Combination of artificial neural networks and fractal theory to predict soil water retention curve

Despite good progress in developing pedotransfer functions (PTFs), the input variables that are more preferable in a PTF have not been yet determined clearly. Among the modeling techniques to characterize soil structure, those using fractal theory are in majority. For the first time, fractal parameters were used as predictors to estimate the water content at different matric suctions using artificial neural networks (ANNs). PTFs were developed to estimate soil water retention curve (SWRC) from a dataset of 148 soil samples from North West of Iran. Including geometric mean (d"g), geometric standard deviation (s"g), and median diameter (M"d) of particle size distribution as input parameters significantly enhanced the PTFs' accuracy and increased the coefficient of determination (R^2) by up to 5.5%. Fractal parameters of particle size distribution (PSDFPs) were used as predictors and it improved the accuracy and reliability by decreasing root mean square error (RMSE) by up to 30% for water content at h value of 5kPa (@q"5" "k"P"a) and by up to 12.5% for water content at h value of 50kPa (@q"5"0" "k"P"a). Entering the fractal parameters of aggregate size distribution (ASDFPs) in the models raised the accuracy at most soil matric suctions (h) and caused up to 6.7% reduction in the RMSE. Their impacts were significant at @q"2"5"k"P"a and @q"5"0"k"P"a. The network architectures were unique and problem specific with respect to the output layer transfer functions and number of hidden neurons. Adding PSDFPs and ASDFPs to the input parameters of the proper ANN models could improve the estimation of SWRC, significantly.

[1]  Costanza Calzolari,et al.  Development of pedotransfer functions using a group method of data handling for the soil of the Pianura Padano-Veneta region of North Italy: water retention properties , 2005 .

[2]  N. Bird,et al.  An assessment of a new model of dynamic fragmentation of soil with test data , 2012 .

[3]  G. Tóth,et al.  Water Retention of Salt-Affected Soils: Quantitative Estimation Using Soil Survey Information , 2012 .

[4]  S. Powers,et al.  Using Particle-Size Distribution Models to Estimate Soil Hydraulic Properties , 2003 .

[5]  M. Homaee,et al.  Deriving and validating pedotransfer functions for some calcareous soils , 2011 .

[6]  M. Schaap,et al.  ROSETTA: a computer program for estimating soil hydraulic parameters with hierarchical pedotransfer functions , 2001 .

[7]  O. Duval,et al.  Prediction of soil water retention properties after stratification by combining texture, bulk density and the type of horizon , 2008 .

[8]  E. Perfect,et al.  Fractal Theory Applied to Soil Aggregation , 1991 .

[9]  Peter J. Shouse,et al.  Scaling Parameter to Predict the Soil Water Characteristic from Particle-Size Distribution Data , 1999 .

[10]  Scott W. Tyler,et al.  Fractal processes in soil water retention , 1990 .

[11]  W. Rawls,et al.  Evaluation of different representations of the particle-size distribution to predict soil water retention , 2006 .

[12]  W. Chepil.  METHODS OF ESTIMATING APPARENT DENSITY OF DISCRETE SOIL GRAINS AND AGGREGATES , 1950 .

[13]  Larry Boersma,et al.  A Unifying Quantitative Analysis of Soil Texture1 , 1984 .

[14]  Harry Vereecken,et al.  ESTIMATING THE SOIL MOISTURE RETENTION CHARACTERISTIC FROM TEXTURE, BULK DENSITY, AND CARBON CONTENT , 1989 .

[15]  Edith Perrier,et al.  Generalizing the fractal model of soil structure : the pore-solid fractal approach , 1999 .

[16]  N. G. Patil,et al.  Soil Water Retention Characteristics of Vertisols and Pedotransfer Functions Based on Nearest Neighbor and Neural Networks Approaches to Estimate AWC , 2012 .

[17]  C. Piedallu,et al.  Mapping soil water holding capacity over large areas to predict potential production of forest stands , 2011 .

[18]  R. H. Brooks,et al.  Hydraulic properties of porous media , 1963 .

[19]  Gaylon S. Campbell,et al.  Soil physics with BASIC :transport models for soil-plant systems , 1985 .

[20]  D. Hillel.  Environmental soil physics , 1998 .

[21]  Raghavendra B. Jana,et al.  Enhancing PTFs with remotely sensed data for multi-scale soil water retention estimation , 2011 .

[22]  Y. Pachepsky,et al.  Artificial Neural Networks to Estimate Soil Water Retention from Easily Measurable Data , 1996 .

[23]  John W. Crawford,et al.  The relation between the moisture-release curve and the structure of soil , 1995 .

[24]  M. Schaap,et al.  Modeling water retention curves of sandy soils using neural networks , 1996 .

[25]  John W. Crawford,et al.  The fractal structure of soil aggregates: its measurement and interpretation , 1991 .

[26]  P. Good.  Resampling Methods , 1999, Birkhäuser Boston.

[27]  Donna L. Hudson,et al.  Neural networks and artificial intelligence for biomedical engineering , 1999 .

[28]  Jeffrey S. Kern,et al.  Evaluation of Soil Water Retention Models Based on Basic Soil Physical Properties , 1995 .

[29]  Application of Artificial Neural Networks in Modeling Soil Solution Electrical Conductivity , 2010 .

[30]  F. Diebold,et al.  Comparing Predictive Accuracy , 1994, Business Cycles.

[31]  D. L. Brakensiek,et al.  Estimation of Soil Water Properties , 1982 .

[32]  Alex B. McBratney,et al.  Soil Mass, Surface, and Spectral Fractal Dimensions Estimated from Thin Section Photographs , 1996 .

[33]  John W. Crawford,et al.  On the relation between number-size distributions and the fractal dimension of aggregates , 1993 .

[34]  M. Das.  Derivation and Validation of Pedotransfer Functions for Point Estimation of Soil Moisture in Sandy to Clayey Soil Texture , 2011 .

[35]  E. Perfect,et al.  Evaluation of selected factors influencing aggregate fragmentation using fractal theory , 1992 .

[36]  Yongfu Xu,et al.  Fractal approach to hydraulic properties in unsaturated porous media , 2004 .

[37]  W. D. Kemper,et al.  Aggregate Stability and Size Distribution , 2018, SSSA Book Series.

[38]  Harry Vereecken,et al.  Functional evaluation of pedotransfer functions for the estimation of soil hydraulic properties. , 1992 .

[39]  Edith Perrier,et al.  The water retention function for a model of soil structure with pore and solid fractal distributions , 2000 .

[40]  Jack F. Paris,et al.  A Physicoempirical Model to Predict the Soil Moisture Characteristic from Particle-Size Distribution and Bulk Density Data 1 , 1981 .

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

[42]  Raghavendra B. Jana,et al.  Multiscale Pedotransfer Functions for Soil Water Retention , 2007 .

[43]  D. Timlin,et al.  Evaluation of the Rawls et al. (1982) Pedotransfer Functions for their Applicability at the U.S. National Scale Large scale environmental impact studies typically involve the use of simulation models and , 2009 .

[44]  Scott W. Tyler,et al.  Fractal scaling of soil particle-size distributions: analysis and limitations , 1992 .

[45]  N. Bird,et al.  Modeling Dynamic Fragmentation of Soil , 2009 .

[46]  Y. Pachepsky,et al.  Use of soil penetration resistance and group method of data handling to improve soil water retention estimates , 1998 .

[47]  Alex B. McBratney,et al.  Soil aggregates as mass fractals , 1995 .

[48]  G. Gee,et al.  Particle-size Analysis , 2018, SSSA Book Series.

[49]  P. A. Dowd,et al.  A neural network approach to geostatistical simulation , 1994 .

[50]  Mathieu Javaux,et al.  Using Pedotransfer Functions to Estimate the van Genuchten–Mualem Soil Hydraulic Properties: A Review , 2010 .

[51]  H. Akaike,et al.  Information Theory and an Extension of the Maximum Likelihood Principle , 1973 .

[52]  Garrison Sposito,et al.  Fractal Fragmentation, Soil Porosity, and Soil Water Properties: I. Theory , 1991 .

[53]  J. Townend,et al.  Water Release Characteristic , 2000 .

[54]  Abdolmajid Liaghat,et al.  Estimation of the van Genuchten soil water retention properties from soil textural data. , 2010 .

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

[56]  Karl Auerswald,et al.  Regionalization of soil water retention curves in a highly variable soilscape, I. Developing a new pedotransfer function , 1997 .

[57]  Budiman Minasny,et al.  The neuro-m method for fitting neural network parametric pedotransfer functions , 2002 .

[58]  F. Bartoli,et al.  Structure and self‐similarity in silty and sandy soils: the fractal approach , 1991 .

[59]  Marcel G. Schaap,et al.  Development of Pedotransfer Functions for Estimation of Soil Hydraulic Parameters using Support Vector Machines , 2009 .

[60]  Jianting Zhu,et al.  Including Topography and Vegetation Attributes for Developing Pedotransfer Functions , 2006 .

[61]  Javier Tomasella,et al.  Comparison of Two Techniques to Develop Pedotransfer Functions for Water Retention , 2003 .

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

[63]  Walter J. Rawls,et al.  Accuracy and reliability of pedotransfer functions as affected by grouping soils , 1999 .

[64]  Astrid M. Lambooy.  Relationship between cation exchange capacity, clay content and water retention of Highveld soils , 1984 .

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

[66]  Olaf Tietje,et al.  Accuracy of the saturated hydraulic conductivity prediction by pedo-transfer functions compared to the variability within FAO textural classes , 1996 .

[67]  H. Millán,et al.  On the fractal scaling of soil data. Particle-size distributions , 2003 .

[68]  M. Schaap,et al.  Neural network analysis for hierarchical prediction of soil hydraulic properties , 1998 .

[69]  R. Walczak,et al.  Pedotransfer studies in Poland , 2004 .

[70]  Y. Pachepsky,et al.  Comparison Of Fractal Dimensions Estimated From Aggregate Mass-size Distribution And Water Retention Scaling , 1999 .

[71]  W. E. Larson,et al.  Estimating soil water retention characteristics from particle size distribution, organic matter percent, and bulk density , 1979 .

[72]  M. Tapkenhinrichs,et al.  Evaluation of Pedo-Transfer Functions , 1993 .

[73]  M. Imhof,et al.  Modelling and prediction of soil water contents at field capacity and permanent wilting point of dryland cropping soils , 2011 .

[74]  Laj R. Ahuja,et al.  Estimating Soil Water Characteristics from Simpler Properties or Limited Data 1 , 1985 .

[75]  Budiman Minasny,et al.  Comparison of different approaches to the development of pedotransfer functions for water-retention curves , 1999 .

[76]  Nader Fathianpour,et al.  Neural network models to predict cation exchange capacity in arid regions of Iran , 2005 .

[77]  Uygar Özesmi,et al.  An artificial neural network approach to spatial habitat modelling with interspecific interaction , 1999 .

[78]  Y. Pachepsky,et al.  Data Assimilation with Soil Water Content Sensors and Pedotransfer Functions in Soil Water Flow Modeling , 2012 .

[79]  W. J. Rawls,et al.  Agricultural Management Effects on Soil Water Processes Part I: Soil Water Retention and Green and Ampt Infiltration Parameters , 1983 .

[80]  N. Nariman-Zadeh,et al.  Estimating Water Retention with Pedotransfer Functions Using Multi-Objective Group Method of Data Handling and ANNs , 2011 .

[81]  R. Walczak,et al.  Modeling of soil water retention curve using soil solid phase parameters , 2006 .

[82]  H. Akaike.  A new look at the statistical model identification , 1974 .

[83]  H. Cresswell,et al.  Estimation of Soil Hydraulic Properties , 2007 .