Acclimatizing Fast Orthogonal Search (FOS) Model for River Stream-flow Forecasting

Abstract. River stream-flow is well-thought-out as an essential element in the hydrology studies, especially for reservoir management. Forecasting river stream-flow is the key for the hydrologists in proposing certain short or long-term planning and management for water resources system. In fact, developing stream-flow forecasting models are generally categorized into two main classes; process and data-driven model. Different model techniques based on empirical methods, such as stochastic model or regression model, more recently, Artificial Intelligent (AI) models have been examined and could provide accurate stream-flow forecasting. However, AI models experienced crucial difficulty is the necessity to utilize appropriate pre-processing methods for the raw data. In addition, the AI model should be augmented with proper optimization model to adjust the model parameters to achieve the optimal accuracy. In this paper, a novel model namely; Fast Orthogonal Search (FOS) model is proposed to develop river stream-flow forecasting. FOS is basically structured for recognizing the difference equation and its functional expression model for the mapping between the model input and output. The major advantage of using FOS is the waiver of the requirement of data pre-processing and optimization model for model parameters adjustment as these procedures are performed implicitly inside FOS. In addition, pole-zero cancellation procedure within FOS process can detect the over-fitted models and avoid them. The proposed FOS method was adopted in this research to perform stream-flow forecasting model at Aswan High Dam using monthly basis for130 years. Results showed outstanding performance for stream-flow forecasting accuracy compared to other AI models developed during the last 10 years.

[1]  M. Valipour.  Long‐term runoff study using SARIMA and ARIMA models in the United States , 2015 .

[2]  Pedro Paulo Balestrassi,et al.  Design of experiments on neural network's training for nonlinear time series forecasting , 2009, Neurocomputing.

[3]  Aboelmagd Noureldin,et al.  Generalized versus non-generalized neural network model for multi-lead inflow forecasting at Aswan High Dam , 2010 .

[4]  Soroosh Sorooshian,et al.  Dual state-parameter estimation of hydrological models using ensemble Kalman filter , 2005 .

[5]  Chuntian Cheng,et al.  Combining a fuzzy optimal model with a genetic algorithm to solve multi-objective rainfall–runoff model calibration , 2002 .

[6]  Tahir Husain,et al.  Kalman filter estimation model in flood forecasting , 1985 .

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

[8]  Ahmed El-Shafie,et al.  Enhancing Inflow Forecasting Model at Aswan High Dam Utilizing Radial Basis Neural Network and Upstream Monitoring Stations Measurements , 2009 .

[9]  Chuntian Cheng,et al.  Multiple criteria rainfall–runoff model calibration using a parallel genetic algorithm in a cluster of computers / Calage multi-critères en modélisation pluie–débit par un algorithme génétique parallèle mis en œuvre par une grappe d'ordinateurs , 2005 .

[10]  R. E. Kalman,et al.  A New Approach to Linear Filtering and Prediction Problems , 2002 .

[11]  Jian Zhao,et al.  Division-based rainfall-runoff simulations with BP neural networks and Xinanjiang model , 2009, Neurocomputing.

[12]  W. L. Lane,et al.  Applied Modeling of Hydrologic Time Series , 1997 .

[13]  Ahmed El-Shafie,et al.  Dynamic versus static neural network model for rainfall forecasting at Klang River Basin, Malaysia , 2011 .

[14]  Ozgur Kisi,et al.  Applications of hybrid wavelet–Artificial Intelligence models in hydrology: A review , 2014 .

[15]  Peter A. Whigham,et al.  Modelling rainfall-runoff using genetic programming , 2001 .

[16]  Zaher Mundher Yaseen,et al.  RBFNN versus FFNN for daily river flow forecasting at Johor River, Malaysia , 2015, Neural Computing and Applications.

[17]  Edward J. Powers,et al.  Application of orthogonal-search method to Volterra modeling of nonlinear systems , 1993, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[18]  O. Kisi,et al.  Short-term and long-term streamflow forecasting using a wavelet and neuro-fuzzy conjunction model , 2010 .

[19]  R. Ibbitt,et al.  Hydrological data assimilation with the ensemble Kalman filter: Use of streamflow observations to update states in a distributed hydrological model , 2007 .

[20]  V. Jothiprakash,et al.  Multi-time-step ahead daily and hourly intermittent reservoir inflow prediction by artificial intelligent techniques using lumped and distributed data , 2012 .

[21]  KisiOzgur,et al.  Modeling rainfall-runoff process using soft computing techniques , 2013 .

[22]  O. Kisi.  Wavelet regression model for short-term streamflow forecasting. , 2010 .

[23]  J. G. Ndiritu,et al.  A hybrid conceptual–fuzzy inference streamflow modelling for the Letaba River system in South Africa , 2010 .

[24]  J. G. Ndiritu,et al.  Application of radial basis function neural networks to short-term streamflow forecasting , 2010 .

[25]  M. J. Korenberg,et al.  A robust orthogonal algorithm for system identification and time-series analysis , 1989, Biological Cybernetics.

[26]  David Labat,et al.  Recent advances in wavelet analyses: Part 1. A review of concepts , 2005 .

[27]  Aboelmagd Noureldin,et al.  GPS/INS integration utilizing dynamic neural networks for vehicular navigation , 2011, Inf. Fusion.

[28]  Ozgur Kisi,et al.  A wavelet-support vector machine conjunction model for monthly streamflow forecasting , 2011 .

[29]  Quazi K. Hassan,et al.  Development of Flow Forecasting Models in the Bow River at Calgary, Alberta, Canada , 2014 .

[30]  Peyman Abbaszadeh,et al.  A new hybrid artificial neural networks for rainfall-runoff process modeling , 2013, Neurocomputing.

[31]  Jun-Fei Qiao,et al.  A structure optimisation algorithm for feedforward neural network construction , 2013, Neurocomputing.

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

[33]  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..

[34]  S. Billings.  Nonlinear System Identification: NARMAX Methods in the Time, Frequency, and Spatio-Temporal Domains , 2013 .

[35]  Mohammad Ebrahim Banihabib,et al.  Monthly Inflow Forecasting using Autoregressive Artificial Neural Network , 2012 .

[36]  Ali Danandeh Mehr,et al.  Successive-station monthly streamflow prediction using neuro-wavelet technique , 2014, Earth Science Informatics.

[37]  Yan-Fang Sang,et al.  A review on the applications of wavelet transform in hydrology time series analysis , 2013 .

[38]  Aboelmagd Noureldin,et al.  Optimizing neuro-fuzzy modules for data fusion of vehicular navigation systems using temporal cross-validation , 2007, Eng. Appl. Artif. Intell..

[39]  Anthony J. Jakeman,et al.  An application of the Kalman filtering technique for Streamflow forecasting in the Upper Murray Basin , 2001 .

[40]  Özlem Terzi,et al.  Forecasting of monthly river flow with autoregressive modeling and data-driven techniques , 2013, Neural Computing and Applications.

[41]  Jy-Shing Wu,et al.  Artificial Neural Networks for Forecasting Watershed Runoff and Stream Flows , 2005 .

[42]  Jun Guo,et al.  Monthly streamflow forecasting based on improved support vector machine model , 2011, Expert Syst. Appl..

[43]  David R. Cox,et al.  Time Series Analysis , 2012 .

[44]  Huixin Chen,et al.  An Example of Non-Linear Time Series Flood Modelling Using the System Identification Method , 2007 .

[45]  Witold Pedrycz,et al.  Fuzzy prediction architecture using recurrent neural networks , 2009, Neurocomputing.

[46]  M. Korenberg.  Identifying nonlinear difference equation and functional expansion representations: The fast orthogonal algorithm , 2006, Annals of Biomedical Engineering.

[47]  Özgür Kisi,et al.  Modeling rainfall-runoff process using soft computing techniques , 2013, Comput. Geosci..

[48]  Zhiyong Liu,et al.  Evaluating a coupled discrete wavelet transform and support vector regression for daily and monthly streamflow forecasting , 2014 .

[49]  Kwok-wing Chau,et al.  Particle Swarm Optimization Training Algorithm for ANNs in Stage Prediction of Shing Mun River , 2006 .