Multiple AI model integration strategy—Application to saturated hydraulic conductivity prediction from easily available soil properties

Abstract A multiple model integration scheme driven by artificial neural network (ANN) (MM-ANN) was developed and tested to improve the prediction accuracy of soil hydraulic conductivity (Ks) in Tabriz plain, an arid region of Iran. The soil parameters such as silt, clay, organic matter (OM), bulk density (BD), pH and electrical conductivity (EC) were used as model inputs to predict soil Ks. Standalone models including multivariate adaptive regression splines (MARS), M5 model tree (M5Tree), support vector machine (SVM) and extreme learning machine (ELM) were also implemented for comparative evaluation with MM-ANN model predictions. Based on several performance indicators such as Nash Sutcliffe Efficiency (NSE), results showed that the calibrated MM-ANN model involving the predictions of MARS, M5Tree, SVM and ELM models by considering all the soil parameters used in this study as inputs provided superior soil Ks estimates. The proposed hybrid model (MM-ANN) emerged as a reliable intelligence model for the assessment of soil hydraulic conductivity with an NSE = 0.939 & 0.917 during training and testing, respectively. Accurate prediction of field-scale soil hydraulic conductivity is crucial from the view point of agricultural sustainability and management prospects.

[1]  Alain Dassargues,et al.  Estimation of Hydraulic Conductivity and Its Uncertainty from Grain-Size Data Using GLUE and Artificial Neural Networks , 2012, Mathematical Geosciences.

[2]  Özgür Kisi,et al.  Pan evaporation modeling using four different heuristic approaches , 2017, Comput. Electron. Agric..

[3]  A. Sommella,et al.  Scaling the saturated hydraulic conductivity of a vertic ustorthens soil under conventional and minimum tillage , 2000 .

[4]  George F. Pinder,et al.  Galerkin solution of the inverse problem for aquifer transmissivity , 1973 .

[5]  Pijush Samui,et al.  Prediction of Field Hydraulic Conductivity of Clay Liners Using an Artificial Neural Network and Support Vector Machine , 2012 .

[6]  Özer Çinar,et al.  Comparison of artificial neural network and regression pedotransfer functions for prediction of soil water retention and saturated hydraulic conductivity , 2006 .

[7]  Shiv O. Prasher,et al.  Modeling runoff from middle Himalayan watersheds employing artificial intelligence techniques , 2006 .

[8]  O. Kisi,et al.  Pan Evaporation Modeling Using Neural Computing Approach for Different Climatic Zones , 2012, Water Resources Management.

[9]  Sujay Raghavendra Naganna,et al.  Factors influencing streambed hydraulic conductivity and their implications on stream–aquifer interaction: a conceptual review , 2017, Environmental Science and Pollution Research.

[10]  Paul L. G. Vlek,et al.  Artificial Neural Network Estimation of Saturated Hydraulic Conductivity , 2007 .

[11]  Guang-Bin Huang,et al.  Extreme learning machine: a new learning scheme of feedforward neural networks , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

[12]  Ozgur Kisi,et al.  Comparison of two different data-driven techniques in modeling lake level fluctuations in Turkey , 2009 .

[13]  Lehua Pan,et al.  Measuring saturated hydraulic conductivity using a generalized solution for single-ring infiltrometers , 1999 .

[14]  Chee Kheong Siew,et al.  Extreme learning machine: Theory and applications , 2006, Neurocomputing.

[15]  Moussa S. Elbisy,et al.  Support Vector Machine and regression analysis to predict the field hydraulic conductivity of sandy soil , 2015 .

[16]  Brian J. Wagner,et al.  Experimental design for estimating parameters of rate‐limited mass transfer: Analysis of stream tracer studies , 1997 .

[17]  Shiv O. Prasher,et al.  Comparison of multivariate adaptive regression splines with coupled wavelet transform artificial neural networks for runoff forecasting in Himalayan micro-watersheds with limited data , 2012 .

[18]  H. Bayat,et al.  Estimation of soil saturated hydraulic conductivity by artificial neural networks ensemble in smectitic soils , 2016, Eurasian Soil Science.

[19]  V. Singh,et al.  Drought forecasting in eastern Australia using multivariate adaptive regression spline, least square support vector machine and M5Tree model , 2017 .

[20]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[21]  O. Kisi.  Pan evaporation modeling using least square support vector machine, multivariate adaptive regression splines and M5 model tree , 2015 .

[22]  Francisco Javier de Cos Juez,et al.  Bankruptcy forecasting: A hybrid approach using Fuzzy c-means clustering and Multivariate Adaptive Regression Splines (MARS) , 2011, Expert Syst. Appl..

[23]  Han Zhao,et al.  Extreme learning machine: algorithm, theory and applications , 2013, Artificial Intelligence Review.

[24]  Jan Adamowski,et al.  Modeling of daily pan evaporation in sub tropical climates using ANN, LS-SVR, Fuzzy Logic, and ANFIS , 2014, Expert Syst. Appl..

[25]  W. W. Wood,et al.  Large-Scale Natural Gradient Tracer Test in Sand and Gravel, , 1991 .

[26]  Paresh Chandra Deka,et al.  Support vector machine applications in the field of hydrology: A review , 2014, Appl. Soft Comput..

[27]  Bahram Gharabaghi,et al.  Predicting Saturated Hydraulic Conductivity by Artificial Intelligence and Regression Models , 2013 .

[28]  Ali Rahimikhoob,et al.  Comparison between M5 Model Tree and Neural Networks for Estimating Reference Evapotranspiration in an Arid Environment , 2014, Water Resources Management.

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

[30]  R. T. Walczak,et al.  Using Support Vector Machines to Develop Pedotransfer Functions for Water Retention of Soils in Poland , 2008 .

[31]  Thomas Harter,et al.  Neural Networks Prediction of Soil Hydraulic Functions for Alluvial Soils Using Multistep Outflow Data , 2004 .

[32]  Vladimir Cherkassky,et al.  The Nature Of Statistical Learning Theory , 1997, IEEE Trans. Neural Networks.

[33]  J. Friedman.  Multivariate adaptive regression splines , 1990 .

[34]  Dianhui Wang,et al.  Extreme learning machines: a survey , 2011, Int. J. Mach. Learn. Cybern..

[35]  M. Pal,et al.  M5 model tree application in daily river flow forecasting in Sohu Stream, Turkey , 2013, Water Resources.

[36]  Mohammad Rezaie-Balf,et al.  Wavelet coupled MARS and M5 Model Tree approaches for groundwater level forecasting , 2017 .

[37]  M Nakhaei,et al.  Estimating the Saturated Hydraulic Conductivity of Granular Material, Using Artificial Neural Network, Based on Grain Size Distribution Curve , 2005 .

[38]  A A Nadiri,et al.  Supervised Intelligent Committee Machine Method for Hydraulic Conductivity Estimation , 2014, Water Resources Management.

[39]  M. Iovino,et al.  An assessment of the Beerkan method for determining the hydraulic properties of a sandy loam soil , 2014 .

[40]  V. Bagarello,et al.  Comparing two methods of analysis of single-ring infiltrometer data for a sandy–loam soil , 2009 .

[41]  T. Elliot,et al.  A natural-gradient field tracer test for evaluation of pollutant-transport parameters in a porous-medium aquifer , 2001 .

[42]  Feilong Cao,et al.  A study on effectiveness of extreme learning machine , 2011, Neurocomputing.

[43]  Vijay P. Singh,et al.  Estimation of Mean Annual Flood in Indian Catchments Using Backpropagation Neural Network and M5 Model Tree , 2010 .

[44]  José David Martín-Guerrero,et al.  Regularized extreme learning machine for regression problems , 2011, Neurocomputing.

[45]  C. Drury,et al.  Comparison of Tension Infiltrometer, Pressure Infiltrometer, and Soil Core Estimates of Saturated Hydraulic Conductivity , 2000 .

[46]  Laj R. Ahuja,et al.  Macroporosity to characterize spatial variability of hydraulic conductivity and effects of land management , 1984 .

[47]  M. Iovino,et al.  Factors affecting measurement of the near-saturated soil hydraulic conductivity. , 2000 .

[48]  Ozgur Kisi,et al.  Evapotranspiration modelling using support vector machines / Modélisation de l'évapotranspiration à l'aide de ‘support vector machines’ , 2009 .