基于激光诱导击穿光谱技术结合随机森林算法快速定量分析土壤中重金属元素

引用本文: 李茂刚, 梁晶, 闫春华, 汤宏胜, 张天龙, 李华. 基于激光诱导击穿光谱技术结合随机森林算法快速定量分析土壤中重金属元素[J]. 分析化学, 2021, 49(8): 1410-1418. doi: 10.19756/j.issn.0253-3820.211067 shu

Citation: LI Mao-Gang, LIANG Jing, YAN Chun-Hua, TANG Hong-Sheng, ZHANG Tian-Long, LI Hua. Rapid Quantitative Analysis of Heavy Metals in Soil by Laser Induced Breakdown Spectroscopy Combined with Random Forest Algorithm[J]. Chinese Journal of Analytical Chemistry, 2021, 49(8): 1410-1418. doi: 10.19756/j.issn.0253-3820.211067 shu

基于激光诱导击穿光谱技术结合随机森林算法快速定量分析土壤中重金属元素

李茂刚 ^1, ,
梁晶 ^1, ,
闫春华 ^2, ,
汤宏胜 ^1, ,
张天龙 ^{1,
,} ,
李华 ^{1,2,
,}

1.
西北大学化学与材料科学学院, 合成与天然功能分子教育部重点实验室, 西安 710127;
2.
西安石油大学化学化工学院, 西安 710065

通讯作者: 张天龙,E-mail:tlzhang@nwu.edu.cn; 李华,E-mail:huali@nwu.edu.cn

基金项目:
国家自然科学基金项目（Nos.22073074，21873076，21675123，21605123）资助。

摘要: 土壤中重金属的检测对土壤污染分析及监控具有重要意义。本研究建立了一种基于激光诱导击穿光谱（Laser induced breakdown spectroscopy，LIBS）技术结合随机森林（Random forest，RF）算法快速定量分析土壤中重金属元素的方法。采用激光诱导击穿光谱仪对22组土壤样品的LIBS光谱进行采集，探究了不同光谱预处理方法对基于土壤样品LIBS光谱的RF模型预测性能的影响。以归一化处理后的LIBS光谱数据作为初始输入变量，分别构建了基于全谱、特征波段、变量重要性以及后向区间的RF校正模型，用于土壤中4种重金属元素（Cu、Cr、Pb和Ni）含量的测定。结果表明，相比于基于全谱、特征波段和变量重要性的RF校正模型，基于后向区间的随机森林校正模型（Backward interval random forest，BiRF）对上述4种元素的定量分析性能更好，Cu、Cr、Pb和Ni的最优均方根误差（Root mean square error，RMSE）值分别为8.0221、6.0120、1.7382和1.2851 μg/g，最优决定系数（Coefficient of determination，R²）值分别为0.9610、0.8985、0.7021和0.9850。本研究结果表明，LIBS技术结合BiRF算法是一种快速测定土壤中重金属元素的新方法。

关键词:

English

Rapid Quantitative Analysis of Heavy Metals in Soil by Laser Induced Breakdown Spectroscopy Combined with Random Forest Algorithm

1.
Key Laboratory of Synthetic and Natural Functional Molecule of the Ministry of Education, College of Chemistry & Materials Science, Northwest University, Xi'an 710127, China;
2.
College of Chemistry and Chemical Engineering, Xi'an Shiyou University, Xi'an 710065, China

Corresponding author: ZHANG Tian-Long, ; LI Hua,

Received Date: 25 January 2021
Revised Date: 09 April 2021
Fund Project:
Supported by the National Natural Science Foundation of China (Nos.22073074, 21873076, 21675123, 21605123).

Abstract: A rapid quantitative analysis method for heavy metals in soil based on laser-induced breakdown spectroscopy (LIBS) and random forest (RF) algorithm was developed. LIBS spectra of 22 soil samples were collected by LIBS spectrometer. The effects of different spectral pretreatment methods on the prediction performance of RF model based on LIBS spectra of soil samples were explored. With normalized LIBS spectral data as initial input variables, the RF calibration models based on full spectrum, characteristic band, variable importance and backward interval were constructed for the quantitative analysis of Cu, Cr, Pb and Ni in soil. The results showed that, compared with the RF calibration models based on full spectrum, characteristic band and variable importance, the RF calibration model based on backward interval (BiRF) had a better performance in quantitative analysis of Cu, Cr, Pb and Ni in soil. The optimal root mean square error (RMSE) values of Cu, Cr, Pb and Ni were 8.0221, 6.0120, 1.7382 and 1.2851 μg/g, respectively, and the optimal coefficient of determination (R²) values were 0.9610, 0.8985, 0.7021 and 0.9850, respectively. The results showed that the LIBS technology combined with BiRF algorithm was a feasible method for detection of heavy metals in soil.

Key words:

1. [1]
  PALANSOORIYA K N, SHAHEEN S M, CHEN S S, TSANG D C W, OK Y S. Environ. Int., 2020, 134: 105046.PALANSOORIYA K N, SHAHEEN S M, CHEN S S, TSANG D C W, OK Y S. Environ. Int., 2020, 134: 105046.
2. [2]
  ZHANG J, LI H, ZHOU Y, LEI D, JING Y. Environ. Pollut., 2018, 235: 710-719.ZHANG J, LI H, ZHOU Y, LEI D, JING Y. Environ. Pollut., 2018, 235: 710-719.
3. [3]
  GONDEK K, MIERZWA-HERSZTEK M, KOPEC M. J. Environ. Manage., 2018, 210: 1-2.GONDEK K, MIERZWA-HERSZTEK M, KOPEC M. J. Environ. Manage., 2018, 210: 1-2.
4. [4]
  HOU S, ZHENG N, TANG L, JI X, LI Y, HU X. Environ. Int., 2019, 128: 430-437.HOU S, ZHENG N, TANG L, JI X, LI Y, HU X. Environ. Int., 2019, 128: 430-437.
5. [5]
  SHARMA S, NAGPAL A K, KAUR I. Food Chem., 2018, 255: 15-22.SHARMA S, NAGPAL A K, KAUR I. Food Chem., 2018, 255: 15-22.
6. [6]
  YU J, ZHANG X, LU Q, SUN D, WANG X, ZHUA S, ZHANG Z, YANG W. Spectrochim. Acta, Part B, 2018, 145: 64-70.YU J, ZHANG X, LU Q, SUN D, WANG X, ZHUA S, ZHANG Z, YANG W. Spectrochim. Acta, Part B, 2018, 145: 64-70.
7. [7]
  ZHOU X, ZHENG N, SU C, WANG J, SOYEURT H. Environ. Pollut., 2019, 255: 113322.ZHOU X, ZHENG N, SU C, WANG J, SOYEURT H. Environ. Pollut., 2019, 255: 113322.
8. [8]
  GU Gao-Quan, WAN Xiao-Ming, ZENG Wei-Bin, LEI Mei. Environ. Sci., 2021, 42(3): 1105-1113. 顾高铨, 万小铭, 曾伟斌, 雷梅. 环境科学, 2021, 42(3): 1105-1113.
9. [9]
  WANG Rui, DENG Hai, JIA Zhong-Min, WANG Jia-Bin, YU Fei, ZENG Qin-Qin. Environ. Sci., 2021, 42(6): 3018-3027. 王锐, 邓海, 贾中民, 王佳彬, 余飞, 曾琴琴. 环境科学, 2021, 42(6): 3018-3027.
10. [10]
  HAO Z, LIU L, SHEN M, ZHOU R, LI J, GUO L, LI X, LU Y, ZENG X. J. Anal. At. Spectrom., 2018, 33: 1564-1570.HAO Z, LIU L, SHEN M, ZHOU R, LI J, GUO L, LI X, LU Y, ZENG X. J. Anal. At. Spectrom., 2018, 33: 1564-1570.
11. [11]
  QI J, ZHANG T, TANG H, LI H. Spectrochim. Acta, Part B, 2018, 149: 288-293.QI J, ZHANG T, TANG H, LI H. Spectrochim. Acta, Part B, 2018, 149: 288-293.
12. [12]
  ZHANG T, LIANG L, WANG K, TANG H, YANG X, DUAN Y, LI H. J. Anal. At. Spectrom., 2014, 29: 2323-2329.ZHANG T, LIANG L, WANG K, TANG H, YANG X, DUAN Y, LI H. J. Anal. At. Spectrom., 2014, 29: 2323-2329.
13. [13]
  CONNORS B, SOMERS A, DAY D. Appl. Spectrosc., 2016, 70: 810-815.CONNORS B, SOMERS A, DAY D. Appl. Spectrosc., 2016, 70: 810-815.
14. [14]
  TANG H, ZHANG T, YANG X, LI H. Anal. Methods, 2015, 7: 9171-9176.TANG H, ZHANG T, YANG X, LI H. Anal. Methods, 2015, 7: 9171-9176.
15. [15]
  NATARAJAN S, BAJAJ H. J. Environ. Chem. Eng., 2016, 4: 4631-4643.NATARAJAN S, BAJAJ H. J. Environ. Chem. Eng., 2016, 4: 4631-4643.
16. [16]
  NASSEF O, AHMED H, HARITH M. Anal. Methods, 2016, 8: 7096-7106.NASSEF O, AHMED H, HARITH M. Anal. Methods, 2016, 8: 7096-7106.
17. [17]
  DHANADA V, GEORGE S, KARTHA V, CHIDANGIL S, UNNIKRISHNAN V. Appl. Spectrosc. Rev., 2020. DOI: 10.1080/05704928.2020.1800486.DHANADA V, GEORGE S, KARTHA V, CHIDANGIL S, UNNIKRISHNAN V. Appl. Spectrosc. Rev., 2020. DOI: 10.1080/05704928.2020.1800486.
18. [18]
  XU X, DU C, MA F, SHEN Y, WU K, LIANG D, ZHOU J. Geoderma, 2019, 355: 113905.XU X, DU C, MA F, SHEN Y, WU K, LIANG D, ZHOU J. Geoderma, 2019, 355: 113905.
19. [19]
  L'HERMITE D, VORS E, VERCOUTER T, MOUTIERS G. Environ. Sci. Pollut. Res., 2016, 23: 8219-8226.L'HERMITE D, VORS E, VERCOUTER T, MOUTIERS G. Environ. Sci. Pollut. Res., 2016, 23: 8219-8226.
20. [20]
  SENESI G, SENESI N. Anal. Chim. Acta, 2016, 938: 7-17.SENESI G, SENESI N. Anal. Chim. Acta, 2016, 938: 7-17.
21. [21]
  El HADDAD J, VILLOT-KADRI M, ISMAEL A, GALLOU G, MICHEL K, BRUYERE D, LAPERCHE V, CANIONI L, BOUSQUET B. Spectrochim. Acta, Part B, 2013, 79-80: 51-57.El HADDAD J, VILLOT-KADRI M, ISMAEL A, GALLOU G, MICHEL K, BRUYERE D, LAPERCHE V, CANIONI L, BOUSQUET B. Spectrochim. Acta, Part B, 2013, 79-80: 51-57.
22. [22]
  LI Zheng-Feng, XU Guang-Jin, WANG Jia-Jun, DU Guo-Rong, CAI Wen-Sheng, SHAO Xue-Guang. Chin. J. Anal. Chem., 2016, 44(2): 305-309. 李正风, 徐广晋, 王家俊, 杜国荣, 蔡文生, 邵学广. 分析化学, 2016, 44(2): 305-309.
23. [23]
  LI M, XUE J, DU Y, ZHANG T, LI H. Energy Fuels, 2019, 33(12): 12286-12294.LI M, XUE J, DU Y, ZHANG T, LI H. Energy Fuels, 2019, 33(12): 12286-12294.
24. [24]
  YUAN Zi-Ran, WEI Li-Fei, ZHANG Yang-Xi, YU Ming, YAN Xin-Ru. Spectrosc. Spectral Anal., 2020, 40(2): 567-573. 袁自然, 魏立飞, 张杨熙, 余铭, 闫芯茹. 光谱学与光谱分析, 2020, 40(2): 567-573.
25. [25]
  ZHANG T, XIA D, TANG H, YANG X, LI H. Chemom. Intell. Lab. Syst., 2016, 157: 196-201.ZHANG T, XIA D, TANG H, YANG X, LI H. Chemom. Intell. Lab. Syst., 2016, 157: 196-201.
26. [26]
  KIM G, KWAK J, KIM K, LEE H, KIM K, YANG H, PARK K. J. Hazard. Mater., 2013, 263: 754-760.KIM G, KWAK J, KIM K, LEE H, KIM K, YANG H, PARK K. J. Hazard. Mater., 2013, 263: 754-760.
27. [27]
  BREIMAN L. Mach. Learn., 2001, 45: 5-32.BREIMAN L. Mach. Learn., 2001, 45: 5-32.
28. [28]
  LI Mao-Gang, YAN Chun-Hua, XUE Jia, ZHANG Tian-Long, LI Hua. Chin. J. Anal. Chem., 2019, 47(12): 1995-2003. 李茂刚, 闫春华, 薛佳, 张天龙, 李华. 分析化学, 2019, 47(12): 1995-2003.
29. [29]
  LI M, XU Y, MEN J, YAN C, TANG H, ZHANG T, LI H. Spectrochim. Acta, Part A, 2021, 251: 119430.LI M, XU Y, MEN J, YAN C, TANG H, ZHANG T, LI H. Spectrochim. Acta, Part A, 2021, 251: 119430.
30. [30]
  WANG P, LI N, YAN C, FENG Y, DING Y, ZHANG T, LI H. Anal. Methods, 2019, 11: 3419-3428.WANG P, LI N, YAN C, FENG Y, DING Y, ZHANG T, LI H. Anal. Methods, 2019, 11: 3419-3428.
31. [31]
  RAN Z, SUN L, LIU Y, PAN X, LI J, LIU Y. Infrared Phys. Technol., 2020, 105: 103207.RAN Z, SUN L, LIU Y, PAN X, LI J, LIU Y. Infrared Phys. Technol., 2020, 105: 103207.

扫一扫看文章

计量

PDF下载量: 22
文章访问数: 889
HTML全文浏览量: 136

通讯作者: 陈斌, bchen63@163.com

1.
沈阳化工大学材料科学与工程学院沈阳 110142

基于激光诱导击穿光谱技术结合随机森林算法快速定量分析土壤中重金属元素

通讯作者: 张天龙,E-mail:tlzhang@nwu.edu.cn; 李华,E-mail:huali@nwu.edu.cn

English

Rapid Quantitative Analysis of Heavy Metals in Soil by Laser Induced Breakdown Spectroscopy Combined with Random Forest Algorithm

Corresponding author: ZHANG Tian-Long, ; LI Hua,

CCS Chemistry：嵌段共聚物自组装成 “三明治”二维有机材料，实现纳米级压力传感功能

CCS Chemistry：颜徐州、鲍哲南：你的皮肤可能是一片SPMs

CCS Chemistry：工作高效不疲劳，只须让催化剂动起来

CCS Chemistry：静电组装导向聚合- 聚电解质纳米凝胶量化制备新策略

CCS Chemistry：金黄色葡萄球菌醛基脱氢酶是如何识别特异性底物的？

计量

通讯作者: 陈斌, bchen63@163.com

中国化学会秘书处

基于激光诱导击穿光谱技术结合随机森林算法快速定量分析土壤中重金属元素

通讯作者: 张天龙,E-mail:tlzhang@nwu.edu.cn; 李华,E-mail:huali@nwu.edu.cn

English

Rapid Quantitative Analysis of Heavy Metals in Soil by Laser Induced Breakdown Spectroscopy Combined with Random Forest Algorithm

Corresponding author: ZHANG Tian-Long, ; LI Hua,

CCS Chemistry：嵌段共聚物自组装成 “三明治”二维有机材料，实现纳米级压力传感功能

CCS Chemistry：颜徐州、鲍哲南： 你的皮肤可能是一片SPMs

CCS Chemistry：工作高效不疲劳，只须让催化剂动起来

CCS Chemistry：静电组装导向聚合- 聚电解质纳米凝胶量化制备新策略

CCS Chemistry：金黄色葡萄球菌醛基脱氢酶是如何识别特异性底物的？

计量

文章相关

通讯作者: 陈斌, bchen63@163.com

中国化学会秘书处

CCS Chemistry：颜徐州、鲍哲南：你的皮肤可能是一片SPMs