基于可见光/近红外反射光谱的沉积型稀土矿La元素含量无损检测

引用本文: 曹发生, 刘严松, 何政伟, 刘心怡, 龚大兴, 孙传敏. 基于可见光/近红外反射光谱的沉积型稀土矿La元素含量无损检测[J]. 分析化学, 2021, 49(2): 292-300. doi: 10.19756/j.issn.0253-3820.191717 shu

Citation: CAO Fa-Sheng, LIU Yan-Song, HE Zheng-Wei, LIU Xin-Yi, GONG Da-Xing, SUN Chuan-Min. Non-destructive Detection of La Content in Sedimentary Rare Earth Ores Based on Visible-Near Infrared Spectroscopy[J]. Chinese Journal of Analytical Chemistry, 2021, 49(2): 292-300. doi: 10.19756/j.issn.0253-3820.191717 shu

基于可见光/近红外反射光谱的沉积型稀土矿La元素含量无损检测

1.
地质灾害防治与地质环境保护国家重点实验室(成都理工大学), 成都 610059;
2.
国土资源部构造成矿成藏重点实验室(成都理工大学), 成都 610059;
3.
成都理工大学地球科学学院, 成都 610059;
4.
中国地质科学院矿产综合利用研究所, 成都 610041

通讯作者: 何政伟,E-mail:hzw@cdut.edu.cn

基金项目:
国家自然科学基金项目（No.41602120）、中国地质调查局能源资源基地综合地质调查项目（No.DD20189507）和四川省国土资源厅科技基金项目（No.J-2016-7）资助。

摘要: 以黔西北二叠系宣威组沉积型稀土矿中的La元素为研究对象，对其进行光谱学分析的基础上，应用机器学习中遗传算法优化的极限学习机（Genetic algorithm-extreme learning machine model，GA-ELM）建模方法对La元素进行了高光谱定量估算反演。通过多种光谱变换（Savitzky-Golay平滑、微分、倒数、连续统去除等）后，使用了光谱特征细节凸显的反射率二阶微分研究对比了变量相关性系数（Pearson相关系数）和变量重要性评价（Competitive adaptive reweighted sampling，CARS；Successive projections algorithm，SPA；Radom frog，RF）两种特征变量选取方法所建立的数学模型精度差异。结果表明，沉积型稀土矿样中La元素含量与光谱反射率是一种非线性关系，不同的光谱变换方法对La含量信息提取能力不同，每种光谱变换都对应特定的敏感波谱区间。通过变量重要性评价方法所建立的模型比变量相关性系数所建立矿样La含量反演模型精度高。变量重要性评价筛选方法提取的特征变量反演模型显示，算法筛选的12个特征波长所建立的CARS-GA-ELM模型效果最佳，R²（Determination coefficients）、RMSE（Root mean square error）和MRE（Mean relative error）分别为0.99、11.36 mg/kg、11.87%，能较好地检测La元素的含量。研究为"点"上沉积型稀土La元素的可见光-近红外光谱定量快速的反演研究提供了新的测试方法，为其它稀土土壤元素的光谱检测提供了思路，同时也为区域面积性的高光谱稀土资源的定量反演评价提供了理论依据。

关键词:

English

Non-destructive Detection of La Content in Sedimentary Rare Earth Ores Based on Visible-Near Infrared Spectroscopy

1.
State Key Laboratory of Geohazard Prevention and Geoenvironment Protection, Chengdu University of Technology, Chengdu 610059, China;
2.
Ministry of Land and Resources Key Laboratory of Tectonic Controlled Mineralization and Oil Reservoir, Chengdu 610059, China;
3.
College of Earth Sciences, Chengdu University of Technology, Chengdu 610059, China;
4.
Institute of Multipurpose Utilization of Mineral Resources, Chinese Academy of Geological Sciences, Chengdu 610041, China

Corresponding author: HE Zheng-Wei, hzw@cdut.edu.cn

Received Date: 04 December 2019
Revised Date: 17 December 2020
Fund Project:
Supported by the National Natural Science Foundation of China (No.41602120), the China Geology Survey Project (No.DD20189507) and the Science and Technology Fund of Sichuan Provincial Department of Land and Resources Project (No.KJ-2016-7).

Abstract: This work studied on La element, which hosted in the Sedimentary rare earth deposits of the Permian Xuanwei Formation, Northwest Guizhou Province. Based on the study of rare earth soil spectroscopy, the hyperspectral quantitative estimation and inversion of La element were carried out under GA-ELM model. After a variety of spectral transformations (S-G smoothing, differential, reciprocal, continuum removal), the accuracy differences of the mathematical models established by two methods of selecting characteristic variables (Pearson correlation coefficient and variable importance assessment (CARS, SPA, RF)) were studied and compared. The results showed that there was a non-linear relationship between the content of La in mineral samples and the spectral reflectance. Different spectral transformation methods had different ability to extract the information of La content in soil. Each spectral transformation corresponded to a specific sensitive spectral interval. The accuracy of the inversion model of soil La content based on the method of variable importance evaluation was higher than that based on the correlation coefficient of variables. Among them, the best model was the first-order reciprocal of absorbance. The value of prediction R² reached 0.89, but the RMSE was 36.26 mg/kg, and the mean relative error reached 45.97%, showing a poor effect. The inversion model of characteristic variables extracted by the method of variable importance evaluation and screening showed that CARS-GA-ELM had the best effect, with R², RMSE and MRE reaching 0.99, 11.36 mg/kg, 11.87%, respectively, which could be well used to detect the content of La element. The research provided a new testing method theory for the fast and quantitative inversion of La element in soil on spot, showed a thought for the hyperspectral detection of other rare earth elements, and also provided a theoretical basis for the quantitative inversion and evaluation of regional hyperspectral rare earth resources.

Key words:

Sedimentary rare earth ores
/ Characteristic variable selection
/ Visible-near infrared spectroscopy
/ Quantitative inversion
/ Genetic algorithm-extreme learning machine model
/ Xuanwei Formation

1. [1]
  WANG Deng-Hong. Acta Geol. Sin., 2019, 93(6):1189-1209. 王登红. 地质学报, 2019, 93(6):1189-1209.
2. [2]
  CHEN Yu-Chuan. Acta Geol. Sin., 2019, 93(6):1. 陈毓川. 地质学报, 2019, 93(6):1.
3. [3]
  WANG Deng-Hong, WANG Rui-Jiang, LI Jian-Kang, ZHAO Zhi, YU Yang, DAI Jing-Jing, CHEN Zheng-Hui, LI De-Xian, QU Wen-Jun, DENG Mao-Chun, FU Xiao-Fang, SUN Yan, ZHENG Guo-Dong. Geol. China, 2013, 40(2):361-370. 王登红, 王瑞江, 李建康, 赵芝, 于扬, 代晶晶, 陈郑辉, 李德先, 屈文俊, 邓茂春, 付小方, 孙艳, 郑国栋. 中国地质, 2013, 40(2):361-370.
4. [4]
  ZHAO Zhi, CHEN Zheng-Hui, ZOU Xin-Yong, WANG Deng-Hong, CHEN Zhen-Yu. Earth Sci., 2018, 43(10):3652-3663. 赵芝, 陈郑辉, 邹新勇, 王登红, 陈振宇. 地球科学, 2018, 43(10):3652-3663.
5. [5]
  QU Wen-Jun, WANG Deng-Hong, ZHU Yun, FAN Xing-Tao, LI Chao, WEN Hong-Li. Acta Geol. Sin., 2019, 93(6):1514-1522. 屈文俊, 王登红, 朱云, 樊兴涛, 李超, 温宏利. 地质学报, 2019, 93(6):1514-1522.
6. [6]
  XU Yin, DAI Zong-Ming, GONG Da-Xing, HUI Bo. Multipurp. Util. Miner. Resour., 2018, 6:90-94. 徐莺, 戴宗明, 龚大兴, 惠博. 矿产综合利用, 2018, 6:90-94.
7. [7]
  TIAN En-Yuan, GONG Da-Xing, LAI Yang, QIU Xiao-Long, XIE Hua, TIAN Kang-Zhi. Earth Sci. (Wuhan, China). http://kns.cnki.net/kcms/detail/42.1874.P.20201105.1401.016.html. 田恩源, 龚大兴, 赖杨, 邱小龙, 谢华, 田康志. 地球科学. http://kns.cnki.net/kcms/detail/42.1874.P.20201105.1401.016.html.
8. [8]
  BVNZLI J G, ELISEEVA S V. Lanthanide Lumin., 2011, 7:1-45.
9. [9]
  DAI Jing-Jing, WANG Deng-Hong, LI Qing-Ting, CHEN Zheng-Hui. Spectrosc. Spect. Anal., 2014, 34(5):1158-1162. 代晶晶, 王登红, 李庆亭, 陈郑辉. 光谱学与光谱分析, 2014, 34(5):1158-1162.
10. [10]
  DAI Jing-Jing, WANG Deng-Hong, CHEN Zheng-Hui. Acta Geosci. Sin., 2017, 38(4):523-528. 代晶晶, 王登红, 陈郑辉. 地球学报, 2017, 38(4):523-528.
11. [11]
  DAI Jing-Jing, WU Ya-Nan, LING Tian-Yu. Spectrosc. Spect. Anal., 2018, 38(12):3801-3808. 代晶晶, 吴亚楠, 令天宇. 光谱学与光谱分析, 2018, 38(12):3801-3808.
12. [12]
  DAI J, WANG D, CHEN Z. J. Rare Earths, https://doi.org/10.1016/j.jre.2020.09.016.
13. [13]
  BATSANOV S S, DERBENEVA S S, BATSANOVA L R. J. Appl. Spectrosc., 1969, 10(2):240-242.
14. [14]
  MEER F V D. Int. J. Appl. Earth OBS, 2004, 5(1):55-68.
15. [15]
  CHEN Yong-Gan, WANG Mei-Juan, LI Peng. Spectrosc. Spect. Anal., 2015, 35(11):3172-3175. 陈勇敢, 王美娟, 李鹏. 光谱学与光谱分析, 2015, 35(11):3172-3175.
16. [16]
  TURNER D J, RIVARD B, GROAT L A. Am. Mineral., 2014, 99(7):1335-1346.
17. [17]
  TURNER D J, RIVARD B, GROAT L A. Am. Mineral., 2016, 101(9-10):2264-2278.
18. [18]
  TURNER D J. RIVARD B, GROAT L A. Am. Mineral., 2018, 103(6):927-943.
19. [19]
  CHENG Gong, LI Jia-Xuan, WANG Zhao-Peng, HU Zhen-Guang, NING Qing-Kun. Spectrosc. Spect. Anal., 2019, 39(5):1571-1578成功, 李嘉璇, 王朝鹏, 胡振光, 宁庆坤. 光谱学与光谱分析, 2019, 39(5):1571-1578.
20. [20]
  WANG C K, ZHANG T L, PAN X Z. Geoderma, 2017, 306:120-126.
21. [21]
  HE Jun-Liang, ZHANG SHU Yuan, ZHA Yong, JIANG Jian-Jun. Remot. Sens. Technol. Appl., 2015, 30(3):407-412. 贺军亮, 张淑媛, 查勇, 蒋建军. 遥感技术与应用, 2015, 30(3):407-412.
22. [22]
  TENG Jing, HE Zheng-Wei, NI Zhong-Yun, ZHAO Yin-Quan, ZHANG Zhi. Spectrosc. Spect. Anal., 2016, 36(11):3637-3642. 滕靖, 何政伟, 倪忠云, 赵印泉, 张志. 光谱学与光谱分析, 2016, 36(11):3637-3642.
23. [23]
  LI Pao, ZHOU Jun, JIANG Li-Wen, LIU Xia, DU Guo-Rong. Spectrosc. Spect. Anal., 2019, 39(5):1428-1432. 李跑, 周骏, 蒋立文, 刘霞, 杜国荣. 光谱学与光谱分析, 2019, 39(5):1428-1432.
24. [24]
  KENNARD R W, STONE L A. Technometrics, 1969, 11(1):137-148.
25. [25]
  HUANG Zhuang-Rong, SHA Sha, RONG Zheng-Qin, LIU Hai-Ying, CHEN Jin-Hong, ZHU Shui-Jin. Chin. J. Anal. Chem., 2013, 41(6):922-926. 黄庄荣, 沙莎, 荣正勤, 刘海英, 陈进红, 祝水金. 分析化学, 2013, 41(6):922-926.
26. [26]
  XU Ming-Xing, WU Shao-Hua, ZHOU Lu-Sheng, LIAO Fu-Qiang, MA Chun-Mei, ZHU Cheng. J. Infrared Millim. W., 2011, 30(2):109-114. 徐明星, 吴绍华, 周路生, 廖富强, 马春梅, 朱诚. 红外与毫米波学报, 2011, 30(2):109-114.
27. [27]
  ZHU Hong-Qiu, ZHOU Tao, LI Yong-Gang, CHEN Jun-Ming. Chin. J. Anal. Chem., 2019, 47(4):576-582. 朱红求, 周涛, 李勇刚, 陈俊名. 分析化学, 2019, 47(4):576-582.
28. [28]
  GAO Sheng, WANG Qiao-Hua, LI Qing-Xu, SHI Hang. Chin. J. Anal. Chem., 2019, 47(6):941-949. 高升, 王巧华, 李庆旭, 施行. 分析化学, 2019, 47(6):941-949.
29. [29]
  LI H D, XU Q S, LIANG Y Z. Anal. Chim. Acta, 2012, 740:20-26.
30. [30]
  LI H D, XU Q S, LIANG Y Z. Chemometr. Intell. Lab., 2018, 176:34-43.

扫一扫看文章

计量

PDF下载量: 12
文章访问数: 610
HTML全文浏览量: 128

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

基于可见光/近红外反射光谱的沉积型稀土矿La元素含量无损检测

通讯作者: 何政伟,E-mail:hzw@cdut.edu.cn

English

Non-destructive Detection of La Content in Sedimentary Rare Earth Ores Based on Visible-Near Infrared Spectroscopy

Corresponding author: HE Zheng-Wei, hzw@cdut.edu.cn

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

基于可见光/近红外反射光谱的沉积型稀土矿La元素含量无损检测

通讯作者: 何政伟,E-mail:hzw@cdut.edu.cn

English

Non-destructive Detection of La Content in Sedimentary Rare Earth Ores Based on Visible-Near Infrared Spectroscopy

Corresponding author: HE Zheng-Wei, hzw@cdut.edu.cn

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