Bed material load estimation in channels using machine learning and meta-heuristic methods

This study is trying to develop an alternative approach to the issues of sediment transport simulation. A machine learning method, named least square support vector regression (LSSVR) and a meta-heuristic approach, called particle swarm optimization (PSO) algorithm are used to estimate bed material load transport rate. PSO algorithm is utilized to calibrate the parameters involved in the model to facilitate a desirable simulation by LSSVR. Implementing on a set of laboratory and field data, the model is capable of performing more satisfactorily in comparison to candidate traditional methods. Similarly, the proposed method has a better performance than a specific version of decision tree method. To enhance the model, the variables are scaled in logarithmic form, leading to an improvement in the results. Thus, the proposed model can be an efficient alternative to conventional approaches for the simulation of bed material load transport rates providing comparable accuracy.

[1]  W. Graf.  Hydraulics of Sediment Transport , 1984 .

[2]  R. Soulsby.  Dynamics of marine sands , 1997 .

[3]  Riccardo Poli,et al.  Particle swarm optimization , 1995, Swarm Intelligence.

[4]  DESIGN OF PLANE SEDIMENT BED CHANNELS AT CRITICAL CONDITION , 2006 .

[5]  Mac McKee,et al.  Multi-time scale stream flow predictions: The support vector machines approach , 2006 .

[6]  Dawei Han,et al.  Assessment of input variables determination on the SVM model performance using PCA, Gamma test, and forward selection techniques for monthly stream flow prediction , 2011 .

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

[8]  Peter Ackers,et al.  Sediment Transport: New Approach and Analysis , 1973 .

[9]  Nasser Talebbeydokhti,et al.  Daily Discharge Forecasting Using Least Square Support Vector Regression and Regression Tree , 2015 .

[10]  James Kennedy,et al.  Particle swarm optimization , 2002, Proceedings of ICNN'95 - International Conference on Neural Networks.

[11]  A. Shields,et al.  Application of similarity principles and turbulence research to bed-load movement , 1936 .

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

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

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

[15]  Zhiwei Huang,et al.  Flood disaster loss comprehensive evaluation model based on optimization support vector machine , 2010, Expert Syst. Appl..

[16]  A. Agarwal,et al.  Application and analysis of support vector machine based simulation for runoff and sediment yield , 2009 .

[17]  M. Çimen,et al.  Estimation of daily suspended sediments using support vector machines , 2008 .

[18]  Johan A. K. Suykens,et al.  Least Squares Support Vector Machines , 2002 .

[19]  O. Kisi,et al.  Suspended sediment modeling using genetic programming and soft computing techniques , 2012 .

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

[21]  Barry Boehm,et al.  Reduced-parameter modeling for cost estimation models , 2006 .

[22]  Siti Mariyam Shamsuddin,et al.  Particle Swarm Optimization: Technique, System and Challenges , 2011 .

[23]  V. Vapnik.  Pattern recognition using generalized portrait method , 1963 .

[24]  Chun Kiat Chang,et al.  Machine Learning Approach to Predict Sediment Load – A Case Study , 2010 .

[25]  F. Engelund,et al.  A monograph on sediment transport in alluvial streams , 1967 .

[26]  R. Müller,et al.  Formulas for Bed-Load transport , 1948 .

[27]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[28]  Yue Shi,et al.  A modified particle swarm optimizer , 1998, 1998 IEEE International Conference on Evolutionary Computation Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98TH8360).

[29]  G. P. Williams.  Flume width and water depth effects in sediment-transport experiments , 1970 .

[30]  Dawei Han,et al.  Flood forecasting using support vector machines , 2007 .

[31]  M. H. Kazeminezhad,et al.  AN ALTERNATIVE APPROACH FOR INVESTIGATION OF THE WAVE-INDUCED SCOUR AROUND PIPELINES , 2010 .

[32]  안정규,et al.  Sediment Transport Theory and Practice , 2012 .

[33]  H. Nagy,et al.  Prediction of Sediment Load Concentration in Rivers using Artificial Neural Network Model , 2002 .

[34]  Shie-Yui Liong,et al.  Rainfall and runoff forecasting with SSA-SVM approach , 2001 .

[35]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[36]  Alexander J. Smola,et al.  Regression estimation with support vector learning machines , 1996 .

[37]  Ian H. Witten,et al.  Induction of model trees for predicting continuous classes , 1996 .

[38]  Zaher Mundher Yaseen,et al.  Past, present and prospect of an Artificial Intelligence (AI) based model for sediment transport prediction , 2016 .

[39]  William R. Brownlie,et al.  Compilation of alluvial channel data : Laboratory and field , 1981 .

[40]  Chih Ted Yang,et al.  Sediment transport : theory and practice / Chih Ted Yang , 1995 .

[41]  Sharad K. Jain,et al.  Development of Integrated Sediment Rating Curves Using ANNs , 2001 .

[42]  R. Bagnold.  An approach to the sediment transport problem from general physics , 1966 .

[43]  H. A. Einstein,et al.  Formulas for the Transportation of Bed Load , 1942 .

[44]  Chih Ted Yang,et al.  Unit Stream Power and Sediment Transport , 1972 .

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