Artificial neural network (ANN) models for determining hydraulic conductivity of compacted fine-grained soils

This study deals with development of artificial neural networks (ANNs) and multiple regression analysis (MRA) models for determining hydraulic conductivity of fine-grained soils. To achieve this, conventional falling-head tests, oedometer falling-head tests, and centrifuge tests were conducted on silty sand and marine clays compacted at different dry densities and moisture contents. Further, results obtained from ANN and MRA models were compared vis-a-vis experimental results. The performance indices such as the coefficient of determination, root mean square error, mean absolute error, and variance were used to assess the performance of these models. The ANN models exhibit higher prediction performance than the MRA models based on their performance indices. It has been demonstrated that the ANN models developed in the study can be employed for determining hydraulic conductivity of compacted fine-grained soils quite efficiently.

[1]  J. W. Biggar,et al.  Determining the Hydraulic Conductivity of Soil Cores by Centrifugation , 1976 .

[2]  Robert P. Chapuis,et al.  SAND-BENTONITE LINERS: PREDICTING PERMEABILITY FROM LABORATORY TESTS , 1990 .

[3]  David E. Daniel,et al.  Hydraulic Conductivity of Two Prototype Clay Liners , 1985 .

[4]  A. T. C. Goh,et al.  Back-propagation neural networks for modeling complex systems , 1995, Artif. Intell. Eng..

[5]  David E. Daniel,et al.  Field Permeability Test for Earthen Liners , 1986 .

[6]  M. Stone.  Cross‐Validatory Choice and Assessment of Statistical Predictions , 1976 .

[7]  R. N. Taylor,et al.  Geotechnical Centrifuge Technology , 2018 .

[8]  Yacoub M. Najjar,et al.  Site Characterization by Neuronets: An Application to the Landfill Siting Problem , 1996 .

[9]  Candan Gokceoglu,et al.  Estimation of rock modulus: For intact rocks with an artificial neural network and for rock masses with a new empirical equation , 2006 .

[10]  D. Singh,et al.  Application of a Geotechnical Centrifuge for Estimation of Unsaturated Soil Hydraulic Conductivity , 2001 .

[11]  Moir D. Haug,et al.  Impact of molding water content on hydraulic conductivity of compacted sand-bentonite , 1992 .

[12]  Robert M. Pap,et al.  Handbook of neural computing applications , 1990 .

[13]  Mushtaque Ahmed,et al.  Simple field method for determining unsaturated hydraulic conductivity , 1991 .

[14]  D. Singh,et al.  Modelling hydraulic conductivity in a small centrifuge , 2000 .

[15]  Marcel G. Schaap,et al.  Improved Prediction of Unsaturated Hydraulic Conductivity with the Mualem‐van Genuchten Model , 2000 .

[16]  John R. Nimmo,et al.  Unsaturated flow in a centrifugal field: Measurement of hydraulic conductivity and testing of Darcy's Law , 1987 .

[17]  Craig H. Benson,et al.  Estimating Hydraulic Conductivity of Compacted Clay Liners , 1994 .

[18]  W. E. Kelly,et al.  Electrical‐Resistivity Measurements For Evaluating Compacted‐Soil Liners , 1994 .

[19]  I. Kanellopoulos,et al.  Strategies and best practice for neural network image classification , 1997 .

[20]  H.W.G. Booltink,et al.  Neural network models to predict soil water retention , 1999 .

[21]  G. W. Bloemen.  Calculation of Hydraulic Conductivities of Soils from Texture and Organic matter Content , 1980 .

[22]  A. R. Gupta,et al.  A Comparative Analysis of Cognitive Systems for the Prediction of Drillability of Rocks and Wear Factor , 2006 .

[23]  Julie Q. Shang,et al.  Using complex permittivity and artificial neural networks to identify and classify copper, zinc, and lead contamination in soil , 2006 .

[24]  Daniel S. Levine,et al.  Neural Network Modeling , 2002 .

[25]  Candan Gokceoglu,et al.  A fuzzy triangular chart to predict the uniaxial compressive strength of the Ankara agglomerates from their petrographic composition , 2002 .

[26]  Robert Babuška,et al.  Fuzzy model for the prediction of unconfined compressive strength of rock samples , 1999 .

[27]  Peter Finke,et al.  Comparison of class and continuous pedotransfer functions to generate soil hydraulic characteristics , 1995 .

[28]  Jacek M. Zurada,et al.  Introduction to artificial neural systems , 1992 .

[29]  Y. Erzin.  Artificial neural networks approach for swell pressure versus soil suction behaviour , 2007 .

[30]  Ibrahim H. Guzelbey,et al.  Neural network modeling of strength enhancement for CFRP confined concrete cylinders , 2008 .

[31]  Kanthasamy K. Muraleetharan,et al.  CENTRIFUGE MODELING OF TRANSPORT PROCESSES FOR POLLUTANTS IN SOILS , 1988 .

[32]  Lisa R. Blotz,et al.  ELECTRICAL RESISTIVITY OF COMPACTED CLAYS , 1996 .

[33]  Yacoub M. Najjar,et al.  NEURAL MODELING OF KANSAS SOIL SWELLING , 1996 .

[34]  J. Joseph,et al.  IN SITU PERMEABILITY TESTING OF PARTIALLY SATURATED SOILS USING A SEALED DOUBLE RING INFILTROMETER , 1995 .

[35]  Milton S. Boyd,et al.  Designing a neural network for forecasting financial and economic time series , 1996, Neurocomputing.

[36]  Yusuf Erzin,et al.  Artificial neural networks approach for zeta potential of Montmorillonite in the presence of different cations , 2008 .

[37]  Yike Guo,et al.  A rule based fuzzy model for the prediction of petrophysical rock parameters , 2001 .

[38]  Holger R. Maier,et al.  ARTIFICIAL NEURAL NETWORK APPLICATIONS IN GEOTECHNICAL ENGINEERING , 2001 .

[39]  J. Wösten,et al.  Development and use of a database of hydraulic properties of European soils , 1999 .

[40]  Falling head hydraulic conductivity tests in a geotechnical centrifuge , 2001 .

[41]  Field Measurement of Unsaturated Hydraulic Conductivity by Infiltration through Artificial Crusts1 , 1971 .

[43]  D. R. Hush,et al.  Classification with neural networks: a performance analysis , 1989, IEEE 1989 International Conference on Systems Engineering.

[44]  Peter Keith Woodward,et al.  Artificial neural network for stress-strain behavior of sandy soils: Knowledge based verification , 2005 .

[45]  D. Singh,et al.  Evaluation of Various Pedo-Transfer Functions for Developing Soil-Water Characteristic Curve of a Silty Soil , 2007 .

[46]  Candan Gokceoglu,et al.  A fuzzy model to predict the uniaxial compressive strength and the modulus of elasticity of a problematic rock , 2004, Eng. Appl. Artif. Intell..

[47]  Walter J. Rawls,et al.  Pedotransfer functions: bridging the gap between available basic soil data and missing soil hydraulic characteristics , 2001 .

[48]  B. Hanumantha Rao,et al.  Artificial neural network models for predicting soil thermal resistivity , 2008 .

[49]  Michael Sakellariou,et al.  A study of slope stability prediction using neural networks , 2005 .

[50]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[51]  D. B. Jaynes,et al.  USING SOIL PHYSICAL PROPERTIES TO ESTIMATE HYDRAULIC CONDUCTIVITY , 1984 .

[52]  S. Leroueil,et al.  The permeability of natural soft clays. Part I: Methods of laboratory measurement , 1983 .

[53]  Hon-Yim Ko,et al.  Centrifugal Modeling of Transient Water Flow , 1983 .

[54]  Ibrahim H. Guzelbey,et al.  Prediction of web crippling strength of cold-formed steel sheetings using neural networks , 2006 .

[55]  J. Feyen,et al.  ESTIMATING UNSATURATED HYDRAULIC CONDUCTIVITY FROM EASILY MEASURED SOIL PROPERTIES , 1990 .

[56]  R. J. Mitchell.  Centrifuge techniques for testing clay liner samples , 1994 .

[57]  X. Yu,et al.  SOIL WATER CONTENT AND DRY DENSITY BY TIME DOMAIN REFLECTOMETRY , 2004 .

[58]  A. Goh.  Seismic liquefaction potential assessed by neural networks , 1994 .

[59]  Laurene V. Fausett,et al.  Fundamentals Of Neural Networks , 1994 .

[60]  Brian D. Ripley,et al.  Pattern Recognition and Neural Networks , 1996 .

[61]  Kingsley Harrop‐Williams.  Clay Liner Permeability: Evaluation and Variation , 1985 .

[62]  V. R. Tarnawski,et al.  Evaluation of Pedo-transfer Functions For Unsaturated Soil Hydraulic , 2001 .

[63]  J.H.M. Wösten,et al.  Testing an Artificial Neural Network for Predicting Soil Hydraulic Conductivity , 1996 .

[64]  Janet M. Twomey,et al.  Validation and Verification , 1997 .

[65]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[66]  James H. Garrett,et al.  Artificial Neural Networks for Civil Engineers: Fundamentals and Applications , 1997 .

[67]  Anthony T. C. Goh.  Modeling soil correlations using neural networks , 1995 .

[68]  Ibrahim H. Guzelbey,et al.  Prediction of rotation capacity of wide flange beams using neural networks , 2006 .

[69]  K. V. Sudhakar,et al.  ANN back-propagation prediction model for fracture toughness in microalloy steel , 2002 .

[70]  D. Singh,et al.  Methodology for Determination of Electrical Properties of Soils , 2004 .

[71]  Carl T. Haas,et al.  Automated quality assessment of stone aggregates based on laser imaging and a neural network , 2004 .

[72]  D. Singh,et al.  Estimating Unsaturated Hydraulic Conductivity of Fine- Grained Soils Using Electrical Resistivity Measurements , 2005 .

[73]  Ibrahim H. Guzelbey,et al.  A soft computing based approach for the prediction of ultimate strength of metal plates in compression , 2007 .

[74]  Mark B. Jaksa,et al.  Neural network prediction of pullout capacity of marquee ground anchors , 2005 .

[75]  H. Vereecken.  Estimating the unsaturated hydraulic conductivity from theoretical models using simple soil properties , 1995 .

[76]  David E. Daniel,et al.  Predicting Hydraulic Conductivity of Clay Liners , 1984 .

[77]  Holger R. Maier,et al.  DATA DIVISION FOR DEVELOPING NEURAL NETWORKS APPLIED TO GEOTECHNICAL ENGINEERING , 2004 .

[78]  J. Shi.  REDUCING PREDICTION ERROR BY TRANSFORMING INPUT DATA FOR NEURAL NETWORKS , 2000 .

[79]  Marcel G. Schaap,et al.  Database-related accuracy and uncertainty of pedotransfer functions , 1998 .

[80]  Matija Fajdiga,et al.  A neural network approach to describing the fretting fatigue in aluminium-steel couplings , 2003 .

[81]  S. Leroueil,et al.  The permeability of natural soft clays. Part II: Permeability characteristics: Reply , 1983 .

[82]  Johan Bouma,et al.  Using Soil Survey Data for Quantitative Land Evaluation , 1989 .