Estimation of discharge with free overfall in rectangular channel using artificial intelligence models

Abstract In open channels, free overfall can be used as a flow-measuring device in various flow regimes for different shapes of channels. The aim of this paper is to accurately estimate the discharge in rectangular channels by applying four soft computing models [i.e., artificial neural network (ANN), gene expression programming (GEP), multivariate adaptive regression spline (MARS) and M5 tree model]. The variables including brink depth, roughness coefficient, channel width and channel bed slope taken from earlier published works were used as inputs for the models. Data were divided according to three different splitting scenarios, 50%–50%, 60%–40% and 75%–25%, for training-testing phases to obtain more robust evaluation of the models. The computed discharges were then compared with experimental results. In order to evaluate the accuracy of discharge estimations by ANN, GEP, MARS and M5 tree models, six statistical measures including correlation coefficient (R), mean absolute error (MAE), root mean square error (RMSE), Nash-Sutcliffe (NS), Willmott index (WI) and Legates and McCabe index (LMI) have been applied. For different training-testing scenarios, the performance of the ANN model is better than the other methods. Regarding 50%–50% training-testing scenario, ANN has the best accuracy with R, RMSE, MAE, NS, WI and LMI of 0.994, 0.004 m3/s/m, 0.002 m3/s/m, 0.986, 0.999 and 0.909 by considering all inputs.

[1]  Alastair C. Davis,et al.  Flow Measurement in Sloping Channels with Rectangular Free Overfall , 1998 .

[2]  Robert J. Keller,et al.  Flow Measurement with Trapezoidal Free Overfall , 1989 .

[3]  Amir Hossein Zaji,et al.  Gene expression programming to predict the discharge coefficient in rectangular side weirs , 2015, Appl. Soft Comput..

[4]  Shahaboddin Shamshirband,et al.  Predicting discharge coefficient of triangular labyrinth weir using extreme learning machine, artificial neural network and genetic programming , 2016, Neural Computing and Applications.

[5]  M. H. Kazeminezhad,et al.  Prediction of pile group scour in waves using support vector machines and ANN , 2011 .

[6]  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 .

[7]  Mohammad R. Chamani,et al.  FREE OVERFALL IN CHANNELS WITH DIFFERENT CROSS SECTIONS AND SUB-CRITICAL FLOW , 2006 .

[8]  Yao-ming Hong,et al.  Impact Characteristics of Free Over-Fall in Pool Zone with Upstream Bed Slope , 2014 .

[9]  J. R. Quinlan.  Learning With Continuous Classes , 1992 .

[10]  M. Ergil,et al.  Solving Trapezoidal Free Overfall by Inserting a Brink Pressure Effect into Sharp-Crested Weir Theory , 2018, Journal of Irrigation and Drainage Engineering.

[11]  Farzin Salmasi,et al.  Predicting discharge coefficient of compound broad-crested weir by using genetic programming (GP) and artificial neural network (ANN) techniques , 2013, Arabian Journal of Geosciences.

[12]  Subhasish Dey,et al.  End depth computation in inverted semicircular channels using ANNs , 2004 .

[13]  Subhasish Dey,et al.  Overfall in U-Shaped Channels , 2003 .

[14]  Özgür Kisi,et al.  Monthly long-term rainfall estimation in Central India using M5Tree, MARS, LSSVR, ANN and GEP models , 2019, Neural Computing and Applications.

[15]  Mohammad Muzzammil,et al.  Application of Neural Networks To Scour Depth Prediction at The Bridge Abutments , 2008 .

[16]  Trevor Hastie,et al.  The Elements of Statistical Learning , 2001 .

[17]  D. Solomatine,et al.  Model trees as an alternative to neural networks in rainfall—runoff modelling , 2003 .

[18]  Mahesh Pal,et al.  Estimation of Discharge and End Depth in Trapezoidal Channel by Support Vector Machines , 2007 .

[19]  K. Taylor.  Summarizing multiple aspects of model performance in a single diagram , 2001 .

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

[21]  Z. Ahmad M.Ish.  FLOW MEASUREMENTS WITH TRAPEZOIDAL FREE OVERFALL , 2001 .

[22]  Subhasish Dey,et al.  End Depth in Circular Channels , 1998 .

[23]  S. Dey.  End depth in steeply sloping rough rectangular channels , 2000 .

[24]  Subhasish Dey,et al.  Free overall in circular channels with flat base: a method of open channel flow measurement , 2002 .

[25]  Jeffrey G. Arnold,et al.  Model Evaluation Guidelines for Systematic Quantification of Accuracy in Watershed Simulations , 2007 .

[26]  Inaam A. Juma,et al.  Analysis of hydraulic characteristics for hollow semi-circular weirs using artificial neural networks , 2014 .

[27]  Z. Ahmad.  Flow measurement using free overfall in inverted semi-circular channel , 2005 .

[28]  D. Legates,et al.  Evaluating the use of “goodness‐of‐fit” Measures in hydrologic and hydroclimatic model validation , 1999 .

[29]  C. Willmott.  ON THE VALIDATION OF MODELS , 1981 .

[30]  Vito Ferro,et al.  Theoretical End-Depth-Discharge Relationship for Free Overfall , 1999 .

[31]  Mark Sterling,et al.  Free overfalls in flat-based circular and U-shaped channels , 2011 .

[32]  Mahesh Pal,et al.  Prediction of the end-depth ratio and discharge in semi-circular and circular shaped channels using support vector machines , 2006 .

[33]  O. Kisi,et al.  Modelling long‐term monthly temperatures by several data‐driven methods using geographical inputs , 2015 .

[34]  Chao Zhai,et al.  Closure of "End Depth-Discharge Relation at Free Overfall of Trapezoidal Channels" , 2004 .

[35]  Abbas Parsaie,et al.  Applications of soft computing techniques for prediction of energy dissipation on stepped spillways , 2016, Neural Computing and Applications.

[36]  Nor Azazi Zakaria,et al.  Prediction of scour below submerged pipeline crossing a river using ANN. , 2011, Water science and technology : a journal of the International Association on Water Pollution Research.

[37]  Subhasish Dey,et al.  Free overall in open channels: state-of-the-art review , 2002 .

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

[39]  Dimitri P. Solomatine,et al.  Neural networks and M5 model trees in modelling water level-discharge relationship , 2005, Neurocomputing.

[40]  Özgür Kisi,et al.  Survey of different data-intelligent modeling strategies for forecasting air temperature using geographic information as model predictors , 2018, Comput. Electron. Agric..

[41]  Rodney Day,et al.  Prediction of scour depth at culvert outlets using neural networks , 2001 .

[42]  Donald W. Knight,et al.  Prediction of end-depth ratio in open channels using genetic programming , 2010 .

[43]  Z. Ahmad.  Quasi-Theoretical End-Depth-Discharge Relationship for Rectangular Channels , 2003 .

[44]  H. Md. Azamathulla,et al.  GEP to predict characteristics of a hydraulic jump over a rough bed , 2016 .

[45]  H. Md. Azamathulla,et al.  Alternative neural networks to estimate the scour below spillways , 2008, Adv. Eng. Softw..

[46]  Z. Ahmad.  FLOW MEASUREMENTS WITH TRAPEZOIDAL FREE OVERFALL , 2001 .

[47]  Hsueh-Chun Lin,et al.  Using Artificial Neuron Network on the Impact Characteristics Analysis of Free Overfall Flow , 2011 .

[48]  Willi H. Hager,et al.  Hydraulics of Plane Free Overfall , 1983 .

[49]  Amir Hossein Zaji,et al.  Performance evaluation of two different neural network and particle swarm optimization methods for prediction of discharge capacity of modified triangular side weirs , 2014 .

[50]  Jerome H. Friedman.  Multivariate adaptive regression splines (with discussion) , 1991 .

[51]  Fevzi Onen,et al.  Prediction of Scour at a Side-Weir with GEP, ANN and Regression Models , 2014 .

[52]  Mahesh Pal,et al.  M5 model tree based modelling of reference evapotranspiration , 2009 .

[53]  Jian-Hao Hong,et al.  Prediction of contraction scour using ANN and GA , 2016 .

[54]  S. Mahapatra,et al.  A neural network approach for prediction of discharge in straight compound open channel flow , 2011 .

[55]  Francisco Javier de Cos Juez,et al.  Bankruptcy forecasting: A hybrid approach using Fuzzy c-means clustering and Multivariate Adaptive Regression Splines (MARS) , 2011, Expert Syst. Appl..

[56]  A. M. Ger,et al.  Use of Brink Depth in Discharge Measurement , 2008 .

[57]  H. Md. Azamathulla,et al.  Flow discharge prediction in compound channels using linear genetic programming , 2012 .

[58]  Saeid Mehdizadeh,et al.  New Approaches for Estimation of Monthly Rainfall Based on GEP-ARCH and ANN-ARCH Hybrid Models , 2017, Water Resources Management.

[59]  Cort J. Willmott,et al.  On the Evaluation of Model Performance in Physical Geography , 1984 .