Issues‎ > ‎vol22n1‎ > ‎


Prediction of Crack Porosity from Other Easily Soil Properties Using Ridge Regression Analysis


Shadan H. Khurshid1


1Department of Natural Resources, College of Agricultural Engineering Sciences, University of Sulaimani, Sulaimani,Kurdistan Region-Iraq.


Original: 18  August 2019       Revised: 6 January 2019      Accepted: 30 January 2020         Published online: 20 June 2020  

Doi Link


The development of accurate, easy, and low-cost method to determine soil cracks porosity (SCP) is important in the evaluation of ecosystem to manage the hydrological, erosional, and geochemical cycles. Indeed, these procedures are cumbersome, time-and energy-consuming, and costly. Accordingly, intensive efforts are being made to formulate a high-performance model to estimate SCPPedotransfer functions (PTFs) have often been developed using multiple linear regression models with no distinction about their involvement in multicollinearity. The paper was focused on ridge regression (RR) to overcome multicollinearity problems via regularizing the regression coefficients by imposing a penalty on their magnitudes. In the application of RR,choosing the ridge parameter (k) is important to control the amount of shrinkage of the regression coefficients. A total of 61 soil samples were analyzed from different land uses (forest, cropland, and pasture) inIraqi Kurdistan Region. Eighty-two percent of the soil sampleswere selected as the training set, and the rest of 11 soil samples (18%) were used as the testing set. Threemethods of modeling regression (simple linear regression SLR, multiple linear regression MLR, and ridge regression RR) were used to formulate accurate PTFs for predicting SCP. The results clearly showed multicollinearity problem (wrong sing and value of regression coefficient) in SMR and the most of MLR; therefore,they are not recommended to be used in predicting SCP. Soil crack porosity was positively correlated with each of clay (C), liquid limit (LL), plastic limit (PL), and percent of shrinkage limit (PLS). While, the most influential variable for predicting SCP is liquid limit (RMSE=126.194 cm2 m-2; adj.R2=0.884). The best model (RMSE=122.786 cm2 m-2, adj. R2=0.891) to predict SCP among all the models is formulated by RR technique when k=0.31395 which gave the lowest intercept value with very low VIF (0.582).

Key Words: Ridge regression, multicollinearity, Soil crack porosity.


[1] Khurshid, Sh.H., "Characterization of cracked soils and strategies for their management in Sulaimani Governorate", PhD dissertation, University of Sulaimani, Sulaimani. (2010).

[2] Stirling, R.A., Davie, C.T., and Glendinning, S., "Numerical modeling of desiccation crack induced permeability", 18th International Conference on Soil Mechanics and Geotechnical Engineering, pp. 813-816, Paris. (2013).

[3] Mitchell, J.K., "Fundamentals of Soil Behavior", John Wiley and Sons, Inc., New York, NY. (1993).

[4] Nahlawi, H. and Kodikara, J.K., "Laboratory experiments on desiccation cracking of thin soil layers", Geotechnical and Geological Engineering. Vol. 24, pp. 1641–1664. (2006).

[5] Omer, M.E.T., and Mohd, R.T., "Cracks in Soils Related to Desiccation and Treatment", Australian Journal of Basic and Applied Sciences, pp. 1080-1089, Malaysia. (2011).

[6] Reeve, M.J., Hall, D.G.M., and Bullock, P., "The effect of soil composition and environmental factors on the shrinkage of some clayey British soils", European Journal of soil scienc. Vol. 31, No. 3, pp. 429- 442. (1980).

[7] Karim, T.H., and Khalid, A.S., "Survey on different soil properties in northern Iraq". (2000).

[8] Gray, C.W. and Allbrook, R., "A relationship between shrinkage induces and soil properties in some New Zealand soils", Geoderma. Vol. 108, No. 3-4, pp. 287-299. (2002).

[9] Tang, Ch., Bin, Sh., Liu, Ch., Zhao, L., and Wang, B., "Influencing factors of geometrical structure of surface shrinkage cracks in clayey soils", Engineering geology. Vol. 101, No. 3-4, pp. 17. (2008).

[10] Fattah, M.A., Khurshid Sh. H., and Ahmad R. A., "Soil Cracking Depth as Influenced By Soil Physical Properties", Special Issue, 2nd Int. Conference of Agricultural Sciences. Journal of Zankoi Sulaimani. pp. 105-114. (2018).

[11] Maulood. Y. I., "Control of Cracks due to Drying Shrinkage of an Expansive Soil Using Different Drying Mechanisms and Filler Additive", Zanco Journal of Pure and Applied Sciences. Vol. 27, No.  1, pp. 31-40. (2015).

[12] Alvis, A. and Marcelo, S., "Analysis of Cracking Behavior of Drying Soil", 2nd International Conference on Environmental Science and Technology. IPCBEE, 6, 66-69, IACSIT Press, Singapore. (2011).

[13] Yesiller, N., Miller, C. J.,Inci, G. and Yaldo, K., "Desiccation and cracking behaviour of three compacted landfill liner soils", Wayne State University, Department of Civil. and Environmental Engineering, Detroit, USA. (2000).

[14] Huawang, S., "Application of Unascertained Measure to Classification of Expansive Soils", International Colloquium on Computing, Communication, Control, and Management, ISECS, pp. 57-60, China. (2009).

[15] Masto, R.E., Sheik, S., Nehru, G., Selvi, V.A., George, J., Ram, L.C., "Assessment of environmental soil quality around SonepurBazari mine of Raniganj coalfield, India", Solid Earth Vol. 6, No. 3, pp. 811–821. (2015).

[16] Van Leeuwen, J.P., Lehtinen, T., Lair, G.J., Bloem, J., Hemerik, L., Ragnarsdóttir, K.V., Gísladóttir, G., Newton, J.S., de Ruiter, P.C., "An ecosystem approach to assess soil quality in organically and conventionally managed farms in Iceland and Austria", Soil Vol. 1, pp. 83–101. (2015).

[17] Costa, J.L., Aparicio, V., Cerdà, A., "Soil physical quality changes under different management systems after 10 years in the Argentine humid pampa", Solid Earth Vol. 6, No. 1, pp. 361–371. (2015).

[18] Pulido, M.M., Gabriels, D., Cornelis, W., Lobo, D., "Comparing aggregate stability tests for soil physical quality indicators", Land Degradation and deployment. Vol. 26, No. 8, pp. 843–852. (2015).

[19] Frisch, R., "Statistical Confluence Analysis by Means of Complete Regression Systems", Oslo: University Institute of Economics, Publication No. 5. (1934). Cited from [Spyroglou I., Chatzimichail, E.Spanou, E.N. Paraskakis, E. andRigas, A., "Ridge regression and bootstrapping in asthma prediction", Conference Paper, New Developments in Pure and Applied Mathematics. (2015).

[20] Pimentel, E. CG., Queiroz, S A. Carvalheiro, R. Fries, L. A., "Use of ridge regression for the prediction of early growth performancein crossbred calves", Genetics and Molecular Biology. Vol. 30, No. 3, pp. 536-544. (2007).

[21] O’brien R.M., "A caution regarding rules of thumb for variance inflation factors", Quality and Quantity. Vol. 41, pp. 673–690. (2007).

[22] Klute, A., "Methods of Soil Analysis", Part 1. 2nded. Agron.Monogr. 9. ASA and SSSA. Madison. WI. (1986).

[23] ASTM-D423. "American Society for testing and materials", 1916 Race street, Phiadelphia, P.A, 19103. (1986).

[24] ASTM-D424., "American Society for testing and materials",1916 Race street, Phiadelphia, P.A, 19103. (1986).

[25] British Standards Institution BS 1377., "Methods of test for soils for civil  engineering purposes", 2 Park Street, London. (1975).

[26] Blake, G.R. and K.H. Hartge, "Bulk density. In method of soil analysis", Part 1: Physical and mineralogical methods. 2nd. edited by A.Klute. pp. 363-375. (1986).

[27] Rowell, D.L., "Soil Science: Methods and applications", Longman Group UK Limited. pp. 50-51. (1996).

[28] Nelson, D. W. and Sommers, L. E., "Total carbon, organic carbon and organic matter", p. 539-580, In: page, A.L., Miller, R.H. and Keeney, D.R. (eds) "Methods of soil analysis" part 2. Chemical and microbiological properties.Agron.Monogr.9 ASA Madison, WI. (1982).

[29] Page, A.L., Miller, R.H. and Keeney, D.R., "Methods of soil analysis", part 2. Chemical and microbiological properties.2nd edition Agronomy No.9.ASA, Madison, Wisconsin USA. (1982).

[30] Fattah, M., A., "Some practical tests to reduce seepage from earthen ponds for different texture soils", MSC. Thesis, University of Salahaddin, College of Agriculture, Soil and water science department. (2004).

[31] Sharma, P. K., T. S. Verma, and R. M. Bhagat, "Soil structural improvements with addition of lantana Camara biomass in rice-wheat cropping", Soil use and management, Vol. 11, pp. 199-203. (1995).

[32] Dasog, G. S., Acton, D. I., Mermute, A. R., de Jong, E., "Shrink-swell potential and cracking in clay soils of Saskatchewan"Canadian Journalof Soil Science. Vol. 68, pp. 251-260. (1988).

[33] Dasog, G. S. and G. B. Shashidhara."Measurements of cracking intensity in a vertisol under different crop cover", Soil Science. Vol. 156, pp. 424-428. (1993).

[34] Novak, V., "Soil crack characteristics-estimation methods applied to heavy soils in the NOPEX area", Inst. Of hydrology, Slovak academy of Sci. P. O. Box 94, Racianska 75, 830 08 Bratislava, Slovak Republic.Agr.And Forest Meteorology Vol. 98-99. pp. 501-507. (1999).

[35] Novak, V., J. Simunek, and M. Th., van Genuchten, "Infiltration of water in to soil with cracks", J. of Irr. And Drain., Eng., ASCE, Vol. 126, pp. 41-47. (2000).

[36] Sequeira, C.H., Wills, S.A., Seybold, C.A., West, L.T., "Predicting soil bulk density for incomplete databases",Geoderma. Vol. 213, pp. 64–73. (2014).

[37] Hoerl, A.E. and Kennard, R.W., "Ridge Regression: Biased estimates for non-orthogonal problems",Technometrics. Vol. 12, No. 55, pp. 55–67. (1970).

[38] Cessie, S. Le and Van Houwlingen, J. C., "Ridge Estimators in Logistic Regression", Journal of the Royal Statistical Society. Vol.41, No. 1, pp. 191–201. (1992).

[39]Hair Jr JF, Anderson RE, Tatham RL and Black WC, "Multivariate Data Analysis", 3rdedition. Macmillan Publishing Company, New York, pp.544. (1992).

[40] Draper NR.and Smith H., "Applied Regression Analysis", 3rdedition. John Wiley & Sons, New York, pp.706 (1998).

[41] Wilding, L.P., "Spatial variability: Its documentation, accommodation and implication to soil surveys", In: D.R. Nielson and J. Bouma,editors, Soil spatial variability. Pudoc, Wageningen, Netherlands. pp.166–196. (1985).