Abstract
To study the extent of soil pollution in Shahrood and Damghan located in Semnan Province, Iran, 229 soil samples were taken and the levels of 12 heavy metals (Ag, Co, Pb, Tl, Be, Ni, Cd, Ba, Cu, V, Zn and Cr) were analyzed. Elevated values of some heavy metals such as Cr, Ni and V were detected in the study area. In order to predict soil pollution index (SPI) with respect to the concentration levels of 12 detected heavy metals, support vector machines (SVMs) with different kernels (linear, RBF and polynomial) and artificial neural networks (ANNs) were utilized. The database was repeatedly randomly split into training and testing data sets, and both SVMs and ANNs were trained and tested for each split. The testing results of the support vector regression (SVR) model with combinations of parameter sets were compared to optimize the parameters of SVMs with different kernels. The out-of-sample generalization ability of different kernels was roughly high and the same. Therefore, RBF kernel was selected for comparison with ANNs with early stopping. The correlation coefficients between the predicted and observed SPI for the RBF kernel and ANN with early stopping were 0.997 and 0.995, implying the same performance of these two methods. The results indicated that because of some problems associated with ANNs (such as local minima), for cases in which there are quite comparable results for ANNs and SVMs, the usage of SVMs is preferable.
Similar content being viewed by others
References
Gergen I, Harmanescu M (2012) Application of principal component analysis in the pollution assessment with heavy metals of vegetable food chain in the old mining areas. Chem Cent J 6:1–13
Loska K, Wiechula D, Barska B, Cebula E, Chojnecka A (2003) Assessment of arsenic enrichment of cultivated soils in Southern Poland. Pol J Environ Stud 2:187–192
Boszke L, Astel A (2009) Application of neural-based modeling in an assessment of pollution with mercury in the middle part of the Warta River. Environ Monit Assess 152(1–4):133–147
Sun Y, Zhou Q, Xie X, Liu R (2010) Spatial, sources and risk assessment of heavy metal contamination of urban soils in typical regions of Shenyang, China. J Hazard Mater 174:455–462
Ruf A (1998) A maturity index for predatory soil mites (Mesostigmata: Gamasina) as an indicator of environmental impacts of pollution on forest soils. Appl Soil Ecol 9:447–452
Atafar Z, Mesdaghinia A, Nouri J, Homaee M, Yunesian M, Ahmadimoghadam M, Mahvi AH (2010) Effect of fertilizer application on soil heavy metal concentration. Environ Monit Assess 160:83–89
Dankoub Z, Ayoubi S, Khademi H, Lu SH (2012) Spatial distribution of magnetic properties and selected heavy metals in calcareous soils as affected by land use in the Isfahan region, Central Iran. Pedosphere 22:33–47
Jalali M, Khanlari ZV (2008) Effect of aging process on the fractionation of heavy metals in some calcareous soils of Iran. Geoderma 143:26–40
Saeedi M, Hosseinzadeh M, Jamshidi A, Pajooheshfar SP (2009) Assessment of heavy metals contamination and leaching characteristics in highway side soils, Iran. Environ Monit Assess 151:231–241
Cheng JL, Shi Z, Zhu YW (2007) Assessment and mapping of environmental quality in agricultural soils of Zhejiang Province, China. J Environ Sci 19:50–54
Chen SH, Jakeman AJ, Norton JP (2008) Artificial intelligence techniques: an introduction to their use for modelling environmental systems. Math Comput Simul 78(2–3):379–400
Hanrahan G (2011) Artificial neural network in biological and environmental analysis. Taylor and Francis Group, London, pp 119–147
Kisi O, Akbari N, Sanatipour M, Hashemi A, Teimourzadeh K, Shiri J (2013) Modeling of dissolved oxygen in river water using artificial intelligence techniques. J Environ Inform 22(2):92–101
May DB, Sivakumar M (2009) Prediction of urban storm water quality using artificial neural networks. Environ Model Softw 24(2):296–302
Nour MH, Smith DW, Gamal El-Din M, Prepas EE (2006) The application of artificial neural networks to flow and phosphorus dynamics in small streams on the Boreal Plain, with emphasis on the role of wetlands. Ecol Model 191(1):19–32
Ozkaya B, Demir A, Bilgili S (2007) Neural network prediction model for the methane fraction in biogas from field-scale landfill bioreactors. Environ Model Softw 22(6):815–822
Panda SS, Garg V, Chaubey I (2004) Artificial neural networks application in lake water quality estimation using satellite imagery. J Environ Inform 4(2):65–74
Wieland R, Mirschel W, Zbell B, Groth K, Pechenick A, Fukuda K (2012) A new library to combine artificial neural networks and support vector machines with statistics and a database engine for application in environmental modeling. Environ Model Softw 25:412–420
Aryafar A, Gholami R, Rooki R, Doulati Ardejani F (2012) Heavy metal pollution assessment using support vector machine in the Shur River, Sarcheshmeh copper mine, Iran. Environ Earth Sci 67:1191–1199
Gill MK, Asefa T, Kemblowski MW, McKee M (2006) Soil moisture prediction using support vector machines. J Am Water Resour Assoc 42:1033–1046
Guo Q, Kelly M, Graham CH (2005) Support vector machines for predicting distribution of Sudden Oak Death in California. Ecol Model 182:75–90
Sadeghi R, Zarkami R, Sabetraftar K, Van Damme P (2012) Use of support vector machines (SVMs) to predict distribution of an invasive water fern Azolla filiculoides (Lam.) in Anzali wetland, southern Caspian Sea, Iran. Ecol Model 244:117–126
Haghverdi A, Cornelis WM, Ghahraman B (2012) A pseudo-continuous neural network approach for developing water retention pedotransfer functions with limited data. J Hydrol 442–443:46–54
Liao K, Xu S, Wu J, Zhu Q, An L (2014) Using support vector machines to predict cation exchange capacity of different soil horizons in Qingdao City, China. J Plant Nutr Soil Sci 177:775–782
Tamari S, Wösten JHM, Ruiz-Suárez JC (1996) Testing an artificial neural network for predicting soil hydraulic conductivity. Soil Sci Am J 60:1732–1741
Jiang H, Cotton WR (2004) Soil moisture estimation using an artificial neural network: a feasibility study. Can J Remote Sens 30(5):827–839
Yu Z, Liu D, Lu H, Fu X, Xiang L, Zhu Y (2012) A multi-layer soil moisture data assimilation using support vector machines and ensemble particle filter. J Hydrol 475:53–64
Were K, Bui DT, Dick OB, Singh BR (2015) A comparative assessment of support vector regression, artificial neural networks, and random forests for predicting and mapping soil organic carbon stocks across an Afromontane landscape. Ecol Indic 52:394–403
Yoon H, Jun SH, Hyun Y, Bae GO, Lee KK (2011) A comparative study of artificial neural networks and support vector machines for predicting groundwater levels in a coastal aquifer. J Hydrol 396:128–138
Dreyfus G (2005) Neural networks methodology and applications. Springer, Berlin, pp 1–493
Hsieh WM (2009) Machine learning methods in the environmental science, neural networks and kernels. Cambridge University Press, Cambridge, pp 86–157
Taylor BJ (2006) Methods and procedures for the verification and validation of artificial neural networks. Springer, Berlin, pp 1–275
Theodoros E, Tomaso P, Massimiliano P (2002) Regularization and statistical learning theory for data analysis. Comput Stat Data Anal 38:421–432
Peng C, Wen X (1999) Recent applications of artificial neural networks in forest resource management: an overview. Environmental decision support systems and artificial intelligence. Aaai Workshop, pp 15–22
Shokri BJ, Ramazi H, Doulati F, Moradzadeh A (2014) A statistical model to relate pyrite oxidation and oxygen transport within a coal waste pile: case study, Alborz Sharghi, northeast of Iran. Environ Earth Sci 71:4693–4702
IAEA (2004) Soil sampling for environmental contaminants, International atomic energy agency, Austria, 81 p
Liang CJ, Zhou S, Wei ZY (2007) Assessment and mapping of environmental quality in agricultural soils of Zhejiang Province, China. J Environ Sci 19:50–54
Chang CC, Lin CJ (2001) LIBSVM: a library for support vector machines. http://www.csie.ntu.edu.tw/~cjlin/libsvm
Li H, Liang Y, Xu Q (2009) Support vector machines and its applications in chemistry. Chem Intell Lab Syst 95:188–198
Hoang H, Lock K, Mouton A, Goethals PLM (2010) Application of classification trees and support vector machines to model the presence of macroinvertebrates in rivers in Vietnam. Ecol Inform 5:140–146
Khalil B, Ouarda TBMJ, St-Hilaire A (2011) Estimation of water quality characteristics at ungauged sites using artificial neural networks and canonical correlation analysis. J Hydrol 405:277–287
Piotrowski AP, Napiorkowski JJ (2013) A comparison of methods to avoid overfitting in neural networks training in the case of catchment runoff modeling. J Hydrol 476:97–111
Khalil A, Almasri MN, McKee M, Kaluarachchi JJ (2005) Applicability of statistical learning algorithms in groundwater quality modeling. Water Resour Res 41:1–16
Isaaks EH, Sivastava RM (1998) An introduction to applied geostatistics. Oxford University Press, New York
Goovaerts P (1997) Geostatistics for natural resources evaluation. Oxford University Press, New York
Eriksson JE (2001) Concentrations of 61 trace elements in sewage sludge, farmyard manure, mineral fertilizers, precipitation and in oil and crops. Swedish EPA Rep 5159, Stockholm
Juchen CR, Cervi EC, Boas MAV, Charlesworth S, Poleto C (2014) Comparative of local background values for trace elements in different Brazilian tropical soils. Int J Environ Eng Nat Resour 1(6):255–261
Cai M, McBride MB, Li K (2015) Bioaccessibility of Ba, Cu, Pb, and Zn in urban garden and orchard soils. Environ Pollut 208:145–152
Esmaeili A, Moore F, Keshavarzi B, Jaafarzadeh N, Kermani M (2014) A geochemical survey of heavy metals in agricultural and background soils of the Isfahan industrial zone, Iran. Catena 121:88–98
Sun C, Liu J, Wang Y, Sun L, Yu H (2013) Multivariate and geostatistical analyses of the spatial distribution and sources of heavy metals in agricultural soil in Dehui, Northeast China. Chemosphere 92(5):517–523
Kelepertsis A, Alexakis D, Kita I (2001) Environmental geochemistry of soils and waters of Susaki area, Korinthos, Greece. Environ Geochem Health 23:117–135
Ardejani FD, Shokri BJ, Moradzadeh A, Shafaei SZ, Kakaei R (2011) Geochemical characterisation of pyrite oxidation and environmental problems related to release and transport of metals from a coal washing low-grade waste dump, Shahrood, northeast Iran. Environ Monit Assess 183:41–55
Wanas NM, Auda G, Kamel M, Karray F (1998) On the optimal number of hidden nodes in a neural network. In: Proceedings of the IEEE Canadian conference on electrical and computer engineering, pp 918–921
Shu C, Ouarda TBMJ (2007) Flood frequency analysis at ungauged sites using artificial neural networks in canonical correlation analysis physiographic space. Water Resour Res 43:1–12
Noori R, Karbassi A, Farokhnia A, Dehghani M (2009) Predicting the longitudinal dispersion coefficient using support vector machine and adaptive neuro-fuzzy inference system techniques. Environ Eng Sci 26(10):1503–1510
Ji AB, Pang JH, Qiu HJ (2010) Support vector machine for classification based on fuzzy training data. Expert Sys Appl 37:3495–3498
Yao XJ, Panaye A, Doucet JP, Zhang RS, Chen HF, Liu MC, Hu ZD, Fan BT (2004) Comparative study of QSAR/QSPR correlations using support vector machines, radial basis function neural networks, and multiple linear regression. J Chem Inf Comput Sci 44:1257–1266
Zhang X, Srinivasan R, Van Liew M (2009) Approximating SWAT model using artificial neural network and support vector machine. J Am Water Resour Assoc 45(2):460–474
Dibike YB, Velickov S, Solomatine DP, Abott MB (2001) Model induction with support vector machines: introduction and applications. J Comput Civ Eng 15(3):208–216
Cristianini N, Shawe-Taylor J (2000) An introduction to support vector methods. Cambridge University Press, Cambridge
Abraham A (2004) Meta learning evolutionary artificial neural networks. Neurocomputing 56:1–38
Acknowledgments
The authors are grateful to Geological Survey of Iran for the help in analysis of heavy metals. The financial support of this project has been provided by the Grant no. 100-2164 offered by Geological Survey of Iran.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Hereby we confirm that there is no conflict of interest associated with this manuscript and all of the people who have contributed to the preparation of this paper have been cited by the authors. In addition, the funding agency related to this manuscript has also been cited in the acknowledgement section.
Rights and permissions
About this article
Cite this article
Sakizadeh, M., Mirzaei, R. & Ghorbani, H. Support vector machine and artificial neural network to model soil pollution: a case study in Semnan Province, Iran. Neural Comput & Applic 28, 3229–3238 (2017). https://doi.org/10.1007/s00521-016-2231-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-016-2231-x