River flow time series using least squares support vector machines

Abstract. This paper proposes a novel hybrid forecasting model known as GLSSVM, which combines the group method of data handling (GMDH) and the least squares support vector machine (LSSVM). The GMDH is used to determine the useful input variables which work as the time series forecasting for the LSSVM model. Monthly river flow data from two stations, the Selangor and Bernam rivers in Selangor state of Peninsular Malaysia were taken into consideration in the development of this hybrid model. The performance of this model was compared with the conventional artificial neural network (ANN) models, Autoregressive Integrated Moving Average (ARIMA), GMDH and LSSVM models using the long term observations of monthly river flow discharge. The root mean square error (RMSE) and coefficient of correlation (R) are used to evaluate the models' performances. In both cases, the new hybrid model has been found to provide more accurate flow forecasts compared to the other models. The results of the comparison indicate that the new hybrid model is a useful tool and a promising new method for river flow forecasting.

[1]  Guoqiang Peter Zhang,et al.  Time series forecasting using a hybrid ARIMA and neural network model , 2003, Neurocomputing.

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

[3]  Johan A. K. Suykens,et al.  Financial time series prediction using least squares support vector machines within the evidence framework , 2001, IEEE Trans. Neural Networks.

[4]  F. S. Wong,et al.  Time series forecasting using backpropagation neural networks , 1991, Neurocomputing.

[5]  R. Modarres.  Streamflow drought time series forecasting , 2007 .

[6]  M. Erol Keskin,et al.  Artificial Models for Interbasin Flow Prediction in Southern Turkey , 2009 .

[7]  Guoping Xia,et al.  An investigation and comparison of artificial neural network and time series models for Chinese food grain price forecasting , 2007, Neurocomputing.

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

[9]  Ajith Abraham,et al.  SELF-ORGANIZING DATA MINING FOR WEATHER FORECASTING , 2007 .

[10]  Mac McKee,et al.  Multi-time scale stream flow predictions: The support vector machines approach , 2006 .

[11]  Paulin Coulibaly,et al.  Comparison of neural network methods for infilling missing daily weather records , 2007 .

[12]  Nitin K. Tripathi,et al.  An artificial neural network model for rainfall forecasting in Bangkok, Thailand , 2008 .

[13]  Michael Y. Hu,et al.  Forecasting with artificial neural networks: The state of the art , 1997 .

[14]  T.H.M. Rientjes.  Inverse modelling of the rainfall-runoff relation: A multi objective model calibration approach , 2004 .

[15]  Kuan-Yu Chen,et al.  A hybrid SARIMA and support vector machines in forecasting the production values of the machinery industry in Taiwan , 2007, Expert Syst. Appl..

[16]  I-Fan Chang,et al.  Support vector regression for real-time flood stage forecasting , 2006 .

[17]  Z. Rao,et al.  A hybrid neural networks and numerical models approach for predicting groundwater abstraction impacts , 2008 .

[18]  Amir F. Atiya,et al.  A comparison between neural-network forecasting techniques-case study: river flow forecasting , 1999, IEEE Trans. Neural Networks.

[19]  P. Gelder,et al.  Forecasting daily streamflow using hybrid ANN models , 2006 .

[20]  F. Tay,et al.  Application of support vector machines in financial time series forecasting , 2001 .

[21]  Héctor Pomares,et al.  Soft-computing techniques and ARMA model for time series prediction , 2008, Neurocomputing.

[22]  Jwan N. Hassan,et al.  Khabur River Flow Modeling using Artificial Neural Networks , 2005 .

[23]  M. Firat,et al.  Comparison of Artificial Intelligence Techniques for river flow forecasting , 2008 .

[24]  Muhsin Tunay Gençoglu,et al.  Prediction of flashover voltage of insulators using least squares support vector machines , 2009, Expert Syst. Appl..

[25]  Gunnar Rätsch,et al.  Using support vector machines for time series prediction , 1999 .

[26]  K. Raahemifar,et al.  On Efficient Tuning of LS-SVM Hyper-Parameters in Short-Term Load Forecasting: A Comparative Study , 2007, 2007 IEEE Power Engineering Society General Meeting.

[27]  A. G. Ivakhnenko,et al.  Polynomial Theory of Complex Systems , 1971, IEEE Trans. Syst. Man Cybern..

[28]  Chuntian Cheng,et al.  A comparison of performance of several artificial intelligence , 2009 .

[29]  Wenrui Huang,et al.  Forecasting flows in Apalachicola River using neural networks , 2004 .

[30]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[31]  Gwilym M. Jenkins,et al.  Time series analysis, forecasting and control , 1971 .

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

[33]  T. Rientjes,et al.  Constraints of artificial neural networks for rainfall-runoff modelling: trade-offs in hydrological state representation and model evaluation , 2005 .

[34]  Yuanli Cai,et al.  Hybrid Fuzzy Neural Network Control for Complex Industrial Process , 2006 .

[35]  A. Agarwal,et al.  Application and analysis of support vector machine based simulation for runoff and sediment yield , 2009 .

[36]  Y. Wang,et al.  Analysis and modeling of multivariate chaotic time series based on neural network , 2009, Expert Syst. Appl..

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

[38]  Fi-John Chang,et al.  A self-organization algorithm for real-time flood forecast , 1999 .

[39]  Ozgur Kisi,et al.  River Flow Modeling Using Artificial Neural Networks , 2004 .

[40]  Michael Y. Hu,et al.  A simulation study of artificial neural networks for nonlinear time-series forecasting , 2001, Comput. Oper. Res..

[41]  Nader Nariman-zadeh,et al.  Polynomial modelling of explosive compaction process of metallic powders using GMDH-type neural networks and singular value decomposition , 2002 .

[42]  Ozgur Kisi,et al.  Wavelet regression model as an alternative to neural networks for monthly streamflow forecasting , 2009 .

[43]  Richard A. Davis,et al.  Introduction to time series and forecasting , 1998 .

[44]  Ajith Abraham,et al.  A neuro-fuzzy approach for modelling electricity demand in Victoria , 2001, Appl. Soft Comput..

[45]  James D. Hamilton.  Time Series Analysis , 1994 .

[46]  Kadri Yürekli,et al.  Prediction of Daily Maximum Streamflow Based on Stochastic Approaches , 2012 .

[47]  C. Fernández,et al.  Streamflow drought time series forecasting: a case study in a small watershed in North West Spain , 2009 .

[48]  Wei Guo,et al.  Robust mobile geo-location algorithm based on LS-SVM , 2005, IEEE Transactions on Vehicular Technology.

[49]  K. Chau,et al.  Predicting monthly streamflow using data‐driven models coupled with data‐preprocessing techniques , 2009 .

[50]  Johan A. K. Suykens,et al.  Least Squares Support Vector Machine Classifiers , 1999, Neural Processing Letters.

[51]  H. Tamura,et al.  Heuristics free group method of data handling algorithm of generating optimal partial polynomials with application to air pollution prediction , 1980 .

[52]  O. Kisi.  River flow forecasting and estimation using different artificial neural network techniques , 2008 .

[53]  Dulakshi S. K. Karunasinghe,et al.  Chaotic time series prediction with a global model: Artificial neural network , 2006 .

[54]  Haifeng Wang,et al.  Comparison of SVM and LS-SVM for Regression , 2005, 2005 International Conference on Neural Networks and Brain.

[55]  Jan Adamowski,et al.  Development of a coupled wavelet transform and neural network method for flow forecasting of non-perennial rivers in semi-arid watersheds. , 2010 .

[56]  Kunio Watanabe,et al.  Daily groundwater level fluctuation forecasting using soft computing technique , 2007 .

[57]  Francesco Camastra,et al.  Neural Short-Term Prediction Based on Dynamics Reconstruction , 1999, Neural Processing Letters.

[58]  Stan Openshaw,et al.  A hybrid multi-model approach to river level forecasting , 2000 .

[59]  Mahmut Firat,et al.  Monthly river flow forecasting by an adaptive neuro‐fuzzy inference system , 2009 .

[60]  Shie-Yui Liong,et al.  FLOOD STAGE FORECASTING WITH SUPPORT VECTOR MACHINES 1 , 2002 .

[61]  Paul A. Fishwick,et al.  Feedforward Neural Nets as Models for Time Series Forecasting , 1993, INFORMS J. Comput..

[62]  R. Lippmann,et al.  An introduction to computing with neural nets , 1987, IEEE ASSP Magazine.

[63]  Lutgarde M. C. Buydens,et al.  Using support vector machines for time series prediction , 2003 .

[64]  Eduardo A. Varas,et al.  Artificial neural networks for streamflow prediction , 2002 .

[65]  王正華,et al.  A hybrid SARIMA and support vector machines in forecasting the production values of the machinery industry in Taiwan , 2007 .

[66]  Amit Kumar,et al.  An evaluation of artificial neural network technique for the determination of infiltration model parameters , 2006, Appl. Soft Comput..

[67]  Cheng-Jian Lin,et al.  Using Least Squares Support Vector Machines for Adaptive Communication Channel Equalization , 2005 .

[68]  Dimitri P. Solomatine,et al.  Model Induction with Support Vector Machines: Introduction and Applications , 2001 .

[69]  Godfrey C. Onwubolu,et al.  Design of hybrid differential evolution and group method of data handling networks for modeling and prediction , 2008, Inf. Sci..

[70]  Sydney Nsw,et al.  Self-Organizing Polynomial Neural Network for Modelling Complex Hydrological Processes , 2006 .

[71]  Johan A. K. Suykens,et al.  Least Squares Support Vector Machines , 2002 .

[72]  Jiang Liangzhong,et al.  Water Quality Prediction Using LS-SVM and Particle Swarm Optimization , 2009, WKDD.

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

[74]  Mahmud Güngör,et al.  River flow estimation using adaptive neuro fuzzy inference system , 2007, Math. Comput. Simul..

[75]  Chuntian Cheng,et al.  Using support vector machines for long-term discharge prediction , 2006 .

[76]  Xin Feng,et al.  A New Methodology For Emergent System Identification Using Particle Swarm Optimization (PSO) And The Group Method Data Handling (GMDH) , 2002, GECCO.

[77]  G. Corzo,et al.  River flow forecasting with artificial neural networks using satellite observed precipitation pre-processed with flow length and travel time information: case study of the Ganges river basin , 2009 .

[78]  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..

[79]  Chao Ton Su,et al.  Combining time series and neural network approaches for modeling reliability growth , 1997 .

[80]  J. K. Vrijling,et al.  IMPROVING DAILY STREAM FLOW FORECASTS BY COMBINING ARMA AND ANN MODELS , 2006 .

[81]  D. S. Jeng,et al.  Self-organizing polynomial neural network for modelling complex hydrological processes , 2005 .

[82]  Suh Young Kang,et al.  An investigation of the use of feedforward neural networks for forecasting , 1992 .

[83]  P. W. Strike,et al.  Forecasting and control , 1991 .

[84]  Lixia Liu,et al.  Exchange Rates Forecasting with Least Squares Support Vector Machine , 2008, 2008 International Conference on Computer Science and Software Engineering.

[85]  Rao S. Govindaraju,et al.  Prediction of watershed runoff using Bayesian concepts and modular neural networks , 2000 .