Discharge forecasting using an Online Sequential Extreme Learning Machine (OS-ELM) model: A case study in Neckar River, Germany

Abstract Flood forecasting in natural rivers is a complicated procedure because of uncertainties involved in the behaviour of the flood wave movement. This leads to complex problems in hydrological modelling which have been widely solved by soft computing techniques. In real time flood forecasting, data generation is continuous and hence there is a need to update the developed mapping equation frequently which increases the computational burden. In short term flood forecasting where the accuracy of flood peak value and time to peak are critical, frequent model updating is unavoidable. In this paper, we studied a new technique: Online Sequential Extreme Learning Machine (OS-ELM) which is capable of updating the model equation based on new data entry without much increase in computational cost. The OS-ELM was explored for use in flood forecasting on the Neckar River, Germany. The reach was characterized by significant lateral flow that affected the flood wave formation. Hourly data from 1999–2000 at the upstream section of Rottweil were used to forecast flooding at the Oberndorf downstream site with a lead time of 1–6 h. Model performance was assessed by using three evaluation measures: the coefficient of determination ( R 2 ), the Nash-Sutcliffe efficiency coefficient (NS) and the root mean squared error (RMSE). The performance of the OS-ELM was comparable to those of other widely used Artificial Intelligence (AI) techniques like support vector machines (SVM), Artificial Neural Networks (ANN) and Genetic Programming (GP). The frequent updating of the model in OS-ELM gave a closer reproduction of flood events and peak values with minimum error compared to SVM, ANN and GP.

[1]  K. P. Sudheer,et al.  Rainfall‐runoff modeling through hybrid intelligent system , 2007 .

[2]  C. L. Wu,et al.  Methods to improve neural network performance in daily flows prediction , 2009 .

[3]  Shou-yu Chen,et al.  Improved annual rainfall-runoff forecasting using PSO-SVM model based on EEMD , 2013 .

[4]  Paresh Chandra Deka,et al.  Support vector machine applications in the field of hydrology: A review , 2014, Appl. Soft Comput..

[5]  R. Sahay,et al.  Predicting Monsoon Floods in Rivers Embedding Wavelet Transform, Genetic Algorithm and Neural Network , 2013, Water Resources Management.

[6]  Honey Badrzadeh,et al.  Hourly runoff forecasting for flood risk management: Application of various computational intelligence models , 2015 .

[7]  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..

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

[9]  O. Kisi.  Neural Networks and Wavelet Conjunction Model for Intermittent Streamflow Forecasting , 2009 .

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

[11]  K. Gupta,et al.  SVM-Based Model for Short-Term Rainfall Forecasts at a Local Scale in the Mumbai Urban Area, India , 2014 .

[12]  P. Young,et al.  Data assimilation and adaptive forecasting of water levels in the river Severn catchment, United Kingdom , 2006 .

[13]  M. Perumal,et al.  A fully mass conservative variable parameter McCarthy-Muskingum method: Theory and verification , 2013 .

[14]  Chuntian Cheng,et al.  A comparison of performance of several artificial intelligence methods for forecasting monthly discharge time series , 2009 .

[15]  S. Liong,et al.  EC-SVM approach for real-time hydrologic forecasting , 2004 .

[16]  A. Arabi Yazdi,et al.  Flood flow forecasting using ANN, ANFIS and regression models , 2013, Neural Computing and Applications.

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

[18]  Bijaya K. Panigrahi,et al.  An integrated wavelet-support vector machine for groundwater level prediction in Visakhapatnam, India , 2014, Neurocomputing.

[19]  P. Willems,et al.  Developing tailored climate change scenarios for hydrological impact assessments , 2014 .

[20]  Vladan Babovic,et al.  Declarative and Preferential Bias in GP-based Scientific Discovery , 2002, Genetic Programming and Evolvable Machines.

[21]  Honey Badrzadeh,et al.  Impact of multi-resolution analysis of artificial intelligence models inputs on multi-step ahead river flow forecasting , 2013 .

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

[23]  Pao-Shan Yu,et al.  Real-time probabilistic forecasting of flood stages , 2007 .

[24]  Yen-Ming Chiang,et al.  Multi-step-ahead neural networks for flood forecasting , 2007 .

[25]  Chee Kheong Siew,et al.  Extreme learning machine: Theory and applications , 2006, Neurocomputing.

[26]  Asaad Y. Shamseldin,et al.  Application of surrogate artificial intelligent models for real‐time flood routing , 2013 .

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

[28]  Ezio Todini,et al.  An operational decision support system for flood risk mapping, forecasting and management , 1999 .

[29]  Pei Li,et al.  Forecasting Model of Coal Mine Water Inrush Based on Extreme Learning Machine , 2013 .

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

[31]  Peter A. Whigham,et al.  Time series modeling using genetic programming: an application to rainfall-runoff models , 1999 .

[32]  Kwok-wing Chau,et al.  Data-driven input variable selection for rainfall-runoff modeling using binary-coded particle swarm optimization and Extreme Learning Machines , 2015 .

[33]  Muthiah Perumal,et al.  FIELD APPLICATIONS OF A VARIABLE-PARAMETER MUSKINGUM METHOD , 2001 .

[34]  C. W. Tong,et al.  RETRACTED ARTICLE: Application of extreme learning machine for estimation of wind speed distribution , 2016, Climate Dynamics.

[35]  T. O'donnell.  A direct three-parameter Muskingum procedure incorporating lateral inflow / Methode directe de Muskingum a trois parametres avec prise en compte des apports lateraux , 1985 .

[36]  Ozgur Kisi,et al.  Precipitation Forecasting Using Wavelet-Genetic Programming and Wavelet-Neuro-Fuzzy Conjunction Models , 2011 .

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

[38]  Peter J. Webster,et al.  Meteorology: Improve weather forecasts for the developing world , 2013, Nature.

[39]  Aranildo R. Lima,et al.  Nonlinear regression in environmental sciences using extreme learning machines: A comparative evaluation , 2015, Environ. Model. Softw..

[40]  Francesco Piazza,et al.  Online sequential extreme learning machine in nonstationary environments , 2013, Neurocomputing.

[41]  B. Yadav,et al.  Variable parameter McCarthy–Muskingum routing method considering lateral flow , 2015 .

[42]  T. Gan,et al.  Regional Flood Frequency Analysis using Support Vector Regression under historical and future climate , 2016 .

[43]  H. Faulkner,et al.  Simulation of summer storms of differing recurrence intervals in a semiarid environment using a kinematic routing scheme , 1992 .

[44]  J. Adamowski.  Development of a short-term river flood forecasting method for snowmelt driven floods based on wavelet and cross-wavelet analysis , 2008 .

[45]  Gene H. Golub,et al.  Matrix computations , 1983 .

[46]  Narasimhan Sundararajan,et al.  A Fast and Accurate Online Sequential Learning Algorithm for Feedforward Networks , 2006, IEEE Transactions on Neural Networks.

[47]  K. P. Sudheer,et al.  Potential application of wavelet neural network ensemble to forecast streamflow for flood management , 2016 .

[48]  N. Chang,et al.  Short-term streamflow forecasting with global climate change implications – A comparative study between genetic programming and neural network models , 2008 .

[49]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[50]  Ashu Jain,et al.  A comparative analysis of training methods for artificial neural network rainfall-runoff models , 2006, Appl. Soft Comput..

[51]  Kwok-wing Chau,et al.  Improving Forecasting Accuracy of Annual Runoff Time Series Using ARIMA Based on EEMD Decomposition , 2015, Water Resources Management.

[52]  Yong Yu,et al.  Sales forecasting using extreme learning machine with applications in fashion retailing , 2008, Decis. Support Syst..

[53]  K. Chau,et al.  Modeling of groundwater level fluctuations using dendrochronology in alluvial aquifers , 2015 .

[54]  Min Han,et al.  Online sequential extreme learning machine with kernels for nonstationary time series prediction , 2014, Neurocomputing.

[55]  K. P. Sudheer,et al.  Short‐term flood forecasting with a neurofuzzy model , 2005 .

[56]  J. Nash,et al.  River flow forecasting through conceptual models part I — A discussion of principles☆ , 1970 .

[57]  Zong Woo Geem,et al.  A new nonlinear Muskingum flood routing model incorporating lateral flow , 2015 .

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

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

[60]  Keith Beven,et al.  A manifesto for the equifinality thesis , 2006 .

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

[62]  S. Uhlenbrook,et al.  Prediction uncertainty of conceptual rainfall-runoff models caused by problems in identifying model parameters and structure , 1999 .

[63]  C. W. Chan,et al.  Modelling of river discharges and rainfall using radial basis function networks based on support vector regression , 2003, Int. J. Syst. Sci..

[64]  B. K. Panigrahi,et al.  Development of an artificial neural network based multi-model ensemble to estimate the northeast monsoon rainfall over south peninsular India: an application of extreme learning machine , 2014, Climate Dynamics.

[65]  K. Chau,et al.  Prediction of rainfall time series using modular artificial neural networks coupled with data-preprocessing techniques , 2010 .

[66]  Henrik Madsen,et al.  Adaptive state updating in real-time river flow forecasting—a combined filtering and error forecasting procedure , 2005 .

[67]  Ming J. Zuo,et al.  Support vector machine based data processing algorithm for wear degree classification of slurry pump systems , 2010 .

[68]  Robert J. Moore,et al.  Risk assessment and drought management in the Thames basin , 1989 .

[69]  K. Loague,et al.  Physics‐based hydrologic response simulation: platinum bridge, 1958 Edsel, or useful tool , 2004 .

[70]  Jalal Shiri,et al.  Forecasting daily stream flows using artificial intelligence approaches , 2012 .

[71]  David E. Goldberg,et al.  Genetic algorithms and Machine Learning , 1988, Machine Learning.

[72]  Cândida Ferreira,et al.  Gene Expression Programming: Mathematical Modeling by an Artificial Intelligence , 2014, Studies in Computational Intelligence.

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

[74]  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 .

[75]  Aranildo R. Lima,et al.  Forecasting daily streamflow using online sequential extreme learning machines , 2016 .

[76]  Muthiah Perumal.  Multilinear muskingum flood routing method , 1992 .

[77]  T. Das.  The impact of spatial variability of precipitation on the predictive uncertainty of hydrological models , 2006 .

[78]  C. L. Wu,et al.  Rainfall–runoff modeling using artificial neural network coupled with singular spectrum analysis , 2011 .