Machine learning coupled laser-induced breakdown self-reversal isotopic spectrometry for determining lithium isotope concentration
Applied Optics · 20.06.2025 · 64 (18) · E119
DOI: 10.1364/ao.555986 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Optics, online erschienen am 13.05.2025. Verfasst von Madison R Moran und 2 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 44 Literaturangaben. Gefördert von: Defense Threat Reduction Agency.
Abstract (Originalsprache)
Laser-induced breakdown self-reversal isotopic spectrometry (LIBRIS) is implemented to record the Li 670.8 nm peak self-reversal shift with varying 6 Li atom percent compared to 7 Li. The self-reversed peak center wavelength is shown to shift across a range of 13.813±1.21pm in LiOH⋅H 2 O 6 Li samples varying from 3 to 95 6 Li atom percent. Supervised machine-learning regressions are trained on the self-reversal shift in order to quantify the isotopic concentration of the samples. A stacked ensemble model using multiple supervised regression base learners is found to yield the superlative characterization of isotopic content with an RMSE of 5.66 at.% and a detection limit of 18.8 at.%.
Förderung
- Defense Threat Reduction Agency
Zitieren
APA
Moran, M. R., Rao, A. P., & Patnaik, A. K. (2025). Machine learning coupled laser-induced breakdown self-reversal isotopic spectrometry for determining lithium isotope concentration. Applied Optics, 64(18), E119. https://doi.org/10.1364/ao.555986
Vancouver
Moran MR, Rao AP, Patnaik AK. Machine learning coupled laser-induced breakdown self-reversal isotopic spectrometry for determining lithium isotope concentration. Applied Optics. 2025;64(18):E119. doi:10.1364/ao.555986
BibTeX
@article{Moran2025,
author = {Moran, Madison R and Rao, Ashwin P and Patnaik, Anil K},
title = {Machine learning coupled laser-induced breakdown self-reversal isotopic spectrometry for determining lithium isotope concentration},
journal = {Applied Optics},
year = {2025},
volume = {64},
number = {18},
pages = {E119},
doi = {10.1364/ao.555986}
}
EUVIMED