zhpsЖурнал прикладной спектроскопииZhurnal Prikladnoii Spektroskopii0514-7506B. I. Stepanov Institute of Physics of the National Academy of Scienceszhps-1152Research ArticleАННОТАЦИИ АНГЛОЯЗЫЧНЫХ СТАТЕЙABSTRACTS ENGLISH-LANGUAGE ARTICLESКАЛИБРОВКА СПЕКТРАЛЬНЫХ ДАННЫХ ChemCam РАЗЛИЧНЫХ ЛАЗЕРНО-ЭМИССИОННЫХ СПЕКТРОМЕТРОВ С ИСПОЛЬЗОВАНИЕМ МАШИНЫ ГЛУБОКОГО ЭКСТРЕМАЛЬНОГО ОБУЧЕНИЯCALIBRATION TRANSFER FOR ChemCam SPECTRAL DATA FROM DIFFERENT LASER-INDUCED BREAKDOWN SPECTROMETERS VIA A DEEP EXTREME LEARNING MACHINEZhouT.ZhouT.

Вэйхай

Ting Zhou

Weihai

ZhangL.ZhangLi

Вэйхай

Li Zhang

Weihai

zhangliwh@sdu.edu.cnLingZ.LingZ.

Вэйхай

Zongcheng Ling

Weihai

zcling@sdu.edu.cnWuZ.WuZ.

Вэйхай

Zongchen Wu

Weihai

ShenZ.ShenZ.

Вэйхай

Zhongben Shen

Weihai

Школа механики, электротехники и информационной инженерии Шаньдунского университетаSchool of Mechanical, Electrical and Information Engineering at Shandong UniversityИнститут космических наук Шаньдунского университетаInstitute of Space Science at Shandong University202228092022895747747Copyright © Zhou T., Zhang L., Ling Z., Wu Z., Shen Z., 20222022Zhou T., Zhang L., Ling Z., Wu Z., Shen Z.Zhou T., Zhang L., Ling Z., Wu Z., Shen Z.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://zhps.ejournal.by/jour/article/view/1152

Для устранения различий в интенсивности, смещении длины волны и ширины максимумов, возникающих при измерении лазерно-искровых эмиссионных спектров (LIBS), использованы метод экстремального обучения и машины глубокого экстремального обучения к двум различным наборам спектральных данных. Первый представляет собой набор образцов калибровочной мишени ChemCam, который содержит спектральные данные, полученные с помощью ChemCam на марсоходе Curiosity и в Марсианской научной лаборатории (MSL). Другой набор содержит спектры образцов калибровочной мишени, созданных командой ChemCam в MSL. Проверка производительности двух алгоритмов показала, что методы переноса калибровки являются стабильными методами прогнозирования и обеспечивают значительно меньшую ошибку прогнозирования по сравнению с линейным переносом и методом кусочно-прямой стандартизации. Модель на основе метода частичных наименьших квадратов для количественного анализа переданных спектров показала улучшенную количественную точность.

Laser-induced breakdown spectroscopy (LIBS) technology has been applied to many fields, so it is crucial for quantitative analyses of LIBS spectra. However, there is a problem in the field of LIBS spectra. Even in the same experimental setting, the same sample exhibits different spectra with different instruments, which is mainly reflected in the intensity, wavelength shift, and peak width differences. These differences cause standardization problems in LIBS spectroscopy and serious interference in quantitative analyses. The aim of this study is to correct the difference by applying the extreme learning machine method and the deep extreme learning machine method to two different spectral datasets. The first dataset is the ChemCam calibration target sample set, which contains two spectral datasets produced by using ChemCam on instruments on the Curiosity rover and at the Mars Science Laboratory (MSL). The other dataset comprises spectra obtained from calibration target samples produced by the ChemCam team at MSL. The performance of the two algorithms is tested, and the results show that our calibration transfer methods are stable predictive methods that provide significantly lower prediction error compared with linear transfer and the piecewise direct standardization method. The model established by the partial least square method is used for quantitative analyses of the transferred spectra, and the transmitted spectra showed improved quantitative accuracy.

лазерно-искровая эмиссионная спектроскопиякалибровочная мишень ChemCamкусочно-прямая стандартизацияэкстремальное обучениемашина глубокого экстремального обученияlaser-induced breakdown spectroscopyChemCam calibration targetpiecewise direct standardizationextreme learning machinedeep extreme learning machineReferencesR. B. Anderson, S. M. Clegg, J. Frydenvang, et al., Spectrochim. Acta B: At. Spectrosc., 129, 49–57 (2017).R. B. Anderson, S. M. Clegg, J. Frydenvang, et al., Spectrochim. Acta B: At. Spectrosc., 129, 49–57 (2017).Z. Shang, K. Xu, Y. Liu, et al., The Astrophys. J. Suppl. Ser., 258, No. 2, 25 (2022).Z. Shang, K. Xu, Y. Liu, et al., The Astrophys. J. Suppl. Ser., 258, No. 2, 25 (2022).S. Le Mouélic, O. Gasnault, K. E. Herkenhoff, et al., Icarus, 249, 93–107 (2015).S. Le Mouélic, O. Gasnault, K. E. Herkenhoff, et al., Icarus, 249, 93–107 (2015).C. Fabre, S. Maurice, A. Cousin, et al., Spectrochim. Acta B: At. Spectrosc., 66, No. 3-4, 280–289 (2011).C. Fabre, S. Maurice, A. Cousin, et al., Spectrochim. Acta B: At. Spectrosc., 66, No. 3-4, 280–289 (2011).The SuperCam Remote Sensing Instrument Suite for the Mars Rover: A Preview (2020).The SuperCam Remote Sensing Instrument Suite for the Mars Rover: A Preview (2020).W. Xu, X. Liu, Z. Yan, et al., Space Sci. Rev., 217, No. 5 (2021).W. Xu, X. Liu, Z. Yan, et al., Space Sci. Rev., 217, No. 5 (2021).S. M. Clegg, R. C. Wiens, R. Anderson, et al., Spectrochim. Acta B: At. Spectrosc., 129, 64–85 (2017).S. M. Clegg, R. C. Wiens, R. Anderson, et al., Spectrochim. Acta B: At. Spectrosc., 129, 64–85 (2017).R. C. Wiens, S. Maurice, B. Barraclough, et al., Space Sci. Rev., 170, No. 1-4, 167–227 (2012).R. C. Wiens, S. Maurice, B. Barraclough, et al., Space Sci. Rev., 170, No. 1-4, 167–227 (2012).E. Ewusi-Annan, D. M. Delapp, R. C. Wiens, et al., Spectrochim. Acta B: At. Spectrosc., 171, 105930 (2020).E. Ewusi-Annan, D. M. Delapp, R. C. Wiens, et al., Spectrochim. Acta B: At. Spectrosc., 171, 105930 (2020).Y. Cao, H. Yuan, Z. Zhao, Spectrosc. Spectr. Analysis, 38, No. 3, 973–981 (2018).Y. Cao, H. Yuan, Z. Zhao, Spectrosc. Spectr. Analysis, 38, No. 3, 973–981 (2018).J. J. Workman, Appl. Spectrosc., 72, No. 3, 340–365 (2018).J. J. Workman, Appl. Spectrosc., 72, No. 3, 340–365 (2018).Y. Chen, Z. Wang, Chemometrics and Intelligent Lab. Systems, 192, 103824 (2019).Y. Chen, Z. Wang, Chemometrics and Intelligent Lab. Systems, 192, 103824 (2019).J. Wahl, M. Sjödahl, K. Ramser, Appl. Spectrosc., 74, No. 4, 427–438 (2020).J. Wahl, M. Sjödahl, K. Ramser, Appl. Spectrosc., 74, No. 4, 427–438 (2020).G. Huang, D. H. Wang, Y. Lan, Int. J. Machine Learning and Cybernetics, 2, No. 2, 107–122 (2011).G. Huang, D. H. Wang, Y. Lan, Int. J. Machine Learning and Cybernetics, 2, No. 2, 107–122 (2011).J. Tang, C. Deng, G. Huang, IEEE Transact. Neural Networks and Learning Systems, 27, No. 4, 809–821 (2016).J. Tang, C. Deng, G. Huang, IEEE Transact. Neural Networks and Learning Systems, 27, No. 4, 809–821 (2016).E. Bouveresse, D. L. Massart, Vibr. Spectr., 11, No. 1, 3–15 (1996).E. Bouveresse, D. L. Massart, Vibr. Spectr., 11, No. 1, 3–15 (1996).Y. Wang, D. J. Veltkamp, B. R. Kowalski, Anal. Chem., 63, No. 23, 2750–2756 (1991).Y. Wang, D. J. Veltkamp, B. R. Kowalski, Anal. Chem., 63, No. 23, 2750–2756 (1991).M. L. Griffiths, D. Svozil, P. Worsfold, et al., J. Analyt. At. Spectrom., 21, No. 10, 1045 (2006).M. L. Griffiths, D. Svozil, P. Worsfold, et al., J. Analyt. At. Spectrom., 21, No. 10, 1045 (2006).C. Liang, H. Yuan, Z. Zhao, et al., Chemometrics and Intelligent Lab. Systems, 153, 51–57 (2016).C. Liang, H. Yuan, Z. Zhao, et al., Chemometrics and Intelligent Lab. Systems, 153, 51–57 (2016).PDS Geosciences Node, Washington University, St. Louis, Missouri [EB/OL]. 2021/6/17, https://pdsgeosciences.wustl.edu/.PDS Geosciences Node, Washington University, St. Louis, Missouri [EB/OL]. 2021/6/17, https://pdsgeosciences.wustl.edu/.C. Fabre, A. Cousin, R. C. Wiens, et al., Spectrochim. Acta B: At. Spectrosc., 99, 34–51 (2014).C. Fabre, A. Cousin, R. C. Wiens, et al., Spectrochim. Acta B: At. Spectrosc., 99, 34–51 (2014).R. C. Wiens, S. Maurice, J. Lasue, et al., Spectrochim. Acta B: At. Spectrosc., 82, No. 1, 27 (2013).R. C. Wiens, S. Maurice, J. Lasue, et al., Spectrochim. Acta B: At. Spectrosc., 82, No. 1, 27 (2013).J. Cao, K. Zhang, M. Luo, et al., Neural Networks, 81, 91–102 (2016).J. Cao, K. Zhang, M. Luo, et al., Neural Networks, 81, 91–102 (2016).G. Huang, X. Ding, H. Zhou, Neurocomputing, 74, No. 1-3, 155–163 (2010).G. Huang, X. Ding, H. Zhou, Neurocomputing, 74, No. 1-3, 155–163 (2010).W. Chen, J. Bin, H. Lu, et al., Analyst (London), 141, No. 6, 1973–1980 (2016).W. Chen, J. Bin, H. Lu, et al., Analyst (London), 141, No. 6, 1973–1980 (2016).R. Eisinga, M. T. Grotenhuis, B. Pelzer, Int. J. Publ. Health, 58, No. 4, 637–642 (2013).R. Eisinga, M. T. Grotenhuis, B. Pelzer, Int. J. Publ. Health, 58, No. 4, 637–642 (2013).L. Xia, Agro Food Industry Hi-Tech, 28, No. 1, 885–889 (2017).L. Xia, Agro Food Industry Hi-Tech, 28, No. 1, 885–889 (2017).S. Wold, M. Sjöström, L. Eriksson, Chemometrics and Intelligent Lab. Systems, 58, No. 2, 109–130 (2001).S. Wold, M. Sjöström, L. Eriksson, Chemometrics and Intelligent Lab. Systems, 58, No. 2, 109–130 (2001).

The authors declare that there are no conflicts of interest present.