Determining the features influencing physical quality of calcareous soils in a semiarid region of Iran using a hybrid PSO-DT algorithm

Soil physical quality indicators (SPQIs) are used to make complex information more accessible to decision makers; however, their site-specific nature may restrict their applicability only to a specific soil type and/or management system. Therefore, it would be advantageous if such indicators could be predicted indirectly from easily available soil properties using inexpensive methods. In this study, we introduce a hybrid algorithm, specifically designed to work with optimized decision tree with particle swarm optimization (PSO-DT), for the prediction of SPQIs (i.e., air capacity, AC; plant-available water capacity, PAWC; and relative field capacity, RFC). The potential power of using the PSO-DT algorithm in setting up a framework for identifying the most determinant parameters affecting the physical quality of agricultural soils in a semiarid region of Iran (Baft plain, 29° 11′ to 29° 13′ N and 56° 34′ to 56° 38′ E) was also investigated. An empirical multiple linear regression (MLR) model was constructed as benchmark for the comparison of performance. In results, a permutation of five input features, including soil organic matter (SOM), electrical conductivity (EC), clay, sand, and bulk density (BD), was introduced by the hybrid PSO-DT algorithm as explanatory variables. Using the PSO-DT method resulted in higher model efficiency and coefficient of determination (R2) than the MLR approach. The obtained R2 values for the constructed PSO-DT model for the AC, PAWC, and RFC predictions were 0.91, 0.90, and 0.96, respectively, whereas they were 0.61, 0.16, and 0.47 for the MLR-model. The SOM, clay, and sand parameters were accounted as the discriminating variables of the models constructed for the prediction of AC, PAWC, and RFC indicators, respectively. This study provides a strong basis for the prediction of SPQIs and identifying the most determinant parameters influencing the physical quality of agricultural soils in semiarid regions of Iran; however, its general analytical framework could be applied to other parts of the world with similar challenges.

[1]  B. Kay,et al.  Visual assessment of soil structure: Part II. Implications of tillage, rotation and traffic on sites in Canada, China and Germany , 2009 .

[2]  Anònim Anònim.  Keys to Soil Taxonomy , 2010 .

[3]  R. E. White,et al.  Principles and practice of soil science , 1997 .

[4]  A. Dexter,et al.  Soil Physical Quality and the Effects of Management , 2000 .

[5]  Craig F. Drury,et al.  Use of indicators and pore volume-function characteristics to quantify soil physical quality , 2009 .

[6]  Sašo Džeroski,et al.  Decision Trees in Ecological Modelling , 2011 .

[7]  G. W. Thomas.  Soil pH and Soil Acidity , 1996, SSSA Book Series.

[8]  S. Ayoubi,et al.  Feature Selection Using Parallel Genetic Algorithm for the Prediction of Geometric Mean Diameter of Soil Aggregates by Machine Learning Methods , 2014 .

[9]  Ravi Jain,et al.  D-SCIDS: Distributed soft computing intrusion detection system , 2007, J. Netw. Comput. Appl..

[10]  E. Perfect,et al.  Management versus inherent soil properties effects on bulk density and relative compaction , 1997 .

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

[12]  S. S. Andrews,et al.  DESIGNING A SOIL QUALITY ASSESSMENT TOOL FOR SUSTAINABLE AGROECOSYSTEM MANAGEMENT , 2001 .

[13]  A. Dexter.  Soil physical quality: Part II. Friability, tillage, tilth and hard-setting , 2004 .

[14]  Anthony R. Dexter,et al.  Soil physical quality: Part III: Unsaturated hydraulic conductivity and general conclusions about S-theory , 2004 .

[15]  M. R. Carter,et al.  Chapter 4 Biological attributes of soil quality , 1997 .

[16]  Wim Cornelis,et al.  Prediction of Water Retention of Soils from the Humid Tropics by the Nonparametric k‐Nearest Neighbor Approach , 2013 .

[17]  R. Anlauf,et al.  Effect of Compaction on Soil Hydraulic Parameters of Vegetative Landfill Covers , 2012 .

[18]  Michael Brady,et al.  Preface - The Changing Shape of Computer Vision , 1981, Artif. Intell..

[19]  L. N. Mielke,et al.  Microbial activity as regulated by soil water-filled pore space. , 1990 .

[20]  Pietro Rubino,et al.  Developing a soil quality index to compare soil fitness for agricultural use under different managements in the Mediterranean environment , 2013 .

[21]  D. Karlen,et al.  Identification of regional soil quality factors and indicators : I. Central and Southern High Plains , 2000 .

[22]  W. Cornelis,et al.  Data-driven analysis of soil quality indicators using limited data , 2014 .

[23]  D. W. Nelson,et al.  Total Carbon, Organic Carbon, and Organic Matter , 1983, SSSA Book Series.

[24]  Craig F. Drury,et al.  Indicators of good soil physical quality: density and storage parameters , 2002 .

[25]  C. Drury,et al.  Land management effects on the near-surface physical quality of a clay loam soil , 2007 .

[26]  D. Karlen,et al.  A framework for evaluating physical and chemical indicators of soil quality , 1994 .

[27]  R. Lal,et al.  Soil structure and management: a review , 2005 .

[28]  Siti Mariyam Shamsuddin,et al.  Particle Swarm Optimization: Technique, System and Challenges , 2011 .

[29]  Zhongbo Yu,et al.  Dual state-parameter estimation of root zone soil moisture by optimal parameter estimation and extended Kalman filter data assimilation , 2011 .

[30]  J. Rhoades.  Salinity: Electrical Conductivity and Total Dissolved Solids , 2018, SSSA Book Series.

[31]  Sašo Džeroski,et al.  Hierarchical classification of environmental factors and agricultural practices affecting soil fauna under cropping systems using Bt maize , 2007 .

[32]  Padhraic Smyth,et al.  From Data Mining to Knowledge Discovery in Databases , 1996, AI Mag..

[33]  C. Drury,et al.  Optimal soil physical quality inferred through structural regression and parameter interactions , 2008 .

[34]  Qiang Fu,et al.  Delineating soil nutrient management zones based on fuzzy clustering optimized by PSO , 2010, Math. Comput. Model..

[35]  A. Besalatpour,et al.  Estimating wet soil aggregate stability from easily available properties in a highly mountainous watershed , 2013 .

[36]  R. Eberhart,et al.  Comparing inertia weights and constriction factors in particle swarm optimization , 2000, Proceedings of the 2000 Congress on Evolutionary Computation. CEC00 (Cat. No.00TH8512).

[37]  Yubin Lan,et al.  Review: Development of soft computing and applications in agricultural and biological engineering , 2010 .

[38]  R. Nelson.  Carbonate and Gypsum , 2015 .

[39]  G. Topp,et al.  Soil Water Desorption and Imbibition: Tension and Pressure Techniques , 2007 .

[40]  D. Karlen,et al.  Identification of Regional Soil Quality Factors and Indicators II. Northern Mississippi Loess Hills and Palouse Prairie , 2000 .

[41]  M. Shukla,et al.  Determining soil quality indicators by factor analysis , 2006 .

[42]  Jimson Mathew,et al.  Runoff prediction using an integrated hybrid modelling scheme , 2009 .

[43]  M. Arshad,et al.  Identifying critical limits for soil quality indicators in agro-ecosystems , 2002 .

[44]  Alberto Maria Segre,et al.  Programs for Machine Learning , 1994 .

[45]  Riccardo Poli,et al.  Particle swarm optimization , 1995, Swarm Intelligence.

[46]  Douglas L. Karlen,et al.  The Soil Management Assessment Framework , 2004 .

[47]  Xu Yang,et al.  Estimating Parameters of Van Genuchten Model for Soil Water Retention Curve by Intelligent Algorithms , 2013 .

[48]  A. K. Misra,et al.  Long-term continuous cropping, fertilisation, and manuring effects on physical properties and organic carbon content of a sandy loam soil , 2006 .

[49]  D. Archer,et al.  EFFECT OF ORGANIC CARBON ON AVAILABLE WATER IN SOIL , 2005 .