Abstract
Purpose
Soil pollution indices are an effective tool in the computation of metal contamination in soil. They monitor soil quality and ensure future sustainability in agricultural systems. However, calculating a soil pollution index requires laboratory measurements of multiple soil heavy metals, which increases the cost and complexity of evaluating soil heavy metal pollution. Visible and near-infrared spectroscopy (VNIR, 350–2500 nm) has been widely used in predicting soil properties due to its advantages of a rapid analysis, non-destructiveness, and a low cost.
Methods
In this study, we evaluated the ability of the VNIR to predict soil heavy metals (As, Cu, Pb, Zn, and Cr) and two commonly used soil pollution indices (Nemerow integrated pollution index, NIPI; potential ecological risk index, RI). Three nonlinear machine learning techniques, including cubist regression tree (Cubist), Gaussian process regression (GPR), and support vector machine (SVM), were compared with partial least squares regression (PLSR) to determine the most suitable model for predicting the soil heavy metals and pollution indices.
Results
The results showed that the nonlinear machine learning models performed significantly better than the PLSR model in most cases. Overall, the SVM model showed a higher prediction accuracy and a stronger generalization for Zn (R2V = 0.95, RMSEV = 6.75 mg kg−1), Cu (R2V = 0.95, RMSEV = 8.04 mg kg−1), Cr (R2V = 0.90, RMSEV = 6.57 mg kg−1), Pb (R2V = 0.86, RMSEV = 4.14 mg kg−1), NIPI (R2V = 0.93, RMSEV = 0.31), and RI (R2V = 0.90, RMSEV 3.88). In addition, the research results proved that the high prediction accuracy of the three heavy metal elements Cu, Pb, and Zn and their significant positive correlations with the soil pollution indices were the reason for the accurate prediction of NIPI and RI.
Conclusion
Using VNIR to obtain soil pollution indices quickly and accurately is of great significance for the comprehensive evaluation, prevention, and control of soil heavy metal pollution.
Similar content being viewed by others
References
Al-Anbari R, Al OAHMJ, Ali FHA (2015) Pollution loads and ecological risk assessment of heavy metals in the urban soil affected by various anthropogenic activities. J ADV RES 3(2):104–110
Askari MS, O’Rourke SM, Holden NM (2015) Evaluation of soil quality for agricultural production using visible–near-infrared spectroscopy. Geoderma 243–244:80–91
Bali AS, Sidhu GPS (2021) Heavy metal contamination indices and ecological risk assessment index to assess metal pollution status in different soils. In: Kumar V, Sharma A, Cerdà A (eds) Heavy metals in the environment: impact, assessment, and remediation. Elsevier, pp 87–98
Ben-Dor E (2002) Quantitative remote sensing of soil properties. Adv Agron 75:173–243
BenDor E, Inbar Y, Chen Y (1997) The reflectance spectra of organic matter in the visible near-infrared and short wave infrared region (400–2500 nm) during a controlled decomposition process. Remote Sens Environ 61(1):1–15
Chakraborty S, Weindorf DC, Paul S, Ghosh B, Li B, Ali MN, Ghosh RK, Ray DP, Majumdar K (2015) Diffuse reflectance spectroscopy for monitoring lead in landfill agricultural soils of India. Geoderma Reg 5:77–85
Chen L, Lai J, Tan K, Wang X, Chen Y, Ding J (2022) Development of a soil heavy metal estimation method based on a spectral index: Combining fractional-order derivative pretreatment and the absorption mechanism. Sci Total Environ 813:151882
Chen ZM, Curran PJ, Hansom JD (1992) Derivative reflectance spectroscopy to estimate suspended sediment concentration. Remote Sens Environ 40(1):67–77
Cheng H, Shen RL, Chen YY, Wan QJ, Shi TZ, Wang JJ, Wan Y, Hong YS, Li XC (2019) Estimating heavy metal concentrations in suburban soils with reflectance spectroscopy. Geoderma 336:59–67
Dong J, Dai W, Xu J, Li S (2016) Spectral estimation model construction of heavy metals in mining reclamation areas. Int J Env Res Pub He 13(7)
Dotto AC, Dalmolin RSD, ten Caten A, Grunwald S (2018) A systematic study on the application of scatter-corrective and spectral-derivative preprocessing for multivariate prediction of soil organic carbon by Vis-NIR spectra. Geoderma 314:262–274
Gong QJ, Deng J, Xiang YC, Wang QF, Yang LQ (2008) Calculating pollution indices by heavy metals in ecological geochemistry assessment and a case study in parks of Beijing. J China Univ Geosci 19(3):230–241
Hakanson L (1980) An ecological risk index for aquatic pollution-control-a sedimentological approach. Water Res 14(8):975–1001
Kemper T, Sommer S (2002) Estimate of heavy metal contamination in soils after a mining accident using reflectance spectroscopy. Environ Sci Technol 36(12):2742–2747
Khosravi V, Doulati Ardejani F, Yousefi S, Aryafar A (2018) Monitoring soil lead and zinc contents via combination of spectroscopy with extreme learning machine and other data mining methods. Geoderma 318:29–41
Kowalska JB, Mazurek R, Gasiorek M, Zaleski T (2018) Pollution indices as useful tools for the comprehensive evaluation of the degree of soil contamination-A review. Environ Geochem Hlth 40(6):2395–2420
Krishnan P, Alexander JD, Butler BJ, Hummel JW (1980) Reflectance technique for predicting soil organic-matter. Soil Sci Soc Am J 44(6):1282–1285
Lin LI (1989) A concordance correlation coefficient to evaluate reproducibility. Biometrics 45(1):255–268
Liu WD, Baret F, Gu XF, Tong QX, Zheng LF, Zhang B (2002) Relating soil surface moisture to reflectance. Remote Sens Environ 81(2):238–246
Morellos A, Pantazi X-E, Moshou D, Alexandridis T, Whetton R, Tziotzios G, Wiebensohn J, Bill R, Mouazen AM (2016) Machine learning based prediction of soil total nitrogen, organic carbon and moisture content by using VIS-NIR spectroscopy. Biosyst Eng 152:104–116
Munnaf MA, Mouazen AM (2021) Development of a soil fertility index using on-line Vis-NIR spectroscopy. Comput Electron Agr 188
Palacios-Orueta A, Ustin SL (1998) Remote sensing of soil properties in the Santa Monica Mountains I. Spectral Analysis Remote Sens Environ 65(2):170–183
Paz-Kagan T, Shachak M, Zaady E, Karnieli A (2014) A spectral soil quality index (SSQI) for characterizing soil function in areas of changed land use. Geoderma 230–23:171–184
Paz-Kagan T, Zaady E, Salbach C, Schmidt A, Lausch A, Zacharias S, Notesco G, Ben-Dor E, Karnieli A (2015) Mapping the Spectral Soil Quality Index (SSQI) Using Airborne Imaging Spectroscopy. Remote Sens 7(11):15748–15781
Quinlan JR (1993) Combining instance-based and model-based learning. In: Utgoff PE (ed) Machine Learning: Proceedings of the Tenth International Conference. Morgan Kaufmann Publishers Inc, San Mateo, CA, pp 236–243
Recena R, Fernández-Cabanás VM, Delgado A (2019) Soil fertility assessment by Vis-NIR spectroscopy: Predicting soil functioning rather than availability indices. Geoderma 337:368–374
Smola AJ, Scholkopf B (2004) A tutorial on support vector regression. Stat Comput 14(3):199–222
St. Luce M, Ziadi N, Gagnon B, Karam A (2017) Visible near infrared reflectance spectroscopy prediction of soil heavy metal concentrations in paper mill biosolid- and liming by-product-amended agricultural soils. Geoderma 288:23–36
Stoner ER, Baumgardner MF (1981) Characteristic variations in reflectance of surface soils. Soil Sci Soc Am J 45(6):1161–1165
Sun WC, Zhang X, Sun XJ, Sun YL, Cen Y (2018) Predicting nickel concentration in soil using reflectance spectroscopy associated with organic matter and clay minerals. Geoderma 327:25–35
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(1–3):455–462
Tan K, Ye YY, Du PJ, Zhang QQ (2014) Estimation of heavy metal concentrations in reclaimed mining soils using reflectance spectroscopy. Spectrosc Spectr Anal 34(12):3317–3322
Tan K, Ma W, Wu F, Du Q (2019) Random forest-based estimation of heavy metal concentration in agricultural soils with hyperspectral sensor data. Environ Monit Assess 191(7):446
Viscarra Rossel RA, Behrens T (2010) Using data mining to model and interpret soil diffuse reflectance spectra. Geoderma 158(1–2):46–54
Viscarra Rossel RA, Rizzo R, Demattê JAM, Behrens T (2010) Spatial Modeling of a Soil Fertility Index using Visible-Near-Infrared Spectra and Terrain Attributes. Soil Sci Soc Am J 74(4):1293–1300
Viscarra Rossel RA, Hicks WS (2015) Soil organic carbon and its fractions estimated by visible-near infrared transfer functions. Eur J Soil Sci 66(3):438–450
Wang JJ, Cui LJ, Gao WX, Shi TZ, Chen YY, Gao Y (2014) Prediction of low heavy metal concentrations in agricultural soils using visible and near-infrared reflectance spectroscopy. Geoderma 216:1–9
Wei ZY, Wang DF, Zhou HP, Qi ZP (2011) Assessment of soil heavy metal pollution with principal component analysis and geoaccumulation index. Procedia Environ Sci 10:1946–1952
Weissmannová HD, Pavlovský J (2017) Indices of soil contamination by heavy metals – methodology of calculation for pollution assessment (minireview). Environ Monit Assess 189:616
Wold S, Sjöström M, Eriksson L (2001) PLS-regression: a basic tool for chemometrics. Chemometr Intell Lab 58(2):109–130
Xu SX, Wang MY, Shi XZ (2020) Hyperspectral imaging for high-resolution mapping of soil carbon fractions in intact paddy soil profiles with multivariate techniques and variable selection. Geoderma 370:114358
Yang MH, Mouazen A, Zhao XM, Guo X (2020) Assessment of a soil fertility index using visible and near-infrared spectroscopy in the rice paddy region of southern China. Eur J Soil Sci 71(4):615–626
Zhou W, Yang H, Xie LJ, Li HR, Huang L, Zhao YP, Yue TX (2021) Hyperspectral inversion of soil heavy metals in Three-River Source Region based on random forest model. Catena 202
Zhu W, Bian B, Li L (2008) Heavy metal contamination of road-deposited sediments in a medium size city of China. Environ Monit Assess 147(1–3):171–181
Acknowledgements
We would like to thank Dr. Xianzhang Pan and Dr. Changkun Wang of ISSAS for their help in VNIR spectroscopy analysis. Many thanks also go to the anonymous reviewers whose constructive comments helped improve this paper.
Funding
This work was supported by the Strategic Priority Research Program of the Chinese Academy of Sciences (XDA28100500) and the National Natural Science Foundation of China (41771253) .
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Consent to participate
This manuscript is new and not being considered elsewhere. All authors have approved the submission of this manuscript.
Conflict of interest
The authors declare no competing interests.
Additional information
Responsible editor: Jun Zhou
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
About this article
Cite this article
Wang, Y., Zhao, Y. & Xu, S. Application of VNIR and machine learning technologies to predict heavy metals in soil and pollution indices in mining areas. J Soils Sediments 22, 2777–2791 (2022). https://doi.org/10.1007/s11368-022-03263-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11368-022-03263-3