M5 Model Tree to Predict Temporal Evolution of Clear-Water Abutment Scour

Scour is a natural phenomenon that is created by the rivers streams or the flood which brings about transferring or eroding of bed materials. To have accurate and safe erosion control structures design, maximum scour depth in downstream of the structures gains specific significance. In the current study, M5 model tree as remedy data mining approaches is suggested to estimate the scour depth around the abutments. To do this, Kayaturk laboratory data (2005), with different hydraulic conditions, are used. Then, the results of M5 model were also compared with genetic programming (GP) and pervious empirical results to investigate the applicability, ability, and accuracy of these procedures. To examine the accuracy of the results yielded from the M5 and GP procedures, two performance indicators (determination coefficient (R2) and root mean square error (RMSE)) were used. The comparison test of results clearly shows that the implementation of M5 technique sounds satisfactory regarding the performance indicators (R2 = 0.944 and RMSE = 0.126) with less deviation from the numerical values. In addition, M5 tree model, by presenting relationships based on liner regression, has good capability to estimate the depth of scour abutment for engineers in practical terms.

[1]  Mohammad Ali Ghorbani,et al.  A study of friction factor formulation in pipes using artificial intelligence techniques and explicit equations , 2012 .

[2]  H. Md. Azamathulla,et al.  Linear genetic programming to scour below submerged pipeline , 2011 .

[3]  Yurdagül Kayatürk,et al.  SCOUR AND SCOUR PROTECTION AT BRIDGE ABUTMENTS , 2005 .

[4]  M. Janga Reddy,et al.  Use of Model Tree and Gene Expression Programming to Predict the Suspended Sediment Load in Rivers , 2009 .

[5]  H. Md. Azamathulla,et al.  Genetic Programming to Predict Bridge Pier Scour , 2010 .

[6]  E. Orsi,et al.  TIME EVOLUTION OF SCOUR AROUND BRIDGE ABUTMENTS , 2001 .

[7]  John R. Koza,et al.  Genetic programming - on the programming of computers by means of natural selection , 1993, Complex adaptive systems.

[8]  K. Chau,et al.  Neural network and genetic programming for modelling coastal algal blooms , 2006 .

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

[10]  António H. Cardoso,et al.  Effects of Time and Channel Geometry on Scour at Bridge Abutments , 1999 .

[11]  Dimitri P. Solomatine,et al.  Machine learning in sedimentation modelling , 2006, Neural Networks.

[12]  M. A. Gill.  Erosion of Sand Beds around Spur Dikes , 1972 .

[13]  A. Etemad-Shahidi,et al.  COMPARISON BETWEEN M5 MODEL TREE AND NEURAL NETWORKS FOR PREDICTION OF SIGNIFICANT WAVE HEIGHT IN LAKE SUPERIOR , 2009 .

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

[15]  Roland K. Price,et al.  Machine Learning Approach to Modeling Sediment Transport , 2007 .

[16]  Mustafa Gunal,et al.  Prediction of Scour Downstream of Grade-Control Structures Using Neural Networks , 2008 .

[17]  Bruce W. Melville,et al.  Clear-water scour development at bridge abutments , 2003 .

[18]  Ian H. Witten,et al.  Data mining: practical machine learning tools and techniques with Java implementations , 2002, SGMD.

[19]  U. C. Kothyari,et al.  Scour around spur dikes and bridge abutments , 2001 .

[20]  B. Melville.  Local Scour at Bridge Abutments , 1992 .

[21]  Dimitri P. Solomatine,et al.  M5 Model Trees and Neural Networks: Application to Flood Forecasting in the Upper Reach of the Huai River in China , 2004 .

[22]  H. Md. Azamathulla,et al.  Comparison between linear genetic programming and M5 tree models to predict flow discharge in compound channels , 2012, Neural Computing and Applications.

[23]  Hazi Mohammad Azamathulla,et al.  Genetic Programming for Predicting Longitudinal Dispersion Coefficients in Streams , 2011 .

[24]  W. Hager,et al.  Temporal Evolution of Clear-Water Pier and Abutment Scour , 2002 .

[25]  A. Johari,et al.  Prediction of Soil-Water Characteristic Curve Using Genetic Programming , 2006 .

[26]  E. V. Richardson,et al.  Practical Method for Scour Prediction at Bridge Piers , 1994 .

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