Other formats:
BibTeX
LaTeX
RIS
@article{2264357,
author = {Prochazka, David and Pořízka, Pavel and Hruška, Jakub and Novotný, Karel and Hrdlička, Aleš and Kaiser, Jozef},
article_location = {Cambridge},
article_number = {3},
doi = {http://dx.doi.org/10.1039/d1ja00389e},
keywords = {Laser; spectroscopy; laser-induced breakdown spectroscopy; machine learning; optimization; artificial neural network; glass; steel},
language = {eng},
issn = {0267-9477},
journal = {Journal of Analytical Atomic Spectrometry},
title = {Machine learning in laser-induced breakdown spectroscopy as a novel approach towards experimental parameter optimization},
url = {https://doi.org/10.1039/D1JA00389E},
volume = {37},
year = {2022}
}
TY - JOUR
ID - 2264357
AU - Prochazka, David - Pořízka, Pavel - Hruška, Jakub - Novotný, Karel - Hrdlička, Aleš - Kaiser, Jozef
PY - 2022
TI - Machine learning in laser-induced breakdown spectroscopy as a novel approach towards experimental parameter optimization
JF - Journal of Analytical Atomic Spectrometry
VL - 37
IS - 3
SP - 603-612
EP - 603-612
PB - Royal Society of Chemistry
SN - 02679477
KW - Laser
KW - spectroscopy
KW - laser-induced breakdown spectroscopy
KW - machine learning
KW - optimization
KW - artificial neural network
KW - glass
KW - steel
UR - https://doi.org/10.1039/D1JA00389E
N2 - Similar to other analytical techniques, the performance of laser-induced breakdown spectroscopy (LIBS) is significantly influenced by the selection of optimal experimental parameters. The optimization of LIBS is challenging because the laser–matter interaction and subsequent plasma formation are influenced not only by selected experimental parameters but also by the physical and mechanical properties of the sample. The goal of this work is to develop an artificial neural network (ANN) that is able to predict the signal-to-noise ratio (SNR) of selected spectral lines based on specific experimental parameters (laser pulse energy and gate delay) and on the sample's physical and mechanical properties. The ANN training was based on input data obtained from a high number of measurements of three certified materials with highly different mechanical and physical properties (low alloyed steel, glass, and aluminium alloy) with 2079 combinations of experimental parameters – gate delay (GD) and laser pulse energy (E). The ANN was optimized in terms of the number of neurons and hidden layers. The minimal number of input data points was studied with emphasis on the ANN prediction accuracy expressed as the determination coefficient R2 (predicted vs. measured values). The number of input data points was studied from three points of view – a minimal number of experimental parameters for one matrix, a minimal amount of data from different matrices, and a minimal number of different spectral lines. It has been shown that at least 20 different combinations of experimental parameters are necessary for one matrix to obtain reasonable performance of the ANN. However, only ten combinations are needed when a new matrix is added to the working model. It has also been shown that the prediction accuracy is poor for spectral lines which were not part of the training data. Finally, the ANN was utilized to predict the SNR of selected spectral lines in a specific range of experimental parameters. The parameters with the maximal SNR were studied, and the values were discussed with an emphasis on sample properties. It has been concluded that the optimization process can be substituted or significantly shortened by means of the ANN.
ER -
PROCHAZKA, David, Pavel POŘÍZKA, Jakub HRUŠKA, Karel NOVOTNÝ, Aleš HRDLIČKA and Jozef KAISER. Machine learning in laser-induced breakdown spectroscopy as a novel approach towards experimental parameter optimization. \textit{Journal of Analytical Atomic Spectrometry}. Cambridge: Royal Society of Chemistry, 2022, vol.~37, No~3, p.~603-612. ISSN~0267-9477. Available from: https://dx.doi.org/10.1039/d1ja00389e.
|
