Machine learning methods applied to combined Raman and LIBS spectra: Implications for mineral discrimination in planetary missions
Journal of Raman Spectroscopy · 2023-11 · 54 (11) · 1353-1366
DOI: 10.1002/jrs.6611 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Raman Spectroscopy, online erschienen am 03.11.2023. Verfasst von Sofía Julve‐Gonzalez und 15 weiteren Autor:innen. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Agencia Estatal de Investigación, Ministerio de Economía y Competitividad, European Commission.
Abstract (Originalsprache)
The combined analysis of geological targets by complementary spectroscopic techniques could enhance the characterization of the mineral phases found on Mars. This is indeed the case with the SuperCam instrument onboard the Perseverance rover. In this framework, the present study seeks to evaluate and compare multiple machine learning techniques for the characterization of carbonate minerals based on Raman‐LIBS (Laser‐Induced Breakdown Spectroscopy) spectroscopic data. To do so, a Ca‐Mg prediction curve was created by mixing hydromagnesite and calcite at different concentration ratios. After their characterization by Raman and LIBS spectroscopy, different multivariable machine learning (Gaussian process regression, support vector machines, ensembles of trees, and artificial neural networks) were used to predict the concentration ratio of each sample from their respective datasets. The results obtained by separately analyzing Raman and LIBS data were then compared to those obtained by combining them. By comparing their performance, this work demonstrates that mineral discrimination based on Gaussian and ensemble methods optimized the combine of Raman‐LIBS dataset outperformed those ensured by Raman and LIBS data alone. This demonstrated that the fusion of data combination and machine learning is a promising approach to optimize the analysis of spectroscopic data returned from Mars.
Förderung
- Agencia Estatal de Investigación
- Ministerio de Economía y Competitividad
- European Commission
Zitieren
APA
Julve‐Gonzalez, S., Manrique, J. A., Veneranda, M., Reyes‐Rodríguez, I., Pascual‐Sanchez, E., Sanz‐Arranz, A., Konstantinidis, M., Lalla, E. A., Charro, M. E., Rodriguez‐Gutiez, E., Lopez‐Rodríguez, J. M., Sanz‐Requena, J. F., Delgado‐Iglesias, J., Gonzalez, M. A., Rull, F., & Lopez‐Reyes, G. (2023). Machine learning methods applied to combined Raman and LIBS spectra: Implications for mineral discrimination in planetary missions. Journal of Raman Spectroscopy, 54(11), 1353-1366. https://doi.org/10.1002/jrs.6611
Vancouver
Julve‐Gonzalez S, Manrique JA, Veneranda M, Reyes‐Rodríguez I, Pascual‐Sanchez E, Sanz‐Arranz A, et al. Machine learning methods applied to combined Raman and LIBS spectra: Implications for mineral discrimination in planetary missions. Journal of Raman Spectroscopy. 2023;54(11):1353-1366. doi:10.1002/jrs.6611
BibTeX
@article{JulveGonzalez2023,
author = {Julve‐Gonzalez, Sofía and Manrique, Jose A. and Veneranda, Marco and Reyes‐Rodríguez, Iván and Pascual‐Sanchez, Elena and Sanz‐Arranz, Aurelio and Konstantinidis, Menelaos and Lalla, Emmanuel A. and Charro, María E. and Rodriguez‐Gutiez, Eduardo and Lopez‐Rodríguez, José M. and Sanz‐Requena, José F. and Delgado‐Iglesias, Jaime and Gonzalez, Manuel A. and Rull, Fernando and Lopez‐Reyes, Guillermo},
title = {Machine learning methods applied to combined Raman and LIBS spectra: Implications for mineral discrimination in planetary missions},
journal = {Journal of Raman Spectroscopy},
year = {2023},
volume = {54},
number = {11},
pages = {1353--1366},
doi = {10.1002/jrs.6611}
}
EUVIMED