Performance Assessment of the Linear, Nonlinear and Nonparametric Data Driven Models in River Flow Forecasting

In recent years, the data-driven modeling techniques have gained more attention in hydrology and water resources studies. River runoff estimation and forecasting are one of the research fields that these techniques have several applications in them. In the current study, four common data-driven modeling techniques including multiple linear regression, K-nearest neighbors, artificial neural networks and adaptive neuro-fuzzy inference systems have been used to form runoff forecasting models and then their results have been evaluated. Also, effects of using of some different scenarios for selecting predictor variables have been studied. It is evident from the results that using flow data of one or two month ago in the predictor variables dataset can improve accuracy of results. In addition, comparison of general performances of the modeling techniques shows superiority of results of KNN models among the studied models. Among selected models of the different techniques, the selected KNN model presented best performance with a linear correlation coefficient equal to 0.84 between observed flow data and predicted values and a RMSE equal to 2.64.

[1]  Armando Brath,et al.  Neural networks and non-parametric methods for improving real-time flood forecasting through conceptual hydrological models , 2002 .

[2]  Zhu Jiang,et al.  Discharge estimation based on machine learning , 2013 .

[3]  S. Araghinejad,et al.  Development of a Nonparametric Model for Multivariate Hydrological Monthly Series Simulation Considering Climate Change Impacts , 2015, Water Resources Management.

[4]  Soichi Nishiyama,et al.  A comparative study of artificial neural networks and neuro-fuzzy in continuous modeling of the daily and hourly behaviour of runoff , 2007 .

[5]  R. Abrahart,et al.  Comparing neural network and autoregressive moving average techniques for the provision of continuous river flow forecasts in two contrasting catchments , 2000 .

[6]  Balaji Rajagopalan,et al.  Modified K-NN Model for Stochastic Streamflow Simulation , 2006 .

[7]  R. Mehrotra,et al.  Conditional resampling of hydrologic time series using multiple predictor variables: A K-nearest neighbour approach , 2006 .

[8]  L. Chua,et al.  Influence of lag time on event-based rainfall–runoff modeling using the data driven approach , 2012 .

[9]  Tommy S. W. Wong,et al.  Evaluation of rainfall and discharge inputs used by Adaptive Network-based Fuzzy Inference Systems (ANFIS) in rainfall–runoff modeling , 2010 .

[10]  Robert LIN,et al.  NOTE ON FUZZY SETS , 2014 .

[11]  Avi Ostfeld,et al.  Data-driven modelling: some past experiences and new approaches , 2008 .

[12]  S. Yakowitz,et al.  Nearest‐neighbor methods for nonparametric rainfall‐runoff forecasting , 1987 .

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

[14]  Dimitri Solomatine,et al.  Experimental investigation of the predictive capabilities of data driven modeling techniques in hydrology - Part 1: Concepts and methodology , 2009 .

[15]  Narendra Singh Raghuwanshi,et al.  Flood Forecasting Using ANN, Neuro-Fuzzy, and Neuro-GA Models , 2009 .

[16]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[17]  Young-Oh Kim,et al.  Rainfall‐runoff models using artificial neural networks for ensemble streamflow prediction , 2005 .

[18]  Esther-Lydia Silva-Ramírez,et al.  Single imputation with multilayer perceptron and multiple imputation combining multilayer perceptron and k-nearest neighbours for monotone patterns , 2015, Appl. Soft Comput..

[19]  Michio Sugeno,et al.  Fuzzy identification of systems and its applications to modeling and control , 1985, IEEE Transactions on Systems, Man, and Cybernetics.

[20]  Amin Elshorbagy,et al.  Cluster-Based Hydrologic Prediction Using Genetic Algorithm-Trained Neural Networks , 2007 .

[21]  Taesam Lee,et al.  Nonparametric Simulation of Single-Site Seasonal Streamflows , 2010 .

[22]  Dimitri Solomatine,et al.  Experimental investigation of the predictive capabilities of data driven modeling techniques in hydrology - Part 2: Application , 2009 .

[23]  Durga Lal Shrestha,et al.  Instance‐based learning compared to other data‐driven methods in hydrological forecasting , 2008 .

[24]  Upmanu Lall,et al.  A Nearest Neighbor Bootstrap For Resampling Hydrologic Time Series , 1996 .

[25]  Rameswar Panda,et al.  Application of neural network and adaptive neuro-fuzzy inference systems for river flow prediction , 2009 .

[26]  Vinay Agrawal,et al.  Soft Computing Approach for Rainfall-runoff Modelling: A Review , 2015 .

[27]  Peter Bajcsy,et al.  Hydroinformatics: Data Integrative Approaches in Computation, Analysis, and Modeling , 2005 .

[28]  Taha B. M. J. Ouarda,et al.  Long‐term prediction of precipitation and hydrologic extremes with nonstationary oscillation processes , 2010 .

[29]  Lloyd H.C. Chua,et al.  Runoff forecasting using a Takagi-Sugeno neuro-fuzzy model with online learning , 2013 .

[30]  Yong-Huang Lin,et al.  The strategy of building a flood forecast model by neuro‐fuzzy network , 2006 .

[31]  T. Ouarda,et al.  Identification of model order and number of neighbors for k-nearest neighbor resampling , 2011 .

[32]  Vahid Nourani,et al.  Using self-organizing maps and wavelet transforms for space–time pre-processing of satellite precipitation and runoff data in neural network based rainfall–runoff modeling , 2013 .

[33]  A. W. Minns,et al.  Artificial neural networks as rainfall-runoff models , 1996 .

[34]  Jyh-Shing Roger Jang,et al.  ANFIS: adaptive-network-based fuzzy inference system , 1993, IEEE Trans. Syst. Man Cybern..

[35]  Robert J. Abrahart,et al.  Neural network rainfall-runoff forecasting based on continuous resampling , 2003 .

[36]  Miguel A. Mariño,et al.  A self-tuning ANN model for simulation and forecasting of surface flows , 2016, Water Resources Management.

[37]  Dillip K. Ghose,et al.  Prediction and optimization of runoff via ANFIS and GA , 2013 .

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