Identifying mining-induced chromium contamination in soil through visible-near infrared spectroscopy and machine learning

Abstract

The extraction, purification, and utilization of mineral resources have been among the largest anthropogenic sources of chromium (Cr) in soil. Determining Cr contamination in soil is a key issue prior to its appropriate remediation. Nevertheless, the efficient identification of large-scale soil Cr contamination requires continuous research. The present study proposes a continental-scale method to rapidly identify soil Cr contamination using visible-near infrared spectroscopy (vis-NIR) and machine learning (ML). A large dataset containing 18,675 topsoil samples from the Land Use/Land Cover Area Frame Survey 2009 projects across Europe was compiled. Five advanced ML algorithms were compared, and hyperparameter optimization was conducted using the grid search method. Permutation importance was employed to calculate the rank of each spectral wavelength, shedding light on the most sensitive spectral wavelength for Cr contamination. Results indicate that hyperparameter optimization had the most significant performance improvement on support vector machine (SVM), exhibiting an increase in training performance from 0.795 to 0.868. The achieved optimal SVM accuracy, area under the receiver operating feature curve, sensitivity, and specificity of 0.78, 0.85, 0.85, and 0.66, respectively, indicating excellent predictive performance on the Cr contamination classification. The optimal SVM model revealed that the most important spectral band for classifying Cr contamination was 1430–1433 nm. This finding implies that the adsorption of molecular water was closely related to the classification of Cr contamination. The current study introduces the first continental-scale identification of Cr contamination using vis-NIR, which has excellent guiding significance for Cr remediation and the identification of other heavy metals using vis-NIR.

Keywords

Mining contamination / Hyperspectral / Classification / Support vector machine / Continental scale

References

[1] I. Razo, L. Carrizales, J. Castro, F. Díaz-Barriga, M. Monroy, Arsenic and heavy metal pollution of soil, water and sediments in a semi-arid climate mining area in mexico, Water Air Soil Pollut. 152 (2004) 129-152.

[2] A.J. Gunson, Y. Jian, Artisanal Mining in the People’s Republic of China, International Institute of Environment and Development, Draft Report, 2001.

[3] M.K. Luo, H. Yu, Q. Liu, W. Lan, Q.R. Ye, Y. Niu, Y. Niu, Effect of river-lake connectivity on heavy metal diffusion and source identification of heavy metals in the middle and lower reaches of the Yangtze River, J. Hazard. Mater. 416 (2021) 125818.

[4] L.J. Wu, W.F. Yue, J. Wu, C.M. Cao, H. Liu, Y.G. Teng, Metal-mining-induced sediment pollution presents a potential ecological risk and threat to human health across China: A meta-analysis, J. Environ. Manag. 329 (2023) 117058.

[5] X.Y. Liu, Z.K. Bai, H.D. Shi, W. Zhou, X.C. Liu, Heavy metal pollution of soils from coal mines in China, Nat. Hazard. 99 (2019) 1163-1177.

[6] D.Y. Hou, D. O'Connor, A.D. Igalavithana, D.S. Alessi, J. Luo, D.C.W. Tsang, D.L. Sparks, Y. Yamauchi, J. Rinklebe, Y.S. Ok, Metal contamination and bioremediation of agricultural soils for food safety and sustainability, Nat. Rev. Earth Environ. 1 (7) (2020) 366-381.

[7] X. Guang, J. Chen, M. Qu, J. Zhang, H. Liu, Y. Zhao, B. Huang, Effects of mining on the potentially toxic elements in the surrounding soils in China: A meta-analysis, Sci. Total Environ. 821 (2022) 153562.

[8] A. Zhitkovich, Chromium in drinking water: Sources, metabolism, and cancer risks, Chem. Res. Toxicol. 24 (10) (2011) 1617-1629.

[9] J. Saha, R. Selladurai, M.V. Coumar, M. Dotaniya, S. Kundu, A.K. Patra, Soil Pollution-An Emerging Threat to Agriculture, Springer, Singapore, 2017.

[10] A.A. Jennings, Analysis of worldwide regulatory guidance values for the most commonly regulated elemental surface soil contamination, J. Environ. Manag. 118 (2013) 72-95.

[11] T. Suzuki, K. Kawai, M. Moribe, M. Niinae, Recovery of Cr as Cr(III) from Cr(VI)-contaminated kaolinite clay by electrokinetics coupled with a permeable reactive barrier, J. Hazard. Mater. 278 (2014) 297-303.

[12] Z. Yang, X. Zhang, Z. Jiang, Q. Li, P. Huang, C. Zheng, Q. Liao, W. Yang, Reductive materials for remediation of hexavalent chromium contaminated soil-A review, Sci. Total Environ. 773 (2021) 145654.

[13] J. Petit, N. Ait-Mouheb, S. Mas García, M. Metz, B. Molle, R. Bendoula, Potential of visible/near infrared spectroscopy coupled with chemometric methods for discriminating and estimating the thickness of clogging in drip-irrigation, Biosyst. Eng. 209 (2021) 246-255.

[14] T. Kemper, S. Sommer, Estimate of heavy metal contamination in soils after a mining accident using reflectance spectroscopy, Environ. Sci. Technol. 36 (12) (2002) 2742-2747.

[15] H. Cheng, R.L. Shen, Y.Y. Chen, Q.J. Wan, T.Z. Shi, J.J. Wang, Y. Wan, Y.S. Hong, X.C. Li, Estimating heavy metal concentrations in suburban soils with reflectance spectroscopy, Geoderma 336 (2019) 59-67.

[16] H.C.S. Amorim, L.C.C. Hurtarte, L. Vergütz, I.R. Silva, O.D.V. Costa, A.A. Pacheco, M.P.F. Fontes, Lead speciation and availability affected by plants in a contaminated soil, Chemosphere 285 (2021) 131468.

[17] M.A. Munnaf, A. Guerrero, S. Nawar, G. Haesaert, M. Van Meirvenne, A.M. Mouazen, A combined data mining approach for on-line prediction of key soil quality indicators by Vis-NIR spectroscopy, Soil Tillage Res. 205 (2021) 104808.

[18] S. Gruszczyński, W. Gruszczyński, Supporting soil and land assessment with machine learning models using the Vis-NIR spectral response, Geoderma 405 (2022) 115451.

[19] L.H. Chen, K. Tan, X. Wang, Y. Chen, A rapid soil Chromium pollution detection method based on hyperspectral remote sensing data, Int. J. Appl. Earth Obs. Geoinf. 128 (2024) 103759.

[20] D.J. Brown, K.D. Shepherd, M.G. Walsh, M.D. Mays, T.G. Reinsch, Global soil characterization with VNIR diffuse reflectance spectroscopy, Geoderma 132 (3-4) (2006) 273-290.

[21] A. Han, X.L. Lu, S. Qing, Y.B. Bao, Y.H. Bao, Q. Ma, X.P. Liu, J.Q. Zhang, Rapid determination of low heavy metal concentrations in grassland soils around mining using Vis-NIR spectroscopy: A case study of Inner Mongolia, China, Sensors 21 (9) (2021) 3220.

[22] A. Gholizadeh, M. Saberioon, E. Ben-Dor, R.A. Viscarra Rossel, L. Borůvka, Modelling potentially toxic elements in forest soils with vis-NIR spectra and learning algorithms, Environ. Pollut. 267 (2020) 115574.

[23] H.X. Guo, K. Yang, F. Wu, Y. Chen, J.X. Shen, Regional inversion of soil heavy metal Cr content in agricultural land using Zhuhai-1 hyperspectral images, Sensors 23 (21) (2023) 8756.

[24] C.C. Qi, A. Fourie, G.W. Ma, X.L. Tang, X.H. Du, Comparative study of hybrid artificial intelligence approaches for predicting hangingwall stability, J. Comput. Civ. Eng. 32 (2) (2018) 04017086.

[25] B.L. Li, E. Wang, Z.H. Li, X. Cao, X.F. Liu, M. Zhang, Automatic recognition of effective and interference signals based on machine learning: A case study of acoustic emission and electromagnetic radiation, Int. J. Rock Mech. Min. Sci. 170 (2023) 105505.

[26] J. Zhou, Y. Qiu, M. Khandelwal, S.L. Zhu, X.L. Zhang, Developing a hybrid model of Jaya algorithm-based extreme gradient boosting machine to estimate blast-induced ground vibrations, Int. J. Rock Mech. Min. Sci. 145 (2021) 104856.

[27] X.D. Wu, V. Kumar, J.R. Quinlan, J. Ghosh, Q. Yang, H. Motoda, G.J. McLachlan, A. Ng, B. Liu, P.S. Yu, Z.H. Zhou, M. Steinbach, D.J. Hand, D. Steinberg, Top 10 algorithms in data mining, Knowl. Inf. Syst. 14 (2008) 1-37.

[28] P. McCullagh, J. Nelder, Generalized Linear Models, second ed., Routledge, New York, 2019.

[29] A. Subasi, Practical Machine Learning for Data Analysis Using Python, Academic Press, 2020.

[30] V.N. Vapnik, The Nature of Statistical Learning Theory, second ed., Springer, New York, NY, 1999.

[31] J. Cervantes, F. Garcia-Lamont, L. Rodríguez-Mazahua, A. Lopez, A comprehensive survey on support vector machine classification: Applications, challenges and trends, Neurocomputing 408 (2020) 189-215.

[32] L. Breiman, Random forests, Mach. Lang. 45 (1) (2001) 5-32.

[33] T.K. Ho, Random decision forests, in: Proceedings of the 3rd International Conference on Document Analysis and Recognition, Montreal, 1995, pp. 278-282.

[34] Y. Amit, D. Geman, Shape quantization and recognition with randomized trees, Neural Comput. 9 (7) (1997) 1545-1588.

[35] T.K. Ho, The random subspace method for constructing decision forests, IEEE Trans. Pattern Anal. Mach. Intell. 20 (8) (1998) 832-844.

[36] M. Belgiu, L. Drăguţ, Random forest in remote sensing: A review of applications and future directions, ISPRS J. Photogramm. Remote. Sens. 114 (2016) 24-31.

[37] T.Q. Chen, C. Guestrin, XGBoost: A scalable tree boosting system, in: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016, pp. 785-794.

[38] T.T. Wang, Y.J. Bian, Q.L. Yang, M.Y. Ren, Correction of P/S amplitude ratios for low‐magnitude seismic events based on Bayesian Kriging Method, Bull. Seismol. Soc. Am. 111 (5) (2021) 2799-2813.

[39] X.Y. Liew, N. Hameed, J. Clos, An investigation of XGBoost-based algorithm for breast cancer classification, Mach. Learn. Appl. 6 (2021) 100154.

[40] V.H. Truong, S. Tangaramvong, G. Papazafeiropoulos, An efficient LightGBM-based differential evolution method for nonlinear inelastic truss optimization, Expert Syst. Appl. 237 (2024) 121530.

[41] G. Tóth, A. Jones, L. Montanarella, C. Alewell, C. Ballabio, F. Carre, D. De Brogniez, R. Guicharnaud, C. Gardi, T. Hermann, K. Meusburger, M. Nocita, P. Panagos, E. Rusco, A. Stevens, M. Van Liedekerke, B. Van Wesemael, M. Weynants, Y. Yigini, LUCAS Topoil Survey-Methodology, Data and Results , Publications Office of the European Union, 2013.

[42] G. Tóth, A. Jones, L. Montanarella, The LUCAS topsoil database and derived information on the regional variability of cropland topsoil properties in the European Union, Environ. Monit. Assess. 185 (2013) 7409-7425.

[43] A. Orgiazzi, C. Ballabio, P. Panagos, A. Jones, O. Fernández-Ugalde, LUCAS Soil, the largest expandable soil dataset for Europe: A review, Eur. J. Soil Sci. 69 (1) (2018) 140-153.

[44] Std Miljö & Konsument, Swedish Standard, Sludge, Treated Biowaste and Soil-Digestion of Aqua Regia Soluble Fractions of Elements, EN ISO 54321, Swedish Institute for Standards, 2021.

[45] S. Cole, J. Jeffries, Using Soil Guideline Values, Environmet Agency, 2009.

[46] Y.M. Sun, J.C. Wang, G.L. Guo, H. Li, K. Jones, A comprehensive comparison and analysis of soil screening values derived and used in China and the UK, Environ. Pollut. 256 (2020) 113404.

[47] C.C. Qi, M.T. Wu, H. Liu, Y.J. Liang, X.M. Liu, Z. Lin, Machine learning exploration of the mobility and environmental assessment of toxic elements in mining-associated solid wastes, J. Clean. Prod. 401 (2023) 136771.

[48] A.M.P. Chacón, I.S. Ramírez, F.P.G. Márquez, K-nearest neighbour and K-fold cross-validation used in wind turbines for false alarm detection, Sustain. Futures 6 (2023) 100132.

[49] M.T. Wu, C.C. Qi, Q.S. Chen, H. Liu, Evaluating the metal recovery potential of coal fly ash based on sequential extraction and machine learning, Environ. Res. 224 (2023) 115546.

[50] Z.A. Sejuti, M. Saiful Islam, A hybrid CNN-KNN approach for identification of COVID-19 with 5-fold cross validation, Sens. Int. 4 (2023) 100229.

[51] A. Huda, A. Castaño, A. Niyogi, J. Schumacher, M. Stewart, M. Bruno, M. Hu, F.S. Ahmad, R.C. Deo, S.J. Shah, A machine learning model for identifying patients at risk for wild-type transthyretin amyloid cardiomyopathy, Nat. Commun. 12 (1) (2021) 2725.

[52] R. Agius, C. Brieghel, M.A. Andersen, A.T. Pearson, B. Ledergerber, A. Cozzi-Lepri, Y. Louzoun, C.L. Andersen, J. Bergstedt, J.H. von Stemann, M. Jørgensen, M.-H.E. Tang, M. Fontes, J. Bahlo, C.D. Herling, M. Hallek, J. Lundgren, C.R. MacPherson, J. Larsen, C.U. Niemann, Machine learning can identify newly diagnosed patients with CLL at high risk of infection, Nat. Commun. 11 (1) (2020) 363.

[53] P. Bannigan, Z.Q. Bao, R.J. Hickman, M. Aldeghi, F. Häse, A. Aspuru-Guzik, C. Allen, Machine learning models to accelerate the design of polymeric long-acting injectables, Nat. Commun. 14 (2023) 35.

[54] L. Vo Ngoc, C.Y. Huang, C.J. Cassidy, C. Medrano, J.T. Kadonaga, Identification of the human DPR core promoter element using machine learning, Nature 585 (7852) (2020) 459-463.

[55] D.M. Belete, M.D. Huchaiah, Grid search in hyperparameter optimization of machine learning models for prediction of HIV/AIDS test results, Int. J. Comput. Appl. 44 (9) (2022) 875-886.

[56] M.A. Zöller, M.F. Huber, Benchmark and survey of automated machine learning frameworks, J. Artif. Intell. Res. 70 (2021) 409-472.

[57] K. Attwood, S. Hou, A. Hutson, Application of the skew exponential power distribution to ROC curves, J. Appl. Stat. 50 (8) (2023) 1709-1724.

[58] S.G. Ramirez, R.C. Hales, G.P. Williams, N.L. Jones, Extending SC-PDSI-PM with neural network regression using GLDAS data and permutation feature importance, Environ. Model. Softw. 157 (2022) 105475.

[59] J.S. Zheng, M.T. Wu, Z.M. Yaseen, C.C. Qi, Machine learning models for occurrence form prediction of heavy metals in tailings, Int. J. Min. Reclam. Environ. 37 (10) (2023) 978-995.

[60] C.C. Qi, X.L. Tang, A hybrid ensemble method for improved prediction of slope stability, Int. J. Numer. Anal. Methods Geomech. 42 (15) (2018) 1823-1839.

[61] S. Fabre, X. Briottet, A. Lesaignoux, Estimation of soil moisture content from the spectral reflectance of bare soils in the 0.4-2.5 µm domain, Sensors 15 (2) (2015) 3262-3281.

[62] C.B. Yang, M.C. Feng, L.F. Song, C. Wang, W.D. Yang, Y.K. Xie, B.H. Jing, L.J. Xiao, M.J. Zhang, X.Y. Song, M. Saleem, Study on hyperspectral estimation model of soil organic carbon content in the wheat field under different water treatments, Sci. Rep. 11 (1) (2021) 18582.

[63] B. Koirala, Z. Zahiri, P. Scheunders, A robust supervised method for estimating soil moisture content from spectral reflectance, IEEE Trans. Geosci. Remote Sens. 60 (2022) 1-13.

[64] S. Fei, A. Alizadeh, W.L. Hsu, J.J. Delaunay, H. Daiguji, Analysis of the water adsorption mechanism in metal-organic framework MIL-101(Cr) by molecular simulations, J. Phys. Chem. C 125 (48) (2021) 26755-26769.