Estimation of soil dispersivity using soft computing approaches

The accurate estimation of soil dispersivity (α) is required for characterizing the transport of contaminants in soil. The in situ measurement of α is costly and time-consuming. Hence, in this study, three soft computing methods, namely adaptive neuro-fuzzy inference system (ANFIS), artificial neural network (ANN), and gene expression programming (GEP), are used to estimate α from more readily measurable physical soil variables, including travel distance from source of pollutant (L), mean grain size (D50), soil bulk density (ρb), and contaminant velocity (Vc). Based on three statistical metrics [i.e., mean absolute error, root-mean-square error (RMSE), and coefficient of determination (R2)], it is found that all approaches (ANN, ANFIS, and GEP) can accurately estimate α. Results also show that the ANN model (with RMSE = 0.00050 m and R2 = 0.977) performs better than the ANFIS model (with RMSE = 0.00062 m and R2 = 0.956), and the estimates from GEP are almost as accurate as those from ANFIS. The performance of ANN, ANFIS, and GEP models is also compared with the traditional multiple linear regression (MLR) method. The comparison indicates that all of the soft computing methods outperform the MLR model. Finally, the sensitivity analysis shows that the travel distance from source of pollution (L) and bulk density (ρb) have, respectively, the most and the least effect on the soil dispersivity.

[1]  H. Md. Azamathulla,et al.  Gene-expression programming for transverse mixing coefficient , 2012 .

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

[3]  Aytac Guven,et al.  Gene Expression Programing for Estimating Suspended Sediment Yield in Middle Euphrates Basin, Turkey , 2010 .

[4]  Ahmed El-Shafie,et al.  Regularized versus non-regularized neural network model for prediction of saturated soil-water content on weathered granite soil formation , 2011, Neural Computing and Applications.

[5]  Ahmed M. A. Sattar,et al.  Gene Expression Models for the Prediction of Longitudinal Dispersion Coefficients in Transitional and Turbulent Pipe Flow , 2014 .

[6]  H. Md. Azamathulla,et al.  Application of Gene-Expression Programming in Hydraulic Engineering , 2015, Handbook of Genetic Programming Applications.

[7]  Hamed Kashi,et al.  Prediction of water quality parameters of Karoon River (Iran) by artificial intelligence-based models , 2014, International Journal of Environmental Science and Technology.

[8]  Dorothea Heiss-Czedik,et al.  An Introduction to Genetic Algorithms. , 1997, Artificial Life.

[9]  Cândida Ferreira.  Gene Expression Programming in Problem Solving , 2002 .

[10]  Hamed Kashi,et al.  Estimation of Soil Infiltration and Cation Exchange Capacity Based on Multiple Regression, ANN (RBF, MLP), and ANFIS Models , 2014 .

[11]  L. Ujfaludi.  Longitudinal dispersion tests in non-uniform porous media , 1986 .

[12]  S. Emamgholizadeh,et al.  Predicting water level drawdown and assessment of land subsidence in Damghan aquifer by combining GMS and GEP models , 2015 .

[13]  Jyh-Shing Roger Jang,et al.  ANFIS: adaptive-network-based fuzzy inference system , 1993, IEEE Trans. Syst. Man Cybern..

[14]  Christoph Hinz,et al.  Relation of dispersivity to properties of homogeneous saturated repacked soil columns , 2007 .

[15]  S. P. Neuman.  Universal scaling of hydraulic conductivities and dispersivities in geologic media , 1990 .

[16]  John A. Cherry,et al.  Contaminant Migration in Saturated Unconsolidated Geologic Deposits , 1982 .

[17]  Mohammad Mehdi Ebadzadeh,et al.  An expert system for predicting longitudinal dispersion coefficient in natural streams by using ANFIS , 2009, Expert Syst. Appl..

[18]  S. Emamgholizadeh,et al.  Seed yield prediction of sesame using artificial neural network , 2015 .

[19]  Jaroslaw J. Napiorkowski,et al.  Are artificial neural network techniques relevant for the estimation of longitudinal dispersion coefficient in rivers? / Les techniques de réseaux de neurones artificiels sont-elles pertinentes pour estimer le coefficient de dispersion longitudinale en rivières? , 2005 .

[20]  Asaad Y. Shamseldin,et al.  Statistical downscaling of watershed precipitation using Gene Expression Programming (GEP) , 2011, Environ. Model. Softw..

[21]  R. B. Grossman,et al.  A method to predict bulk density of tilled Ap horizons , 1995 .

[22]  Cândida Ferreira,et al.  Gene Expression Programming: A New Adaptive Algorithm for Solving Problems , 2001, Complex Syst..

[23]  C. Axness,et al.  Three‐dimensional stochastic analysis of macrodispersion in aquifers , 1983 .

[24]  Hamid Taghavifar,et al.  Use of artificial neural networks for estimation of agricultural wheel traction force in soil bin , 2013, Neural Computing and Applications.

[25]  Majid Dehghani,et al.  Predicting the Longitudinal Dispersion Coefficient Using Support Vector Machine and Adaptive Neuro-Fuzzy Inference System Techniques , 2009 .

[26]  Adam P. Piotrowski,et al.  Are Artificial Neural Network Techniques Relevant for the Estimation of Longitudinal Dispersion Coefficient in Rivers , 2005 .

[27]  H. Md. Azamathulla,et al.  A Review on Application of Soft Computing Methods in Water Resources Engineering , 2013 .

[28]  Y. Eckstein,et al.  Statistical Analysis of the Relationships Between Dispersivity and Other Physical Properties of Porous Media , 1997 .

[29]  Philip A. Adewuyi.  Performance Evaluation of Mamdani-type and Sugeno-type Fuzzy Inference System Based Controllers for Computer Fan , 2012 .

[30]  Vijay P. Singh,et al.  Predicting Longitudinal Dispersion Coefficient in Natural Streams by Artificial Neural Network , 2005 .

[31]  S. M. Bateni,et al.  Estimation of soil cation exchange capacity using Genetic Expression Programming (GEP) and Multivariate Adaptive Regression Splines (MARS) , 2015 .

[32]  Clark C. K. Liu,et al.  Fluid flow and solute transport processes in unsaturated heterogeneous soils: Preliminary numerical experiments , 1991 .

[33]  Hikmet Kerem Cigizoglu,et al.  Predicting longitudinal dispersion coefficient in natural streams by artificial intelligence methods , 2008 .

[34]  W. E. Brigham.  Mixing Equations in Short Laboratory Cores , 1974 .

[35]  S. M. Bateni,et al.  Neural network and neuro-fuzzy assessments for scour depth around bridge piers , 2007, Eng. Appl. Artif. Intell..

[36]  Samad Emamgholizadeh,et al.  Prediction the Groundwater Level of Bastam Plain (Iran) by Artificial Neural Network (ANN) and Adaptive Neuro-Fuzzy Inference System (ANFIS) , 2014, Water Resources Management.

[37]  H. Md. Azamathulla,et al.  Prediction of Local Scour Depth Downstream of Bed Sills Using Soft Computing Models , 2014 .

[38]  E. Perfect,et al.  Prediction of Dispersivity for Undisturbed Soil Columns from Water Retention Parameters , 2002 .

[39]  P. B. Deolalikar,et al.  Neural Networks for Estimation of Scour Downstream of a Ski-Jump Bucket , 2005 .

[40]  H. Md. Azamathulla,et al.  Prediction of soil erodibility factor for Peninsular Malaysia soil series using ANN , 2012, Neural Computing and Applications.

[41]  A. Malik,et al.  Artificial neural network modeling of the river water quality—A case study , 2009 .

[42]  Yudong Cal,et al.  Soil classification by neural network , 1995 .

[43]  H. Md. Azamathulla,et al.  Use of Gene-Expression Programming to Estimate Manning’s Roughness Coefficient for High Gradient Streams , 2013, Water Resources Management.

[44]  J. J. Fried,et al.  Dispersion in Porous Media , 1971 .

[45]  S. Hyakin,et al.  Neural Networks: A Comprehensive Foundation , 1994 .