Regularization Learning of Trace Element Contamination Stemmed from Tailings Dam-Break

Document Type : Original Research Paper


1 Department of Mining Engineering, Inonu University, Malatya, Türkiye

2 Department of Computer and Information Science, Seikei University, Tokyo, Japan


An important practice in environmental risk management is assessing the consequences of heavy metal concentrations resulting from a mine dam tailing failure on soil, water, and trees. To appraise the extent of pollution, an effective classification is essential. In this study, trace element contamination is handled as a two-group classification problem and examined the performance of supervised regularization algorithms as spatial classifiers using imbalanced uncertain data. In addition to conventional shrinkage algorithms such as Ridge, the Lasso and Elastic-Net, the generalized t-statistic-based U-Lasso classifiers have been introduced and tested for mitigating such imbalances and adjusting weights for class distributions. The feature interpretation studies underlined that the most important indicator of the models is Zinc (Zn). The experimental studies revealed that the Ridge classifier (l2 penalty) outperforms the other models. Statistically, the U-Lasso models exhibited notable explanation capacity and their performances recorded close to the conventional shrinkage algorithms. The use of statistical learning-based classification approach to appraise geo-environmental contamination under the conditions of natural variability and spatial uncertainty provides useful meta-data and reliable classification models. 


Main Subjects

Akoto, A., Bortey-Sam, N., Nakayama, S.M.M., Ikenaka, Y., Baidoo, E., Apau, J., Marfo, J.T. & Ishizuka, M. (2018). Characterization, Spatial Variation & Risk Assessment of Heavy Metals & a Metalloid in Surface Soils in Obuasi, Ghana. Journal of Health & Pollution, 8(19); 180902.
Baek, S., Komori, O. & Ma, Y. (2018) An optimal semiparametric method for two-group classification. Scandinavian Journal of Statistics, 45; 806-846.
Boehmke, B. & Greenwell, B. (2020). Hands-on machine learning with R. (Boca Raton: CRC Press).
Byrne, P., Hudson-Edwards, K.A., Bird, G., Macklin, M.G., Brewer, P.A., Williams, R.D. & Jamieson, H.E. (2018).  Water quality impacts & river system recovery following the 2014 Mount Polley mine tailings dam spill, British Columbia. Canada. Applied Geochemistry, 91; 64-74. 10.1016/j.apgeochem.2018.01.012.
Davila, R.B., Fontes, M.P.F., Pacheco, A.A. & Ferreira, M.D.S. (2019).   Heavy metals in iron ore tailings & floodplain soils affected by the Samarco dam collapse in Brazil. Science of the Total Environment, 709; 136151.
Domínguez, M.T., Marañón, T., Murillo, J.M., Schulin,R. & Robinson, B.H. (2008).  Trace elements accumulation in woody plants of the Guadiamar Valley, SW Spain: a largescale phytomanagement case study. Environ. Pollut., 152; 50–59. /10.1016/j.envpol.2007.05.021.
Domínguez, M.T., Madejón, P., Marañón, T. & Murillo, J.M. (2010).  Afforestation of a trace element polluted area in SW Spain: woody plant performance & trace element accumulation. Eur. J. For. Res., 129; 47–59. /10.1007/s10342-008-0253-3.
Dorugade, A.V. (2014).  New ridge parameters for ridge regression. Journal the Association of Arab Universities for Basic & Applied Sciences, 15(1); 94-99.
Friedman, J., Hastie, T. & Tibshirani, R. (2010). Regularization paths for generalized linear models via coordinate descent, J Stat Softw., 33(1); 1-22.  
Eguchi, S. & Copas, J. (2002). A class of logistic-type discriminant functions. Biometrika, 89(1); 1-22.
Gildeh, H.K., Halliday, A., Arenas, A. & Zhang, H. (2021). Tailings dam breach analysis: a review of methods, practices, & uncertainties. Mine Water & the Environment, 40; 128-150.  DOI:10.1007/s10230-020-00718-2
Grimalt, J.O., Ferrer, M. & Macpherson, E. (1999). The environmental impact of the mine tailing accident in Aznalcóllar. Sci. Total Environ., 242 (1-3); 3-11. doi: 10.1016/s0048-9697(99)00372-1
James, G., Witten, D., Hastie, T. & Tibshirani, R. (2013). An Introduction to Statistical Learning, (New York: Springer). 
Jin, Z.J., Li, Z.Y., Li, Q., Hu, Q.J., Yang, R.M., Tang, H.F., Li, M., Huang, B.F., Zhang, J.Y. & Li, G.W. (2015). Canonical correspondence analysis of soil heavy metal pollution, microflora & enzyme activities in the Pb-Zn mine tailing dam collapse area of Sidi village, SW China. Environmental Earth Science, 73(1); 267-274.
Hastie, T., Tibshirani, R. & Wainwright, M. (2015).  Statistical learning with sparsity. (CRC Press).
Holtra, A. & Zamorska-Wojdyla, D. (2020). The pollution indices of trace elements in soils & plants close to the copper & zinc smelting works in Poland’s Lower Silesia. Environmental Science & Pollution Research, 27; 16086-16099,
Hsieh, W.W. (2009). Machine learning methods in the environmental sciences. (Cambridge: Cambridge University Press).
Hudson-Edwards, K.A., Macklin, M.G., Jamieson, H.E., Brewer, P., Coulthard, T.J., Howard, A.J. & Turner, J. (2003). The impact of tailings dam spills & clean-up operations on sediment & water quality in river systems: the Rios Agrio-Guadiamar, Aznalcollar, Spain. Applied Geochemistry, 18; 221–239.
Igual, L. & Segui, S. (2017). Introduction to data science, a Python approach to concepts, techniques & applications. (Switzerland: Springer).
Jafarzadeh, A.A., Pal, M., Servati, M., Fazelifard, M.H. & Ghorbani, M.A. (2016). Comparative analysis of support vector machine & artificial neural network models for soil cation exchange capacity prediction. Int. J. Environ. Sci. Technol., 13; 87–96.
Khan, M.H.R., Anamika, B. & Tamanna, H. (2019). Stability selection for Lasso, ridge & elastic net implemented with AFT models. Statistical Applications in Genetics & Molecular Biology, 18(5). /10.1515/sagmb-2017-0001.
Komori, O., Eguchi, S. & Copas, J.B. (2015). Generalized t-statistic for two-group classification. Biometrics, 71; 404-416.
Komori, O. & Eguchi, S. (2019). Statistical methods for imbalanced data in ecological & biological studies. (Japan: Springer).
Kossoff, D., Dubbin, W.E., Alfredsson, M., Edwards, S.J., Macklin, M.G. & Hudson-Edwards, K.A. (2014).   Mine tailings dams: Characteristics, failure, environmental impacts. & remediation. Applied Geochemistry, 51; 229-245. 
Kumar, M., Ramanathan, A.L., Tripathi, R., Farswan, S., Kumar, D. & Bhattacharya, P. (2017). A study of trace element contamination using multivariate statistical techniques & health risk assessment in groundwater of Chhaprola Industrial Area, Gautam Buddha Nagar, Uttar Pradesh, India. Chemosphere, 166; 135-145.
Li, P., Qian, H., Howard, KWF. & Wu, J. (2015). Heavy metal contamination of Yellow River alluvial sediments, Northwest China. Environ Earth Sci, 73; 3403–3415. /10.1007/s12665-014-3628-4.
Lyu, Z.J., Chai, J.R., Xu, Z.G., Qin, Y. & Cao, J. (2019).  A comprehensive review on reasons for tailings dam failures based on case history. Advances in Civil Engineering, ID:159306.
Madejón, P., Domínguez, M.T., Gil-Martinez, M., Navarro-Fernandez, C.M., Montiel-Rozas, M.M., Madejón, E., Murillo, J.M., Cabrera,F. & Marañón, T. (2018a). Evaluation of amendment addition & tree planting as measures to remediate contaminated soils: The Guadiamar case study (SW Spain). Catena, 166; 34-43.
Madejón, P., Domínguez, M.T., Madejón, E., Cabrera,F., Marañón, T. & Murillo, J.M. (2018b). Soil-plant relationships & contamination by trace elements: A review of twenty years of experimentation & monitoring after the Aznalcóllar (SW Spain) mine accident. Science of the Total Environment, 625; 50-63.
Mokhtia, M., Eftekhari, M. & Saberi-Movahed, F. (2020). Feature selection based on regularization of sparsity based regression models by hesitant fuzzy correlation. Applied Soft Computing, 91, ttps://
Moshupya, P., Abiye, T., Mouri, H., Levin, M., Strauss, M. & Strydom, R. (2019). Assessment of Radon concentration & impact on human health in a region dominated by abandoned Gold mine tailings dams: a case from the West Rand Region, South Africa. Geosciences, 9(11); 466. /10.3390/geosciences9110466.
Norini, M.P., Thouin, H., Miard, F., Battaglia-Brunet, F., Gautret, P., Guégan, R., LeForestier, L., Morabito, D., Bourgerie, S. & Motelica-Heino, M. (2019).  Mobility of Pb, Zn, Ba, As & Cd toward soil pore water & plants (willow & ryegrass) from a mine soil amended with biochar. Journal of Environmental Management, 232; 117-130. 10.1016/j.jenvman.2018.11.021.
Palma, P., Lopez-Orozco, R., Mourinha, C., Oropesa, A.L., Novais, M.H. & Alvarenga, P. (2019). Assessment of the environmental impact of an abandoned mine using an integrative approach: A case-study of the Las Musas mine (Extremadura, Spain), Science of the Total Environment, 659; 84-94.
Randelovic, D., Mutic, J., Marjanovic, P., Dordevic, T. & Kasanin-Grubin, M. (2019).  Geochemical distribution of selected elements in flotation tailings & soils/sediments from the dam spill at the abandoned antimony mine Stolice, Serbia. Environmental Science Pollution Research, 27; 6253-6258.
Revuelta, M.B. (2018).  Mineral resources-from exploration to sustainability assessment, (Cham:Springer)
Rico, M., Benito, G., Salgueiro, A.R., Diez-Herrero, A. & Pereira, H.G. (2008).  Reported tailings dam failures: a review of the European incidents in the worldwide context. J. Hazard. Mater., 152; 846–852. /10.1016/j.jhazmat.2007.07.050
Sey, E. & Belford, E.J.D. (2019).  Levels of heavy metals & contamination status of a decommissioned tailings dam in Ghana. EQA - International Journal of Environmental Quality, 35; 33-50.   DOI: 10.6092/issn.2281-4485/9060 33.
Tutmez, B. (2020). Air quality assessment by statistical learning-based regularization. Çukurova University Journal of the Faculty of Engineering & Architecture, 35(2); 271-278.
Zou, H. & Hastie, T. (2005). Regularization & variable selection via the elastic net. Journal of the Royal Statistical Society, Series B:301-320.