transport in alluvial streams , 1967 .

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

[50]  John R. Koza,et al.  Genetic programming - on the programming of computers by means of natural selection , 1993, Complex adaptive systems.

[51]  D. S. van Maren,et al.  Predictability of sediment transport in the Yellow River using selected transport formulas , 2008 .

[52]  H. Md. Azamathulla,et al.  ANFIS-based approach for predicting sediment transport in clean sewer , 2012, Appl. Soft Comput..

[53]  Oscar Castillo,et al.  Interval type-2 fuzzy weight adjustment for backpropagation neural networks with application in time series prediction , 2014, Inf. Sci..

[54]  Ozgur Kisi,et al.  Evolutionary fuzzy models for river suspended sediment concentration estimation. , 2009 .

[55]  Joseph Sill,et al.  Feature-Weighted Linear Stacking , 2009, ArXiv.

[56]  Tadashi Suetsugi,et al.  Comparison of regionalization approaches in parameterizing sediment rating curve in ungauged catchments for subsequent instantaneous sediment yield prediction , 2014 .