Prediction of soil clay minerals from some soil properties with use of feature selection algorithm and ANFIS methods
Mahdi Najafi-Ghiri![https://orcid.org/0000-0003-0401-7566](/media/client/orcid_16x16.png)
A Department of Soil Science, College of Agriculture and Natural Resources of Darab, Shiraz University, Iran.
B Department of Range and Watershed Management, College of Agriculture and Natural Resources of Darab, Shiraz University, Iran.
C Department of Soil Science, College of Agriculture, Yasouj University, Iran.
D Corresponding author. Email: mnajafighiri@yahoo.com
Soil Research 57(7) 788-796 https://doi.org/10.1071/SR18352
Submitted: 26 November 2018 Accepted: 13 May 2019 Published: 10 July 2019
Abstract
Researchers use different methods to investigate and quantify clay minerals. X-ray diffraction is a common and widespread approach for clay mineralogy investigation, but is time-consuming and expensive, especially in highly calcareous soils. The aim of this research was prediction of clay minerals in calcareous soils of southern Iran using a feature selection algorithm and adaptive neuro-fuzzy inference system (ANFIS) methods. Fifty soil samples from different climatic regions of southern Iran were collected and different climatic, soil properties and clay minerals were determined using X-ray diffraction. Feature selection algorithms were used for selection of the best feature subset for prediction of clay mineral types along with two sets of training and testing data. Results indicated that the best feature subset by Best-First for prediction of illite was cation exchange capacity (CEC), sand, total potassium, silt and agroclimatic index (correlation coefficient (R) = 0.99 for training and testing data); for smectite was precipitation, temperature, evapotranspiration and CEC (R = 0.89 and 0.87 for training and testing data respectively); and for palygorskite was precipitation, temperature, evapotranspiration and calcium carbonate equivalent (CCE) (R = 0.98 for training and testing data). An attempt was made to predict clay minerals type by ANFIS using selected data from the feature selection algorithm. The evaluation of method by calculating root mean square error (RMSE), mean absolute error (MAE) and R indicated that the ANFIS method may be suitable for illite, chlorite, smectite and palygorskite prediction (RMSE, MAE and R of 0.001–0.028, 0.004–0.012 and 0.67–0.89 respectively for training and testing data). Comparison of data for all clay minerals showed that ANFIS method did not predict illite and chlorite as well as other minerals in the studied soils.
Additional keywords: ANFIS method, clay mineralogy, feature selection algorithm, soil properties.
References
Al-Hamed S, Wahby M, Al-Sulaiman M, Aboukarima A (2014) Prediction of soil fractions (sand, silt and clay) in surface layer based on natural radionuclides concentration in the soil using adaptive neuro fuzzy inference system. Open Journal of Soil Science 4, 215| Prediction of soil fractions (sand, silt and clay) in surface layer based on natural radionuclides concentration in the soil using adaptive neuro fuzzy inference system.Crossref | GoogleScholarGoogle Scholar |
Aqil M, Kita I, Yano A, Nishiyama S (2007) A comparative study of artificial neural networks and neuro-fuzzy in continuous modeling of the daily and hourly behaviour of runoff. Journal of Hydrology 337, 22–34.
| A comparative study of artificial neural networks and neuro-fuzzy in continuous modeling of the daily and hourly behaviour of runoff.Crossref | GoogleScholarGoogle Scholar |
Banaei M (1998) ‘Soil moisture and temperature regime map of Iran.’ (Soil and Water Research Institute, Ministry of Agriculture, Iran)
Bui MD, Kaveh K, Penz P, Rutschmann P (2015) Contraction scour estimation using data-driven methods. Journal of Applied Water Engineering and Research 3, 143–156.
| Contraction scour estimation using data-driven methods.Crossref | GoogleScholarGoogle Scholar |
Dash M, Liu H (1997) Feature selection for classification. Intelligent data analysis 1, 131–156.
| Feature selection for classification.Crossref | GoogleScholarGoogle Scholar |
Dash M, Liu H (2003) Consistency-based search in feature selection. Artificial Intelligence 151, 155–176.
| Consistency-based search in feature selection.Crossref | GoogleScholarGoogle Scholar |
Dixon JB, Weed SB, Parpitt R (1990) Minerals in soil environments. Soil Science 150, 562
| Minerals in soil environments.Crossref | GoogleScholarGoogle Scholar |
Gee GW, Or D (2002) Particle size analysis. In ‘Methods of soil analysis. Part 4 - Physical methods’. (Ed. DL Sparks) pp. 255–293. (Soil Science Society of America: Madison, WI, USA)
Helmke PA, Sparks DL, Page AL, Loeppert RH, Soltanpour PN, Tabatabai MA, Johnston CT, Sumner ME (1996) Lithium, sodium, potassium, rubidium, and cesium. In ‘Methods of soil analysis. Part 3 -Chemical methods’. (Ed. DL Sparks) pp. 551–574. (American Society of Agronomy-Soil Science Society of America: Madison, WI, USA)
Jackson ML (2005) ‘Soil chemical analysis: advanced course.’ (UW-Madison Libraries Parallel Press: Madison, WI)
Jang JS (1993) ANFIS: adaptive-network-based fuzzy inference system. IEEE Transactions on Systems, Man, and Cybernetics 23, 665–685.
| ANFIS: adaptive-network-based fuzzy inference system.Crossref | GoogleScholarGoogle Scholar |
Jang, J-SR, Sun, C-T, Mizutani, E (1997) Neuro-fuzzy and soft computing; a computational approach to learning and machine intelligence. (Prentice-Hall: Englewood Cliffs, NJ)
Johns WD, Grim RE, Bradley WF (1954) Quantitative estimations of clay minerals by diffraction methods. Journal of Sedimentary Research 24, 242–251.
Keshavarzi A, Sarmadian F, Labbafi R, Vandechali MR (2011) Modeling of soil cation exchange capacity based on fuzzy table look-up scheme and artificial neural network approach. Modern Applied Science 5, 153–164.
| Modeling of soil cation exchange capacity based on fuzzy table look-up scheme and artificial neural network approach.Crossref | GoogleScholarGoogle Scholar |
Khormali F, Abtahi A (2003) Origin and distribution of clay minerals in calcareous arid and semi-arid soils of Fars Province, southern Iran. Clay Minerals 38, 511–527.
| Origin and distribution of clay minerals in calcareous arid and semi-arid soils of Fars Province, southern Iran.Crossref | GoogleScholarGoogle Scholar |
Kim M, Gilley JE (2008) Artificial Neural Network estimation of soil erosion and nutrient concentrations in runoff from land application areas. Computers and Electronics in Agriculture 64, 268–275.
| Artificial Neural Network estimation of soil erosion and nutrient concentrations in runoff from land application areas.Crossref | GoogleScholarGoogle Scholar |
Kittrick J, Hope E (1963) A procedure for the particle-size separation of soils for X-ray diffraction analysis. Soil Science 96, 319–325.
| A procedure for the particle-size separation of soils for X-ray diffraction analysis.Crossref | GoogleScholarGoogle Scholar |
Loppert RH, Suarez M (1996) Carbonate and gypsum. In ‘Methods of soil analysis. Part 3 - Chemical methods’. (Ed. DL Sparks) pp. 437–474. (American Society of Agronomy-Soil Science Society of America: Madison, WI, USA)
Mehra O, Jackson M (1960) Iron oxide removal from soils and clays by a dithionite–citrate system buffered with sodium bicarbonate. In ‘Clays and clay minerals’. (Ed. E Ingerson) pp. 317–327. (Pergamon Press)
Merdun H, Çınar Ö, Meral R, Apan M (2006) Comparison of artificial neural network and regression pedotransfer functions for prediction of soil water retention and saturated hydraulic conductivity. Soil & Tillage Research 90, 108–116.
| Comparison of artificial neural network and regression pedotransfer functions for prediction of soil water retention and saturated hydraulic conductivity.Crossref | GoogleScholarGoogle Scholar |
Millot G (2013) ‘Geology of clays: weathering· sedimentology· geochemistry.’ (Springer Science & Business Media: Vienna, Austria)
Nahafi-Ghiri M, Abtahi A, Hashemi SS (2012) Palygorskite distribution along a soil climosequence derived from calcareous parent materials in southern Iran. In ‘8th International Soil Science Congress on Land Degradation and Challenges in Sustainable Soil Management, 15–17 May 2012, Çesme-İzmir/Turkey at Ege University’. (Soil Science Society of Turkey)
Najafi-Ghiri M (2010) Study of morphological and mineralogical properties and potassium status of soils of Fars Province. PhD Thesis, Department of Soil Science, Shiraz University, Iran.
Najafi-Ghiri M, Abtahi A (2013) Potassium fixation in soil size fractions of arid soils. Soil and Water Research 8, 49–55.
| Potassium fixation in soil size fractions of arid soils.Crossref | GoogleScholarGoogle Scholar |
Najafi-Ghiri M, Abtahi A, Jaberian F (2011) Factors affecting potassium release in calcareous soils of southern Iran. Soil Research 49, 529–537.
| Factors affecting potassium release in calcareous soils of southern Iran.Crossref | GoogleScholarGoogle Scholar |
Najafi-Ghiri M, Niazi M, Khodabakhshi M, Boostani H, Owliaie H (2019) Mechanisms of potassium release from calcareous soils to different salt, organic acid and inorganic acid solutions. Soil Research 57, 301–309.
| Mechanisms of potassium release from calcareous soils to different salt, organic acid and inorganic acid solutions.Crossref | GoogleScholarGoogle Scholar |
Naseriparsa M, Bidgoli A-M, Varaee T (2014) A hybrid feature selection method to improve performance of a group of classification algorithms. International Journal of Computer Applications 69, 28–35.
Nelson DW, Sommers LE (1996) Total carbon, organic carbon, and organic matter. In ‘Methods of soil analysis. Part 3 - Chemical methods’. (Ed. DL Sparks) pp. 961–1010. (American Society of Agronomy-Soil Science Society of America: Madison, WI, USA)
Owliaie H, Abtahi A, Heck R (2006) Pedogenesis and clay mineralogical investigation of soils formed on gypsiferous and calcareous materials, on a transect, southwestern Iran. Geoderma 134, 62–81.
| Pedogenesis and clay mineralogical investigation of soils formed on gypsiferous and calcareous materials, on a transect, southwestern Iran.Crossref | GoogleScholarGoogle Scholar |
Paquet H, Millot G (1972) Geochemical evolution of clay minerals in the weathered products in soils of Mediterranean climate. In ‘Proceedings of the International Clay Conference 1927, Madrid, Spain’ (Ed. JM Serratosa) pp. 199–206.
Rhoades JD (1996) Salinity: electrical conductivity and total dissolved solids. In ‘Methods of Soil Analysis. Part 3 - Chemical methods’. (Ed. DL Sparks) pp. 417–435. (American Society of Agronomy-Soil Science Society of America: Madison, WI, USA)
Sumner ME, Miller WP (1996) Cation exchange capacity and exchange coefficients. In ‘Methods of soil analysis. Part 3 - Chemical methods’. (Ed. DL Sparks) pp. 1201–1229. (American Society of Agronomy-Soil Science Society of America: Madison, WI, USA)
Tang L, Zeng G, Nourbakhsh F, Shen GL (2009) Artificial neural network approach for predicting cation exchange capacity in soil based on physico-chemical properties. Environmental Engineering Science 26, 137–146.
| Artificial neural network approach for predicting cation exchange capacity in soil based on physico-chemical properties.Crossref | GoogleScholarGoogle Scholar |
Tekin E, Akbas S (2011) Artificial neural networks approach for estimating the groutability of granular soils with cement-based grouts. Bulletin of Engineering Geology and the Environment 70, 153–161.
| Artificial neural networks approach for estimating the groutability of granular soils with cement-based grouts.Crossref | GoogleScholarGoogle Scholar |
Thomas GW (1996) Soil pH and soil acidity. In ‘Methods of soil analysis. Part 3 - Chemical methods’. (Ed. DL Sparks) pp. 475–490. (American Society of Agronomy-Soil Science Society of America: Madison, WI, USA)
Yetilmezsoy K, Demirel S (2008) Artificial neural network (ANN) approach for modeling of Pb (II) adsorption from aqueous solution by Antep pistachio (Pistacia vera L.) shells. Journal of Hazardous Materials 153, 1288–1300.
| Artificial neural network (ANN) approach for modeling of Pb (II) adsorption from aqueous solution by Antep pistachio (Pistacia vera L.) shells.Crossref | GoogleScholarGoogle Scholar | 17980484PubMed |
Yilmaz I, Kaynar O (2011) Multiple regression, ANN (RBF, MLP) and ANFIS models for prediction of swell potential of clayey soils. Expert Systems with Applications 38, 5958–5966.
| Multiple regression, ANN (RBF, MLP) and ANFIS models for prediction of swell potential of clayey soils.Crossref | GoogleScholarGoogle Scholar |
Zorluer I, Icaga Y, Yurtcu S, Tosun H (2010) Application of a fuzzy rule-based method for the determination of clay dispersibility. Geoderma 160, 189–196.
| Application of a fuzzy rule-based method for the determination of clay dispersibility.Crossref | GoogleScholarGoogle Scholar |