标題: Diagnosis of cadmium contamination in urban and suburban soils using visible-to-near-infrared spectroscopy

作者: Hong, YS (Hong, Yongsheng); Chen, YY (Chen, Yiyun); Shen, RL (Shen, Ruili); Chen, SC (Chen, Songchao); Xu, G (Xu, Gang); Cheng, H (Cheng, Hang); Guo, L (Guo, Long); Wei, ZS (Wei, Zushuai); Yang, J (Yang, Jian); Liu, YL (Liu, Yaolin); Shi, Z (Shi, Zhou); Mouazen, AM (Mouazen, Abdul M.)

來源出版物: ENVIRONMENTAL POLLUTION 卷:291DOI: 10.1016/j.envpol.2021.118128出版年: DEC 15 2021

摘要: Previous studies have mostly focused on using visible-to-near-infrared spectral technique to quantitatively estimate soil cadmium (Cd) content, whereas little attention has been paid to identifying soil Cd contamination from a perspective of spectral classification. Here, we developed a framework to compare the potential of two spectral transformations (i.e., raw reflectance and continuum removal [CR]), three optimization strategies (i.e., full-spectrum, Boruta feature selection, and synthetic minority over-sampling technique [SMOTE]), and three classification algorithms (i.e., partial least squares discriminant analysis, random forest [RF], and support vector machine) for diagnosing soil Cd contamination. A total of 536 soil samples were collected from urban and suburban areas located in Wuhan City, China. Specifically, Boruta and SMOTE strategies were aimed at selecting the most informative predictors and obtaining balanced training datasets, respectively. Results indicated that soils contaminated by Cd induced decrease in spectral reflectance magnitude. Classification models developed after Boruta and SMOTE strategies out-performed to those from full-spectrum. A diagnose model combining CR preprocessing, SMOTE strategy, and RF algorithm achieved the highest validation accuracy for soil Cd (Kappa = 0.74). This study provides a theoretical reference for rapid identification of and monitoring of soil Cd contamination in urban and suburban areas.

作者關鍵詞: Urban and suburban soil Cd contamination; Visible-to-near-infrared spectroscopy; Boruta algorithm; Synthetic minority over-sampling technique; Machine learning

地址: [Hong, Yongsheng; Chen, Yiyun; Cheng, Hang; Liu, Yaolin] Wuhan Univ, Sch Resource & Environm Sci, Wuhan 430079, Peoples R China.

[Hong, Yongsheng; Mouazen, Abdul M.] Univ Ghent, Dept Environm, Coupure Links 653, B-9000 Ghent, Belgium.

[Shen, Ruili] Hubei Acad Environm Sci, Wuhan 430072, Peoples R China.

[Chen, Songchao; Shi, Zhou] Zhejiang Univ, Coll Environm & Resource Sci, Inst Agr Remote Sensing & Informat Technol Applic, Hangzhou 310058, Peoples R China.

[Xu, Gang] Wuhan Univ, Sch Remote Sensing & Informat Engn, Wuhan 430079, Peoples R China.

[Guo, Long] Huazhong Agr Univ, Coll Resources & Environm, Wuhan 430070, Peoples R China.

[Wei, Zushuai; Yang, Jian] Minist Ecol & Environm, South China Inst Environm Sci, Guangzhou 510530, Peoples R China.

通訊作者地址: Chen, YY (通訊作者)，Wuhan Univ, Sch Resource & Environm Sci, Wuhan 430079, Peoples R China.

電子郵件地址: chenyy@whu.edu.cn

影響因子：8.071