Soil pollution is a big issue caused by anthropogenic activities. The spatial distribution of potentially toxic elements (PTEs) varies in most urban and peri-urban areas. As a result, spatially predicting the PTEs content in such soil is difficult. A total number of 115 samples were obtained from Frydek Mistek in the Czech Republic. Calcium (Ca), magnesium (Mg), potassium (K), and nickel (Ni) concentrations were determined using Inductively Coupled Plasma Optical Emission Spectroscopy. The response variable was Ni, while the predictors were Ca, Mg, and K. The correlation matrix between the response variable and the predictors revealed a satisfactory correlation between the elements. The prediction results indicated that support vector machine regression (SVMR) performed well, although its estimated root mean square error (RMSE) (235.974 mg/kg) and mean absolute error (MAE) (166.946 mg/kg) were higher when compared with the other methods applied. The hybridized model of empirical bayesian kriging-multiple linear regression (EBK-MLR) performed poorly, as evidenced by a coefficient of determination value of less than 0.1. The empirical bayesian kriging-support vector machine regression (EBK-SVMR) model was the optimal model, with low RMSE (95.479 mg/kg) and MAE (77.368 mg/kg) values and a high coefficient of determination (R2 = 0.637). EBK-SVMR modelling technique output was visualized using a self-organizing map. The clustered neurons of the hybridized model CakMg-EBK-SVMR component plane showed a diverse colour pattern predicting the concentration of Ni in the urban and peri-urban soil. The results proved that combining EBK and SVMR is an effective technique for predicting Ni concentrations in urban and peri-urban soil.

Department of Plants Protection Faculty of Agrobiology Food and Natural Resources Czech University of Life Sciences Prague 16500 Prague Czech Republic

Department of Soil Science and Soil Protection Faculty of Agrobiology Food and Natural Resources Czech University of Life Sciences Prague 16500 Prague Czech Republic

Zobrazit více v PubMed

PlantProbs.net. Nickel in plants and soil https://plantprobs.net/plant/nutrientImbalances/sodium.html (accessed Apr 28, 2021).

Guodong Liu, E. H. Simonne, and Y. L. Nickel Nutrition in Plants | EDIS. EDis2011.

Liu, G. D. “A New Essential Mineral Element–Nickel.” Plants Nutr. Fertil. Sci.2001.

Kabata-Pendias, A.; Mukherjee, A. Trace Elements from Soil to Human; 2007.

Kasprzak KS. Nickel advances in modern environmental toxicology. Environ. Toxicol. 1987;11:145–183.

Cempel M, Nikel G. Nickel: A review of its sources and environmental toxicology. Polish J. Environ. Stud. 2006;15:375–382.

Bradl HB. Chapter Sources and origins of heavy metals. Interface Sci. Technol. 2005;6:1–27. doi: 10.1016/S1573-4285(05)80020-1. DOI

Von Burg R. Nickel and some nickel compounds. J. Appl. Toxicol. 1997;17:425–431. doi: 10.1002/(SICI)1099-1263(199711/12)17:6<425::AID-JAT460>3.0.CO;2-R. PubMed DOI

Freedman B, Hutchinson TC. Pollutant inputs from the atmosphere and accumulations in soils and vegetation near a nickel–copper smelter at Sudbury, Ontario, Canada. Can. J. Bot. 1980;58(1):108–132. doi: 10.1139/b80-014. DOI

Manyiwa T, Ultra VU, Rantong G, Opaletswe KA, Gabankitse G, Taupedi SB, Gajaje K. Heavy metals in soil, plants, and associated risk on grazing ruminants in the vicinity of Cu–Ni mine in Selebi-Phikwe, Botswana. Environ. Geochem. Health. 2021 doi: 10.1007/s10653-021-00918-x. PubMed DOI

Kabata-Pendias. Kabata-Pendias A. 2011. Trace elements in soils and... - Google Scholar https://scholar.google.com/scholar?hl=en&as_sdt=0%2C5&q=Kabata-Pendias+A.+2011.+Trace+elements+in+soils+and+plants.+4th+ed.+New+York+%28NY%29%3A+CRC+Press&btnG= (accessed Nov 24, 2020).

Almås, A., Singh, B., Agricultural, T. S.-N. J. of & 1995, undefined. The impact of nickel industry in Russia on concentrations of heavy metals in agricultural soils and grass in Soer-Varanger, Norway. agris.fao.org.

Nielsen GD, et al. Absorption and retention of nickel from drinking water in relation to food intake and nickel sensitivity. Toxicol. Appl. Pharmacol. 1999;154:67–75. doi: 10.1006/taap.1998.8577. PubMed DOI

Costa M, Klein CB. Nickel carcinogenesis, mutation, epigenetics, or selection. Environ. Health Perspect. 1999;107:2. doi: 10.1289/ehp.99107a438. PubMed DOI PMC

Agyeman, P. C.; Ahado, S. K.; Borůvka, L.; Biney, J. K. M.; Sarkodie, V. Y. O.; Kebonye, N. M.; Kingsley, J. Trend Analysis of Global Usage of Digital Soil Mapping Models in the Prediction of Potentially Toxic Elements in Soil/Sediments: A Bibliometric Review. Environmental Geochemistry and Health. Springer Science and Business Media B.V. 2020. 10.1007/s10653-020-00742-9. PubMed

Minasny B, McBratney AB. Digital soil mapping: A brief history and some lessons. Geoderma. 2016;264:301–311. doi: 10.1016/j.geoderma.2015.07.017. DOI

McBratney AB, Mendonça Santos ML, Minasny B. On digital soil mapping. Geoderma. 2003;117(1–2):3–52. doi: 10.1016/S0016-7061(03)00223-4. DOI

Deutsch.C.V. Geostatistical Reservoir Modeling,... - Google Scholar https://scholar.google.com/scholar?hl=en&as_sdt=0%2C5&q=C.V.+Deutsch%2C+2002%2C+Geostatistical+Reservoir+Modeling%2C+Oxford+University+Press%2C+376+pages.+&btnG= (accessed Apr 28, 2021).

Olea RA. Geostatistics for engineers & earth scientists. Stoch. Environ. Res. Risk Assess. 2000;14(3):207–209. doi: 10.1007/pl00009782. DOI

Gumiaux C, Gapais D, Brun JP. Geostatistics applied to best-fit interpolation of orientation data. Tectonophysics. 2003;376(3–4):241–259. doi: 10.1016/j.tecto.2003.08.008. DOI

Wadoux AMJC, Minasny B, McBratney AB. Machine learning for digital soil mapping: applications, challenges and suggested solutions. Earth-Sci Rev. 2020 doi: 10.1016/j.earscirev.2020.103359. DOI

Tan K, Wang H, Chen L, Du Q, Du P, Pan C. Estimation of the spatial distribution of heavy metal in agricultural soils using airborne hyperspectral imaging and random forest. J. Hazard. Mater. 2020;382:120987. doi: 10.1016/j.jhazmat.2019.120987. PubMed DOI

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. Appl. 2017;28(11):3229–3238. doi: 10.1007/s00521-016-2231-x. DOI

Vega FA, Matías JM, Andrade ML, Reigosa MJ, Covelo EF. Classification and regression trees (CARTs) for modelling the sorption and retention of heavy metals by soil. J. Hazard. Mater. 2009;167(1–3):615–624. doi: 10.1016/j.jhazmat.2009.01.016. PubMed DOI

Sun H, Guo ZX, Guo Y, Yuan YZ, Chai M, Bi RT, Yang J. Prediction of distribution of soil cd concentrations in Guangdong Province, China. Huanjing Kexue/Environmental Sci. 2017;38(5):2111–2124. doi: 10.13227/j.hjkx.201611006. PubMed DOI

Woodcock CE, Gopal S. Fuzzy set theory and thematic maps: accuracy assessment and area estimation. Int. J. Geogr. Inf. Sci. 2000;14(2):153–172. doi: 10.1080/136588100240895. DOI

Finke PA. Chapter 39 Quality assessment of digital soil maps: producers and users perspectives. Dev. Soil Sci. 2006 doi: 10.1016/S0166-2481(06)31039-2. DOI

Pontius RG, Cheuk ML. A generalized cross-tabulation matrix to compare soft-classified maps at multiple resolutions. Int. J. Geogr. Inf. Sci. 2006;20(1):1–30. doi: 10.1080/13658810500391024. DOI

Grunwald S. Multi-criteria characterization of recent digital soil mapping and modeling approaches. Geoderma. 2009;152(3–4):195–207. doi: 10.1016/j.geoderma.2009.06.003. DOI

Nelson MA, Bishop TFA, Triantafilis J, Odeh IOA. An error budget for different sources of error in digital soil mapping. Eur. J. Soil Sci. 2011;62:417–430. doi: 10.1111/j.1365-2389.2011.01365.x. DOI

McBratney AB, Minasny B, ViscarraRossel R. Spectral soil analysis and inference systems: A powerful combination for solving the soil data crisis. Geoderma. 2006;136:272–278. doi: 10.1016/j.geoderma.2006.03.051. DOI

Stumpf F, et al. Uncertainty-guided sampling to improve digital soil maps. CATENA. 2017;153:30–38. doi: 10.1016/j.catena.2017.01.033. DOI

Legates DR, McCabe GJ. Evaluating the use of ‘goodness-of-fit’ measures in hydrologic and hydroclimatic model validation. Water Resour. Res. 1999;35:233–241. doi: 10.1029/1998WR900018. DOI

Sergeev AP, Tarasov DA, Buevich AG, Subbotina IE, Shichkin AV, Sergeeva MV, Lvova OA. High variation subarctic topsoil pollutant concentration prediction using neural network residual kriging. AIP Conf. Proc. 2017;2017:1836. doi: 10.1063/1.4981963. DOI

Subbotina IE, Buevich AG, Shichkin AV, Sergeev AP, Tarasov DA, Tyagunov AG, Sergeeva MV, Baglaeva EM. Multilayer perceptron, generalized regression neural network, and hybrid model in predicting the spatial distribution of impurity in the topsoil of urbanized area. AIP Conf. Proc. 2018 doi: 10.1063/1.5045410. DOI

Tarasov DA, Buevich AG, Sergeev AP, Shichkin AV. High variation topsoil pollution forecasting in the Russian subarctic: using artificial neural networks combined with residual kriging. Appl. Geochemistry. 2018;88:188–197. doi: 10.1016/j.apgeochem.2017.07.007. DOI

Tarasov, D.; Buevich, A.; Shichkin, A.; Subbotina, I.; Tyagunov, A.; Baglaeva, E. Chromium Distribution Forecasting Using Multilayer Perceptron Neural Network and Multilayer Perceptron Residual Kriging. In AIP Conference Proceedings; American Institute of Physics Inc., 2018; Vol. 1978, p 440019. 10.1063/1.5044048.

John K, et al. Hybridization of cokriging and gaussian process regression modelling techniques in mapping soil sulphur. CATENA. 2021;206:2. doi: 10.1016/j.catena.2021.105534. DOI

Gribov A, Krivoruchko K. Empirical Bayesian Kriging Implementation and Usage. Sci. Total Environ. 2020 doi: 10.1016/j.scitotenv.2020.137290. PubMed DOI

Samsonova VP, Blagoveshchenskii YN, Meshalkina YL. Use of empirical Bayesian kriging for revealing heterogeneities in the distribution of organic carbon on agricultural lands. Eurasian Soil Sci. 2017;50(3):305–311. doi: 10.1134/S1064229317030103. DOI

Fabijańczyk P, Zawadzki J, Magiera T. Magnetometric assessment of soil contamination in problematic area using empirical bayesian and indicator kriging: a case study in upper Silesia, Poland. Geoderma. 2017;308:69–77. doi: 10.1016/j.geoderma.2017.08.029. DOI

John K, Afu SM, Isong IA, Aki EE, Kebonye NM, Ayito EO, Chapman PA, Eyong MO, Penížek V. Mapping soil properties with soil-environmental covariates using geostatistics and multivariate statistics. Int. J. Environ. Sci. Technol. 2021;2:1–16. doi: 10.1007/s13762-020-03089-x. DOI

Li T, Sun G, Yang C, Liang K, Ma S, Huang L. Using self-organizing map for coastal water quality classification: Towards a better understanding of patterns and processes. Sci. Total Environ. 2018;628–629:1446–1459. doi: 10.1016/j.scitotenv.2018.02.163. PubMed DOI

Wang Z, Xiao J, Wang L, Liang T, Guo Q, Guan Y, Rinklebe J. Elucidating the differentiation of soil heavy metals under different land uses with geographically weighted regression and self-organizing map. Environ. Pollut. 2020 doi: 10.1016/j.envpol.2020.114065. PubMed DOI

Hossain Bhuiyan MA, Chandra Karmaker S, Bodrud-Doza M, Rakib MA, Saha BB. Enrichment, sources and ecological risk mapping of heavy metals in agricultural soils of dhaka district employing SOM PMF and GIS Methods. Chemosphere. 2021 doi: 10.1016/j.chemosphere.2020.128339. PubMed DOI

Kebonye NM, Eze PN, John K, Gholizadeh A, Dajčl J, Drábek O, Němeček K, Borůvka L. Self-organizing map artificial neural networks and sequential gaussian simulation technique for mapping potentially toxic element hotspots in polluted mining soils. J. Geochemical Explor. 2021;222:106680. doi: 10.1016/j.gexplo.2020.106680. DOI

Weather Spark. Average Weather in Frýdek-Místek, Czechia, Year Round - Weather Spark https://weatherspark.com/y/83671/Average-Weather-in-Frýdek-Místek-Czechia-Year-Round (accessed Sep 14, 2020).

Kozák, J. Soil Atlas of the Czech Republic. 2010, 150.

Vacek O, Vašát R, Borůvka L. Quantifying the pedodiversity-elevation relations. Geoderma. 2020;373:114441. doi: 10.1016/j.geoderma.2020.114441. DOI

Krivoruchko, K. Empirical Bayesian Kriging; 2012; Vol. Fall 2012.

Vapnik V. The nature of statistical learning theory. Technometrics. 1995;38(4):409. doi: 10.2307/1271324. DOI

Li Z, Zhou M, Xu LJ, Lin H, Pu H. Training sparse SVM on the core sets of fitting-planes. Neurocomputing. 2014;130:20–27. doi: 10.1016/j.neucom.2013.04.046. DOI

Cherkassky, V.; Mulier, F. Learning from Data: Concepts, Theory, and Methods: Second Edition; 2006. 10.1002/9780470140529.

John K, Isong IA, Kebonye NM, Ayito EO, Agyeman PC, Afu SM. Using machine learning algorithms to estimate soil organic carbon variability with environmental variables and soil nutrient indicators in an alluvial soil. Land. 2020;9(12):1–20. doi: 10.3390/land9120487. DOI

Vohland M, Besold J, Hill J, Fründ HC. Comparing different multivariate calibration methods for the determination of soil organic carbon pools with visible to near infrared spectroscopy. Geoderma. 2011;166(1):198–205. doi: 10.1016/j.geoderma.2011.08.001. DOI

Fraser, S. J.; Dickson, B. L. A New Method for Data Integration and Integrated Data Interpretation: Self-Organising Maps; 2007.

Melssen, W. J.; Smits, J. R. M.; Buydens, L. M. C.; Kateman, G. Using Artificial Neural Networks for Solving Chemical Problems Part II. Kohonen Self-Organising Feature Maps and Hopfield Networks. Chemometrics and Intelligent Laboratory Systems. Elsevier, Amsterdam, 1, 1994, pp 267–291. 10.1016/0169-7439(93)E0036-4.

Kooistra L, Wanders J, Epema GF, Leuven RSEW, Wehrens R, Buydens LMC. The potential of field spectroscopy for the assessment of sediment properties in river floodplains. Anal. Chim. Acta. 2003;484(2):189–200. doi: 10.1016/S0003-2670(03)00331-3. DOI

Li L, Lu J, Wang S, Ma Y, Wei Q, Li X, Cong R, Ren T. Methods for estimating leaf nitrogen concentration of winter oilseed rape (Brassica Napus L.) using in situ leaf spectroscopy. Ind. Crops Prod. 2016;91:194–204. doi: 10.1016/j.indcrop.2016.07.008. DOI

Różański SŁ, Kwasowski W, Castejón JMP, Hardy A. Heavy metal content and mobility in urban soils of public playgrounds and sport facility areas, Poland. Chemosphere. 2018;212:456–466. doi: 10.1016/j.chemosphere.2018.08.109. PubMed DOI

Bretzel F, Calderisi M. Metal contamination in urban soils of coastal Tuscany (Italy) Environ. Monit. Assess. 2006;118(1–3):319–335. doi: 10.1007/s10661-006-1495-5. PubMed DOI

Jim CY. Urban soil characteristics and limitations for landscape planting in hong kong. Landsc. Urban Plan. 1998;40(4):235–249. doi: 10.1016/S0169-2046(97)00117-5. DOI

Birke, M.; Rauch, U.; Chmieleski, J. Environmental Geochemical Survey of the City of Stassfurt: An Old Mining and Industrial Urban Area in Sachsen-Anhalt, Germany. In Mapping the Chemical Environment of Urban Areas; John Wiley and Sons, 2011; pp 269–306. 10.1002/9780470670071.ch18.

Khodadoust AP, Reddy KR, Maturi K. Removal of nickel and phenanthrene from kaolin soil using different extractants. Environ. Eng. Sci. 2004;21(6):691–704. doi: 10.1089/ees.2004.21.691. DOI

Jakovljevic, M.; Kostic, N.; Antic-Mladenovic, S. The Availability of Base Elements (Ca, Mg, Na, K) in Some Important Soil Types in Serbia; 2003. 10.2298/zmspn0304011j.

Orzechowski, M.; Smolczynski, S. IN SOILS DEVELOPED FROM THE HOLOCENE DEPOSITS IN NORTH-EASTERN POLAND*; -, 2007; Vol. 15.

Pongrac P, McNicol JW, Lilly A, Thompson JA, Wright G, Hillier S, White PJ. Mineral element composition of cabbage as affected by soil type and phosphorus and zinc fertilisation. Plant Soil. 2019;434(1–2):151–165. doi: 10.1007/s11104-018-3628-3. DOI

Kingston, G.; Anink, M. C.; Clift, B. M.; Beattie, R. N. Potassium Management for Sugarcane on Base Saturated Soils in Northern New South Wales; 2009; Vol. 31.

Santo, L. T., Nakahata, M. H., & Schell, V. P. Santo LT, Nakahata MH, Ito GP and Schell VP (2000).... - Google Scholar https://scholar.google.com/scholar?hl=en&as_sdt=0%2C5&q=Santo+LT%2C+Nakahata+MH%2C+Ito+GP+and+Schell+VP+%282000%29.+Calcium+and+liming+trials+from+1994+to+1998+at+HC%26S.+Technical+supplement+to+Agronomy+Report+83%2C+Hawaiian+Agricultural+Research+Centre. (accessed May 16, 2021).

Burgos P, Madejón E, Pérez-de-Mora A, Cabrera F. Horizontal and vertical variability of soil properties in a trace element contaminated area. Int. J. Appl. Earth Obs. Geoinf. 2008;10(1):11–25. doi: 10.1016/j.jag.2007.04.001. DOI

Olinic T, Olinic E. The effect of quicklime stabilization on soil properties. Agric. Agric. Sci. Procedia. 2016;10:444–451. doi: 10.1016/j.aaspro.2016.09.013. DOI

Madaras, M.; Lipavský, J. Interannual Dynamics of Available Potassium in a Long-Term Fertilization Experiment; 2009; Vol. 55. 10.17221/34/2009-pse.

Madaras M, Koubova M, Lipavský J. Stabilization of available potassium across soil and climatic conditions of the Czech Republic. Arch. Agron. Soil Sci. 2010;56(4):433–449. doi: 10.1080/03650341003605750. DOI

Pulkrabová J, Černý J, Száková J, Švarcová A, Gramblička T, Hajšlová J, Balík J, Tlustoš P. Is the long-term application of sewage sludge turning soil into a sink for organic pollutants?: Evidence from field studies in the Czech Republic. J. Soils Sedim. 2019;19(5):2445–2458. doi: 10.1007/s11368-019-02265-y. DOI

Asare MO, Horák J, Šmejda L, Janovský M, Hejcman M. A medieval hillfort as an island of extraordinary fertile archaeological dark earth soil in the Czech Republic. Eur. J. Soil Sci. 2021;72(1):98–113. doi: 10.1111/ejss.12965. DOI

Zádorová T, Penížek V, Šefrna L, Drábek O, Mihaljevič M, Volf Š, Chuman T. Identification of Neolithic to Modern Erosion-Sedimentation Phases Using Geochemical Approach in a Loess Covered Sub-Catchment of South Moravia Czech Republic. Geoderma. 2013;195–196:56–69. doi: 10.1016/j.geoderma.2012.11.012. DOI

Tlustoš P, Hejcman M, Kunzová E, Hlisnikovský L, Zámečníková H, Száková J. Nutrient status of soil and winter wheat (Triticum Aestivum L.) in response to long-term farmyard manure application under different climatic and soil physicochemical conditions in the Czech Republic. Arch. Agron. Soil Sci. 2018;64(1):70–83. doi: 10.1080/03650340.2017.1331297. DOI

Wang Z, et al. Elucidating the differentiation of soil heavy metals under different land uses with geographically weighted regression and self-organizing map. Environ. Pollut. 2020;260:2. PubMed

Yan P, Peng H, Yan L, Lin K. Spatial variability of soil physical properties based on GIS and geo-statistical methods in the red beds of the Nanxiong Basin, China. Polish J. Environ. Stud. 2019;28:2961–2972. doi: 10.15244/pjoes/92245. DOI

Beguin J, Fuglstad GA, Mansuy N, Paré D. Predicting soil properties in the Canadian boreal forest with limited data: Comparison of spatial and non-spatial statistical approaches. Geoderma. 2017;306:195–205. doi: 10.1016/j.geoderma.2017.06.016. DOI

Adhikary PP, Dash CJ, Bej R, Chandrasekharan H. Indicator and probability kriging methods for delineating Cu, Fe, and Mn contamination in groundwater of Najafgarh Block, Delhi, India. Environ. Monit. Assess. 2011;176:663–676. doi: 10.1007/s10661-010-1611-4. PubMed DOI

John K, et al. Mapping soil properties with soil-environmental covariates using geostatistics and multivariate statistics. Int. J. Environ. Sci. Technol. 2021;18:3327–3342. doi: 10.1007/s13762-020-03089-x. DOI

Eldeiry AA, Garcia LA. Detecting soil salinity in alfalfa fields using spatial modeling and remote sensing. Soil Sci. Soc. Am. J. 2008;72:201–211. doi: 10.2136/sssaj2007.0013. DOI