Sparse kernel regression technique for self-cleansing channel design

Abstract The application of a robust learning technique is inevitable in the development of a self-cleansing sediment transport model. This study addresses this problem and advocates the use of sparse kernel regression (SKR) technique to design a self-cleaning model. The SKR approach is a regression technique operating in the kernel space which also benefits from the desirable properties of a sparse solution. In order to develop a model applicable to a wide range of channel characteristics, five different experimental data sets from 14 different channels are utilized in this study. In this context, the efficacy of the SKR model is compared against the support vector regression (SVR) approach along with several other methods from the literature. According to the statistical analysis results, the SKR method is found to outperform the SVR and other regression equations. In particular, while empirical regression models fail to generate accurate results for other channel cross-section shapes and sizes, the SKR model provides promising results due to the inclusion of a channel parameter at the core of its structure and also by operating on an extensive range of experimental data. The superior efficacy of the SKR approach is also linked to its formulation in the kernel space while also benefiting from a sparse representation method to select the most useful training samples for model construction. As such, it also circumvents the requirement to evaluate irrelevant or noisy observations during the test phase of the model, and thus improving on the test phase running time.

[1]  Wei Chen,et al.  Landslide susceptibility modeling based on ANFIS with teaching-learning-based optimization and Satin bowerbird optimizer , 2021, Geoscience Frontiers.

[2]  C. J. Apelt,et al.  New Data On Shape Effects In Smooth Rectangular Channels , 1982 .

[3]  Kiyoumars Roushangar,et al.  Prediction of non-cohesive sediment transport in circular channels in deposition and limit of deposition states using SVM , 2017 .

[4]  H. Aksoy,et al.  Experimental analysis for self-cleansing open channel design , 2020 .

[5]  H. Md. Azamathulla,et al.  Gene-Expression Programming for Sediment Transport in Sewer Pipe Systems , 2011 .

[6]  Dietmar Stephan,et al.  Ensemble data mining modeling in corrosion of concrete sewer: A comparative study of network-based (MLPNN & RBFNN) and tree-based (RF, CHAID, & CART) models , 2020, Adv. Eng. Informatics.

[7]  Wei Chen,et al.  Landslide Susceptibility Evaluation Using Hybrid Integration of Evidential Belief Function and Machine Learning Techniques , 2019, Water.

[8]  Richard May,et al.  Development of design methodology for self-cleansing sewers , 1996 .

[9]  R. Tibshirani,et al.  REJOINDER TO "LEAST ANGLE REGRESSION" BY EFRON ET AL. , 2004, math/0406474.

[10]  M. Safari,et al.  Rainfall-runoff modeling through regression in the reproducing kernel Hilbert space algorithm , 2020, Journal of Hydrology.

[11]  Wei Chen,et al.  GIS-based landslide susceptibility assessment using optimized hybrid machine learning methods , 2021, CATENA.

[12]  Shape effects on resistance to flow in smooth channels of circular cross-section , 1985 .

[13]  Mir Jafar Sadegh Safari,et al.  Implementation of hybrid particle swarm optimization-differential evolution algorithms coupled with multi-layer perceptron for suspended sediment load estimation , 2020 .

[14]  Luigi Berardi,et al.  Non-deposition self-cleansing models for large sewer pipes. , 2020, Water science and technology : a journal of the International Association on Water Pollution Research.

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

[16]  Nhat-Duc Hoang,et al.  Prediction of interface yield stress and plastic viscosity of fresh concrete using a hybrid machine learning approach , 2020, Adv. Eng. Informatics.

[17]  Jose J. Ota,et al.  Urban Storm Sewer Design: Approach in Consideration of Sediments , 2003 .

[18]  H. Md. Azamathulla,et al.  ANFIS-based approach for predicting sediment transport in clean sewer , 2012, Appl. Soft Comput..

[19]  De-Cheng Feng,et al.  Failure mode classification and bearing capacity prediction for reinforced concrete columns based on ensemble machine learning algorithm , 2020, Adv. Eng. Informatics.

[20]  Lihua Cao,et al.  Benchmark value determination of energy efficiency indexes for coal-fired power units based on data mining methods , 2020, Adv. Eng. Informatics.

[21]  Richard May,et al.  Self-Cleansing Sewer Design Based on Sediment Transport Principles , 2003 .

[22]  Hafzullah Aksoy,et al.  Non-deposition self-cleansing design criteria for drainage systems , 2017 .

[23]  Bahram Gharabaghi,et al.  Combination of sensitivity and uncertainty analyses for sediment transport modeling in sewer pipes , 2020 .

[24]  Wei Chen,et al.  GIS-based evaluation of landslide susceptibility using hybrid computational intelligence models , 2020, CATENA.

[25]  Wei Chen,et al.  Evaluating the usage of tree-based ensemble methods in groundwater spring potential mapping , 2020 .

[26]  Mir Jafar Sadegh Safari,et al.  Sediment transport modeling in open channels using neuro-fuzzy and gene expression programming techniques. , 2019, Water science and technology : a journal of the International Association on Water Pollution Research.

[27]  Hossein Bonakdari,et al.  Sediment transport modeling in rigid boundary open channels using generalize structure of group method of data handling , 2019, Journal of Hydrology.

[28]  C Nalluri,et al.  SEDIMENT TRANSPORT IN SMOOTH FIXED BED CHANNELS , 1975 .

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

[30]  Millard P. Robinson,et al.  Pipelining of Low-Centration Sand-Water Mixtures , 1972 .

[31]  Wei Chen,et al.  Optimization of Computational Intelligence Models for Landslide Susceptibility Evaluation , 2020, Remote. Sens..

[32]  Josef Kittler,et al.  Robust One-Class Kernel Spectral Regression , 2019, IEEE Transactions on Neural Networks and Learning Systems.

[33]  Hossein Bonakdari,et al.  Assessment of evolutionary algorithms in predicting non-deposition sediment transport , 2015 .

[34]  Nhat-Duc Hoang,et al.  Image processing based automatic recognition of asphalt pavement patch using a metaheuristic optimized machine learning approach , 2019, Adv. Eng. Informatics.

[35]  Yan Li,et al.  Short-term electricity demand forecasting with MARS, SVR and ARIMA models using aggregated demand data in Queensland, Australia , 2018, Adv. Eng. Informatics.

[36]  Mohammad Najafzadeh,et al.  Application of model tree and Evolutionary Polynomial Regression for evaluation of sediment transport in pipes , 2017 .

[37]  K. Khosravi,et al.  Iterative classifier optimizer-based pace regression and random forest hybrid models for suspended sediment load prediction , 2020, Environmental Science and Pollution Research.

[38]  P. Novak,et al.  Sediment transport in rigid bed conveyances , 1991 .

[39]  Alexander J. Smola,et al.  Support Vector Method for Function Approximation, Regression Estimation and Signal Processing , 1996, NIPS.

[40]  Aminuddin Ab. Ghani,et al.  Experimental Studies of Self-Cleansing Drainage System Design: A Review , 2018, Journal of Pipeline Systems Engineering and Practice.

[41]  Mir Jafar Sadegh Safari,et al.  Decision tree (DT), generalized regression neural network (GR) and multivariate adaptive regression splines (MARS) models for sediment transport in sewer pipes. , 2019, Water science and technology : a journal of the International Association on Water Pollution Research.

[42]  Mukand S. Babel,et al.  Non-deposition design criteria for sewers with part-full flow , 2010 .

[43]  C. J. Apelt,et al.  SHAP EEFFECTS ON RESISTANCE TO UNIFORM FLOW IN OPEN CHANNELS , 1979 .

[44]  J J Ota,et al.  Particle velocity and sediment transport at the limit of deposition in sewers. , 2013, Water science and technology : a journal of the International Association on Water Pollution Research.

[45]  Nhat-Duc Hoang,et al.  Prediction of soil compression coefficient for urban housing project using novel integration machine learning approach of swarm intelligence and Multi-layer Perceptron Neural Network , 2018, Adv. Eng. Informatics.