Current Science

Open Access Open Access  Restricted Access Subscription Access

Modelling Soil Cation Exchange Capacity in Different Land-Use Systems using Artificial Neural Networks and Multiple Regression Analysis


Affiliations
1 Rain Forest Research Institute, Jorhat - 785 001, India
2 Soil Sciences Department, College of Food and Agricultural Sciences, King Saud University, P.O. Box 2460, Riyadh 11451, Saudi Arabia
 

Cation exchange capacity (CEC), as an important indicator of soil quality, represents the ability of the soil to hold positively charged ions. In this study, CEC was successfully predicted using different statistical methods, including artificial neural networks (ANNs) involving multi-layer perceptron (MLP), radial basis function (RBF), multiple linear regression (MLR) and nonlinear regression (NLR). About 293 soil samples were collected from North East India, which are under three land uses (shifting agriculture (jhum), forest and cash crops). Also, 70% of the samples (205 samples) was selected as the calibration set and the remaining 30% (88 samples) used as the prediction set. Soil pH, texture, bulk density (BD) and organic carbon (OC) were used as predictor variables to estimate CEC. The CEC-pedotransfer function (CECPTF) performance was evaluated with the coefficient of determination (R2), ischolar_main mean square error (RMSE) and standard error for the estimate (SEE) between the observed and predicted values. The results indicated that the nonlinear model (R2 = 0.91 and SEE = 1.82 for training) for cash-crop system, and RBF (R2 = 0.91 and SEE = 3.83 for training) for jhum system were the best models to estimate CEC. In contrast, RBF (R2 = 0.67 and SEE = 14.87 for training) for forest system was the worst model to estimate CEC. The results confirm that clay and OC were the most influential variables to predict CEC in the cashcrop system, whereas BD and OC were more suitable for jhum system. Although the ANNs provided suitable predictions of the entire dataset, NLR gave a formula to estimate soil CEC using commonly tested soil properties. Thus, NLR provided a reasonable estimate of CEC for most soils analysed.

Keywords

Artificial Neural Networks, Cation Exchange Capacity, Multiple Regression, Land Uses.
User
Notifications
Font Size

  • Brevik, E. C. and Sauer, T. J., The past, present, and future of soils and human health studies. Soil, 2015, 1, 35-46.

  • Lal, R., Negassa, W. and Lorenz, K., Carbon sequestration in soil. Curr. Opin. Environ. Sustain., 2015, 15, 79-86.

  • Khaledian, Y., Brevik, E. C., Pereirac, P., Cerdàd, A., Fattahe, M. A. and Tazikehf, H., Modeling soil cation exchange capacity in multiple countries. Catena, 2017, 158, 194-200.

  • Willaarts, B. A., Oyonarte, C., Muñoz-Rojas, M., Ibáñez, J. J. and Aguilera, P. A., Environmental factors controlling soil organic carbon stocks in two contrasting Mediterranean-climate areas. Land Degrad. Dev., 2016, 27, 603-611.

  • Keesstra, S. D. et al., The significance of soils and soil science towards realization of the United Nations sustainable development goals. Soil, 2016, 2, 111-128.

  • Brejda, J. J., Moorman, T. B., Karlen, D. L., Smith, J. L. and Dao, T. H., Identification of regional soil quality factors and indicators: I. Central and southern hill plains. Soil Sci. Soc. Am. J., 2000, 64, 2115-2124.

  • Van Hall, R. L., Cammeraat, L. H., Keesstra, S. D. and Zorn, M., Impact of secondary vegetation succession on soil quality in a humid Mediterranean landscape. Catena, 2017, 149, 836-843.

  • Costa, J. L., Aparicio, V. and Cerdà, A., Soil physical quality changes under different management systems after 10 years in the Argentine humid pampa. Solid Earth, 2015, 6(1), 361-371.

  • Pulido, M. M., Gabriels, D., Cornelis, W. and Lobo, D., Comparing aggregate stability tests for soil physical quality indicators. Land Degrad. Dev., 2015, 26(8), 843-852; http:// dx.doi.org/10.1002/ldr.2225.

  • Larson, W. E. and Pierce, F. J., The dynamics of soil quality as a measure of sustainable management. In Defining Soil Quality for a Sustainable Environment (ed. Doran, J. W.), SSSA Spec. Pub. No. 35, ASA, CSSA and SSSA, Madison, WI, 1994, pp. 37-51.

  • Li, P., Zhang, T., Wang, X. and Yu, D., Development of biological soil quality indicator system for subtropical China. Soil Tillage Res., 2013, 126, 112-118.

  • Masto, R. E., Chhonkar, P. K., Singh, D. and Patra, A. K., Alternative soil quality indices for evaluating the effect of intensive cropping, fertilization and manuring for 31 years in the semi-arid soils of India. Environ. Monit. Assess, 2008, 136(1-3), 419-435.

  • Saidi, D., Relationship between cation exchange capacity and the saline phase of Cheliff sol. Agric. Sci., 2012, 3(3), 434-443; https://doi.org/10.4236/as.2012.33051.

  • Brevik, E. C., Soil health and productivity. In Soils, Plant Growth and Crop Production (ed. Verheye, W.), Encyclopedia of Life Support Systems (EOLSS), EOLSS Publishers, Oxford, UK, developed under the auspices of UNESCO; http://www.eolss.net

  • Mukherjee, A. and Zimmerman, A. R., Organic carbon and nutrient release from a range of laboratory-produced biochars and biochar-soil mixtures. Geoderma, 2013, 193-194, 122-130.

  • McBratney, A. B., Minasny, B., Cattle, S. R. and Vervoort, R. W., From pedotransfer function to soil inference system. Geoderma, 2002, 109, 41-73.

  • Amini, M., Abbaspour, K. C., Khademi, H., Fathianpour, N., Afyuni, M. and Schulin, R., Neural network models to predict cation exchange capacity in arid regions of Iran. Eur. J. Soil Sci., 2002, 53, 748-757.

  • Budiman, M. and Alfred, E. H., Predicting soil properties in the tropics. Earth Sci. Rev., 2011, 106, 52-62.

  • Bell, M. A. and Van Keulen, H., Soil pedotransfer functions for four Mexican soils. Soil Sci. Soc. Am. J., 1995, 59, 865-871.

  • Yukselen, Y. and Kaya, A., Prediction of cation exchange capacity from soil index properties. Clay Miner., 2006, 41, 827-837.

  • Shabani, A. and Norouzi, M., Predicting cation exchange capacity by artificial neural network and multiple linear regression using terrain and soil characteristics. Indian J. Sci. Technol., 2015, 8(28), 1-10; http://dx.doi.org/10.17485/ijst/2015/v8i28/83328.

  • Olorunfemi, E. I., Fasinmirin, T. J. and Ojo, S. A., Modeling cation exchange capacity and soil water holding capacity from basic soil properties. Eur. J. Soil Sci., 2016, 5(4), 266-274.

  • Khaledian, Y., Pereira, P., Brevik, E. C., Pundyte, N. and Paliulis, D., The influence of organic carbon and pH on heavy metals, potassium, and magnesium levels in Lithuanian Podzols. Land Degrad. Dev., 2016, 28(1), 345-354; http://dx.doi.org/10.1002/ ldr.2638.

  • Sulieman, M., Saeed, I., Hassaballa, A. and Rodrigo Comino, J., Modeling cation exchange capacity in multi geochronologicalderived alluvium soils: an approach based on soil depth intervals. Catena, 2018, 167, 327-339; https://doi.org/10.1016/j.catena.2018.05.001.

  • Seybold, C. A., Grossman, R. B. and Reinsch, T. G., Predicting cation exchange capacity for soil survey using linear models. Soil Sci. Soc. Am. J., 2005, 69, 856-863.

  • Hartmann, A., Gräsle, W. and Horn, R., Cation exchange processes in structured soils at various hydraulic properties. Soil Tillage Res., 1998, 47(1), 67-72.

  • Shekofteh, H., Ramazani, F. and Shirani, H., Optimal feature selection for predicting soil CEC: comparing the hybrid of ant colony organization algorithm and adaptive network-based fuzzy system with multiple linear regression. Geoderma, 2017, 298, 27- 34.

  • Choudhury, B. U., Fiyaz, A. R., Mohapatra, K. P. and Ngachan, S., Impact of land uses, agrophysical variables and altitudinal gradient on soil organic carbon concentration of North Eastern Himalayan Region of India. Land Degrad. Dev., 2016, 27(4), 1163-1174.

  • Saha, R., Chaudhary, R. S. and Somasundaram, J., Soil health management under hill agroecosystem of North East India. Appl. Environ. Soil Sci., 2012, 2012, 1-9.

  • Mishra, G., Marzaioli, R., Giri, K., Borah, R., Dutta, A. and Jayaraj, R. S. C., Soil quality assessment under shifting cultivation and forests in Northeastern Himalaya of India. Arch. Agron. Soil Sci., 2017, 63(10), 1355-1368.

  • FSI, Indian’s state of forest report. Forest Survey of India, Dehradun, 2017, p. 363.

  • Singh, A. K., Bordoloi, L. J., Kumar, M., Hazarika, S. and Parmar, B., Land use impact on soil quality in eastern Himalayan region of India. Environ. Monit. Assess, 2014, 186, 2013-2024.

  • Rathore, S. S., Paradigm shift for enhancing rice productivity in Nagaland: existing practices and their refinement. Himalayan Ecol., 2008, 16(2), 17-25.

  • Soil Survey Staff, Soil Taxonomy: A Basic System of Soil Classification for Making and Interpreting Soil Surveys, Natural Resources Conservation Service. US Department of Agriculture Handbook 436, 1999, 2nd edn.

  • Klute, A. (ed.), Methods of Soil Analysis: Part 1. Physical and Mineralogical Methods, Soil Science Society of America (SSSA), Book Series No. 5, Madison, Wisconsin, USA, 1986, pp. 687-734.

  • Blake, G. R. and Hartge, K. H., In Methods of Soil Analysis Part 1, Physical and Mineralogical Methods (ed. Klute, A.), SSSA Book Series No. 5. Soil Science Society of America, Madison, Wisconsin, USA, 1986, 2nd edn, pp. 363-375.

  • Walkley, A. and Black, I. A., An examination of the Degtjareff method for determining soil organic matter and a proposed modification of the chromic acid titration method. Soil Sci., 1934, 37(1), 29-38.

  • Sumner, M. E. and Miller, W. P., Cation exchange capacity and exchange coefficients. In Methods of Soil Analysis Part 3, Chemical Methods (eds Sparks, D. L., Page, A. L. and Helmke, P. A.), SSSA, Madison, Wisconsin, USA, 1996, pp. 1201-1229.

  • Memarian, H. and Balasundram, S. K., Comparison between Multi-layer perceptron and radial basis function networks for sediment load estimation in a tropical watershed. J. Water Resour. Protec., 2012, 4, 870-876.

  • Verfaillie, E., Lancker, V. V. and Meirvenne, M. V., Multivariate geostatistics for the predictive modeling of the surficial sand distribution in shelf seas. Cont. Shelf Res., 2006, 26, 2454-2468.

  • Karmakar, R. M. and Rao, A. E. V., Soils on different physiographic units in Lower Brahmaputra Valley zone of Assam I. Characterization and classification. J. Indian Soc. Soil Sci., 1999, 47, 761-767.

  • Rao, P. S. C. and Wagenet, R. J., Spatial variability of field soils: methods for data analysis and consequences. Weed Sci., 1985, 33, 18-24.

  • Rao, V. A. P., Naidu, M. V. S., Ramavatharam, N. and Rama Rao, G., Characterization, classification and evaluation of soils on different landforms in Ramachandrapuram mandal of Chittoor district in Andhra Pradesh for sustainable land use planning. J. Indian Soc. Soil Sci., 2008, 56, 23-33.

  • Bhattacharyya, T., Sen, T. K., Singh, R. S., Nayak, D. C. and Sehgal, J. L., Morphology and classification of Ultisols with Kandic horizon in north eastern region. J. Indian Soc. Soil Sci., 1994, 42, 301-306.

  • Nayak, D. C., Gangopadhyay, S. K. Sarkar, D. K. and Sen, T. K., Characteristics and classification of some acid soils of lower Subansiri district of Arunachal Pradesh. Agropedology, 2002, 12, 112-121.

  • Brady, N. C. and Weil, R. R., Nature and Properties of Soils, Prentice Hall, NJ, USA, 2008, 14th edn.

  • Zeraatpishe, M. and Khormali, F., Carbon stock and mineral factors controlling soil organic carbon in a climatic gradient, Golestan Province. J. Soil Sci. Plant Nutr., 2012, 12(4), 637-654.

  • Ulusoy, Y., Tekin, Y., Tümsavas, Z. and Mouazen, A. M., Prediction of soil cation exchange capacity using visible and near infrared spectroscopy. Biosyst. Eng., 2016, 152, 79-93; http://dx.doi.org/10.1016/j.biosystemseng.2016.03.005.

  • Khaledian, Y., Kiani, F., Ebrahimi, S., Brevik, E. C. and Aitkenhead-Peterson, J., Assessment and monitoring of soil degradation during land use change using multivariate analysis. Land Degrad. Dev., 2016, 28(1), 128-141; http://dx.doi.org/ 10.1002/ldr.2541.


Abstract Views: 334

PDF Views: 128




  • Modelling Soil Cation Exchange Capacity in Different Land-Use Systems using Artificial Neural Networks and Multiple Regression Analysis

Abstract Views: 334  |  PDF Views: 128

Authors

Gaurav Mishra
Rain Forest Research Institute, Jorhat - 785 001, India
Juri Das
Rain Forest Research Institute, Jorhat - 785 001, India
Magboul Sulieman
Soil Sciences Department, College of Food and Agricultural Sciences, King Saud University, P.O. Box 2460, Riyadh 11451, Saudi Arabia

Abstract


Cation exchange capacity (CEC), as an important indicator of soil quality, represents the ability of the soil to hold positively charged ions. In this study, CEC was successfully predicted using different statistical methods, including artificial neural networks (ANNs) involving multi-layer perceptron (MLP), radial basis function (RBF), multiple linear regression (MLR) and nonlinear regression (NLR). About 293 soil samples were collected from North East India, which are under three land uses (shifting agriculture (jhum), forest and cash crops). Also, 70% of the samples (205 samples) was selected as the calibration set and the remaining 30% (88 samples) used as the prediction set. Soil pH, texture, bulk density (BD) and organic carbon (OC) were used as predictor variables to estimate CEC. The CEC-pedotransfer function (CECPTF) performance was evaluated with the coefficient of determination (R2), ischolar_main mean square error (RMSE) and standard error for the estimate (SEE) between the observed and predicted values. The results indicated that the nonlinear model (R2 = 0.91 and SEE = 1.82 for training) for cash-crop system, and RBF (R2 = 0.91 and SEE = 3.83 for training) for jhum system were the best models to estimate CEC. In contrast, RBF (R2 = 0.67 and SEE = 14.87 for training) for forest system was the worst model to estimate CEC. The results confirm that clay and OC were the most influential variables to predict CEC in the cashcrop system, whereas BD and OC were more suitable for jhum system. Although the ANNs provided suitable predictions of the entire dataset, NLR gave a formula to estimate soil CEC using commonly tested soil properties. Thus, NLR provided a reasonable estimate of CEC for most soils analysed.

Keywords


Artificial Neural Networks, Cation Exchange Capacity, Multiple Regression, Land Uses.

References





DOI: https://doi.org/10.18520/cs%2Fv116%2Fi12%2F2020-2027