Support Vector Machine and regression analysis to predict the field hydraulic conductivity of sandy soil
Tóm tắt
Saturated hydraulic conductivity is one of the key parameters in soil physics and hydrological modeling. This study explores the use of Support Vector Machine (SVM) and a nonlinear statistical regression approach for the purpose of predicting the field saturated soil hydraulic conductivity (Kfield) of sandy soil based on basic soil properties of saline and alkaline soil data sets. Considering the significance of soil properties, both methods used the following levels of input soil data, which are easily measurable in the laboratory: hydraulic conductivity, clay/silt ratio, liquid limit, hydro carbonate anions, chloride ions, and calcium carbonate content. The influence of three kernel functions (linear, radial basis and sigmoid) on the performance of the SVM model was investigated. An adaptive genetic algorithm is used to determine the optimal free parameters of the SVM models. The results indicated that the SVM with the RBF model has better accuracy compared to the linear- and sigmoid-based models. The RBF model performed satisfactorily with a modeling efficiency of 0.972 and a correlation coefficient of 0.976. According to all of the performance measures, the different SVM models are a powerful tool and have better performance than statistical regression models. The excellent performance of the SVM with the RBF model demonstrated its potential to function as a useful tool for the indirect estimation of Kfield to assess maximum obtainable prediction accuracy.
Tài liệu tham khảo
Abdel Hadi, A. M., Elbisy, M. S., and Ali, H. (2002). “Estimating the saturated soil hydraulic conductibility from easily measurable soil properties.” III Regional Conference on Civil Engineering, ASCEEGS, Cairo, Egypt.
Agyare, W. A., Park, S. J., and Vlek, P. L. (2007). “Artificial neural network estimation of saturated hydraulic conductivity.” Vadose Zone J., Vol. 6, No. 2, pp. 423–431.
Aronovici, V. S. (1947). “The mechanical analysis as an index of subsoil permeability.” Proc., Soil Science Society of American, Vol. 11, No. C, pp. 137–141, DOI: 10.2136/sssaj1947.036159950011000C0026x.
Arshad, R., Sayyad, G., Mosaddeghi, M., and Gharabaghi, B. (2013). “Predicting saturated hydraulic conductivity by artificial intelligence and regression models” ISRN Soil Science, Hindawi Publishing Corporation, Vol. 2013, pp. 1–8, DOI: org/10.1155/2013/308159.
Benson, C. H., Zhai, H., and Wang, X. (1994). “Estimating of hydraulic conductivity of compacted clay liners.” J. Geotechnical Engineering, ASCE, Vol. 120, No. 2, pp. 366–387, DOI: 10.1061/(ASCE)0733-9410(1994)120:2(366)
Cawley, G. C. and Talbot, N. L. C. (2004). “Fast exact leave-one-out cross-validation of sparse least-squares support vector machines.” Neural Networks, Vol. 17, No. 10, pp. 1467–1475, DOI: 10.1016/j.neunet.2004.07.002
Cristianini, N., Campell, C., and Shawe-Taylor, J. (1998). Dynamically adapting kernels in support vector machines, NeuroCOLTH Technical Report NC-TR-98-017, Royal Holloway Collage, University of London, UK.
Das, S. K., Samui, P., and Sabat, A. K. (2012). “Prediction of field hydraulic conductivity of clay liners using an artificial neural network and support vector machine.” International Journal of Geomechanics, Vol. 12, No. 5, pp. 606–6011, DOI: 10.1061/(ASCE)GM.1943-5622.0000129.
Elbisy, M. S. (2006). “Prediction of saturated hydraulic conductivity of sandy soil using neural network.” Ain Shams Engineering Journal, Ain Shams University, Vol. 41, No. 1, pp. 480–493.
Elhakeem, M., Chang, Y., Wilson, C. G., and Papanicolaou, A. N. (2009). Field measurement of saturated hydraulic conductivity at the hillslope scale under different soil series and management practices, AGU 2009 Fall Meeting, San Francisco, California.
Erzin, Y., Gumaste, S. D., Gupta, A. K., and Singh, D. N. (2009). “Artificial Neural Network (ANN) models for determining hydraulic conductivity of compacted fine-grained soils.” Canadian Geotechnical Journal, Vol. 46, No. 8, pp. 955–968, DOI: 10.1139/T09-035.
Ghulman, B., Elbisy, M. S., and Abdel Hadi, A. M. (2011). “Effect of soil properties on the saturated hydraulic conductivity of some Egyptian problematic soils.” International Conference on Advances and Trends in Engineering Materials and their Applications, Canada.
Goldberg, D. E. (1998). Genetic algorithms in search optimization and machine learning, Addison-Wesley Longman, New York.
Gupta, R. K., Rudra, R. P., Dickinson, W. T., Patni, N. K., and Wall, G. J. (1993). “Comparison of saturated hydraulic conductivity measured by various field methods.” Transactions of the ASAE, Vol. 36, No. 1, pp. 51–55, DOI: 10.13031/2013.28313.
Hack-ten Broke, M. J. D. and Hegmans, J. H. B. (1996). “Use of soil physical characteristics from laboratory measurements or standard series for modeling unsaturated water flow.” Agricultural Water Management, Vol. 29, No. 2, pp. 201–213, DOI: 10.1016/0378-3774(95)01190-0.
Lamorski, K., Pachepsky, Y., Slawihski, C., and Walczak, R. T. (2008). “Using support vector machines to develop pedotransfer functions for water retention of soils in Poland.” Soil Science Society of America Journal, Vol. 72, No. 5, pp. 1243–1247, DOI: 10.2136/sssaj2007.0280N.
Libardi, P. L., Reichardt, K., Nielsen, D. R., and Biggar, J. W. (1980). “Simple field method for estimating soil hydraulic conductivity.” Soil Science Society of America Journal, Vol. 44, pp. 3–7, DOI: 10.2136/sssaj1980.03615995004400010001x.
Merdun, H., Cinar, O., Meral, R., and Apan, M. (2006). “Comparison of artificial neural network and regression pedotransfer functions for prediction of soil water retention and saturated hydraulic conductivity.” Soil and Tillage Research, Vol. 90 No. 1–2, pp. 108–116, DOI: 10.1016/j.still.2005.08.011.
Minasny, B. and Perfect, E. (2004). “Solute adsorption and transport parameters.” Development of Pedotransfer Functions in Hydrology, Elsevier, Amsterdam, pp. 195–224.
Mohanty, B. P., Kanvar, R. S., and Everts, C. J. (1994). “Comparison of saturated hydraulic conductivity measurement methods for a glacialtill soil.” Soil Science Society of America Journal, Vol. 58, No. 3, pp. 672–677, DOI: 10.2136/sssaj1994.03615995005800030006x.
Nakhaei, M. (2005). “Estimating the saturated hydraulic conductivity of granular material using artificial neural network based on grain size distribution curve.” J. Sci. Islam Repub. Iran, Vol. 16, No. 1, pp. 55–62.
Reynolds, W. D. and Elrick, D. E. (1991). “Determination of hydraulic conductivity using a tension infiltrometer.” Soil Science Society of America Journal, Vol. 55, No. 3, pp. 633639, DOI: 10.2136/sssaj1991.03615995005500030001x
Reynolds, W. D. and Zebchuk, W. D. (1996). “Hydraulic conductivity in a clay soil: Two measurement techniques and spatial characterization.” Soil Science Society of America Journal, Vol. 60, No. 6, pp. 1679–1685, DOI: 10.2136/sssaj1996.03615995006000060011x.
Rogiers, B., Mallants, D., Batelaan, O., Gedeon, M., Huysmans, M., and Dassargues, A. (2012). “Estimation of hydraulic conductivity and its uncertainty from grain-size data using GLUE and artificial neural networks.” Math Geosci, Vol. 44, pp. 739–763, DOI: 10.1007/s11004-012-9409-2.
Schwab, G. O., Frangmeier, D. D., and Elliot, W. J. (1996). Soil and water management systems, John Wiley & Sons, New York.
Smedema, L. K. and Rycrofrt, D. W. (1983). Land drainage: Planning and design of agricultural drainage systems, Batsford Academic Educational Ltd., London, 376 pp.
Taskinen, A., Sirviö, H., and Bruen, M. (2008). “Generation of two dimensionally variable saturated hydraulic conductivity fields: Model theory, verification and computer program.” Computers & Geosciences, Vol. 34, No. 8, pp. 876–890, DOI: 10.1016/j.cageo.2007.04.010.
Tayfur, G., Nadiri, A., and Moghaddam, A. (2014). “Supervised intelligent committee machine method for hydraulic conductivity estimation” Water Resour. Manage., Vol. 28, pp. 1173–1184, DOI: 10.1007/s11269-014-0553-y.
Vapnik, V. N. (1995). The nature of statistical learning theory, John Wiley & Sons, New York.
Vapnik, V., Golowich, S., and Smola, A. (1997). “Support vector method for function approximation, regression estimation, and signal processing.” Advances in Neural Information Processing Systems 9, MA, MIT Press, Cambridge, pp. 281–287.
Wösten, J. H. M. and Van Genuchten, M. Th. (1988). “Using texture and other soil properties to predict the unsaturated soil hydraulic functions” Soil Science Society of America Journal, Vol. 52, pp. 1762–1770, No. 6, DOI: 10.2136/sssaj1988.03615995005200060045x.