Development of advanced machine learning models for analysis of plutonium surrogate optical emission spectra

Rao, Ashwin P.; Jenkins, Phillip R.; Auxier, John D.; Shattan, Michael B.; Patnaik, Anil K.

doi:10.1364/AO.444093

Title: Development of advanced machine learning models for analysis of plutonium surrogate optical emission spectra

Journal Article · 20 January 2022 · Applied Optics

DOI: https://doi.org/10.1364/AO.444093 · OSTI ID:1841043

;

This work investigates and applies machine learning paradigms seldom seen in analytical spectroscopy for quantification of gallium in cerium matrices via processing of laser-plasma spectra. Ensemble regressions, support vector machine regressions, Gaussian kernel regressions, and artificial neural network techniques are trained and tested on cerium-gallium pellet spectra. A thorough hyperparameter optimization experiment is conducted initially to determine the best design features for each model. The optimized models are evaluated for sensitivity and precision using the limit of detection (LoD) and root mean-squared error of prediction (RMSEP) metrics, respectively. Gaussian kernel regression yields the superlative predictive model with an RMSEP of 0.33% and an LoD of 0.015% for quantification of Ga in a Ce matrix. This study concludes that these machine learning methods could yield robust prediction models for rapid quality control analysis of plutonium alloys.

View Accepted Manuscript (Publisher)

Cite

Export

Save

Sponsoring Organization:: USDOE

OSTI ID:: 1841043

Journal Information:: Applied Optics, Journal Name: Applied Optics Journal Issue: 7 Vol. 61; ISSN 1559-128X; ISSN APOPAI

Publisher:: Optical Society of AmericaCopyright Statement

Country of Publication:: United States

Language:: English

References (40)

Effects of pre-processing of Raman spectra onin vivo classification of nutrient status of microalgal cells Heraud, Philip; Wood, Bayden R.; Beardall, John Journal of Chemometrics, Vol. 20, Issue 5 https://doi.org/10.1002/cem.990	journal	May 2006
Data Preprocessing in Data Mining García, Salvador; Luengo, Julián; Herrera, Francisco Intelligent Systems Reference Library, Vol. 72 https://doi.org/10.1007/978-3-319-10247-4	book	January 2015
On the limited memory BFGS method for large scale optimization Liu, Dong C.; Nocedal, Jorge Mathematical Programming, Vol. 45, Issue 1-3 https://doi.org/10.1007/BF01589116	journal	August 1989
Rapid analysis of pharmaceutical drugs using LIBS coupled with multivariate analysis Tiwari, P. K.; Awasthi, S.; Kumar, R. Lasers in Medical Science, Vol. 33, Issue 2 https://doi.org/10.1007/s10103-017-2358-8	journal	October 2017
Plutonium: Coping with instability Hecker, Siegfried S. JOM, Vol. 55, Issue 9 https://doi.org/10.1007/s11837-003-0022-1	journal	September 2003
Image recognition neural network: IRNN Cios, Krzysztof J.; Shin, Inho Neurocomputing, Vol. 7, Issue 2 https://doi.org/10.1016/0925-2312(93)E0062-I	journal	March 1995
Evaluation of chemical components and properties of the jujube fruit using near infrared spectroscopy and chemometrics Guo, Ying; Ni, Yongnian; Kokot, Serge Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, Vol. 153 https://doi.org/10.1016/j.saa.2015.08.006	journal	January 2016
Artificial neural network for Cu quantitative determination in soil using a portable Laser Induced Breakdown Spectroscopy system Ferreira, Edilene C.; Milori, Débora M. B. P.; Ferreira, Ednaldo J. Spectrochimica Acta Part B: Atomic Spectroscopy, Vol. 63, Issue 10 https://doi.org/10.1016/j.sab.2008.08.016	journal	October 2008
Multivariate analysis of remote laser-induced breakdown spectroscopy spectra using partial least squares, principal component analysis, and related techniques Clegg, Samuel M.; Sklute, Elizabeth; Dyar, M. Darby Spectrochimica Acta Part B: Atomic Spectroscopy, Vol. 64, Issue 1 https://doi.org/10.1016/j.sab.2008.10.045	journal	January 2009
Clustering and training set selection methods for improving the accuracy of quantitative laser induced breakdown spectroscopy Anderson, Ryan B.; Bell, James F.; Wiens, Roger C. Spectrochimica Acta Part B: Atomic Spectroscopy, Vol. 70 https://doi.org/10.1016/j.sab.2012.04.004	journal	April 2012
Determination of uranium concentration in an ore sample using laser-induced breakdown spectroscopy Kim, Y. -S.; Han, B. -Y.; Shin, H. S. Spectrochimica Acta Part B: Atomic Spectroscopy, Vol. 74-75 https://doi.org/10.1016/j.sab.2012.06.029	journal	August 2012
Artificial neural network for on-site quantitative analysis of soils using laser induced breakdown spectroscopy El Haddad, J.; Villot-Kadri, M.; Ismaël, A. Spectrochimica Acta Part B: Atomic Spectroscopy, Vol. 79-80 https://doi.org/10.1016/j.sab.2012.11.007	journal	January 2013
A partial least squares based spectrum normalization method for uncertainty reduction for laser-induced breakdown spectroscopy measurements Li, Xiongwei; Wang, Zhe; Lui, Siu-Lung Spectrochimica Acta Part B: Atomic Spectroscopy, Vol. 88 https://doi.org/10.1016/j.sab.2013.07.005	journal	October 2013
An artificial neural network approach to laser-induced breakdown spectroscopy quantitative analysis D’Andrea, Eleonora; Pagnotta, Stefano; Grifoni, Emanuela Spectrochimica Acta Part B: Atomic Spectroscopy, Vol. 99 https://doi.org/10.1016/j.sab.2014.06.012	journal	September 2014
A study of machine learning regression methods for major elemental analysis of rocks using laser-induced breakdown spectroscopy Boucher, Thomas F.; Ozanne, Marie V.; Carmosino, Marco L. Spectrochimica Acta Part B: Atomic Spectroscopy, Vol. 107 https://doi.org/10.1016/j.sab.2015.02.003	journal	May 2015
Evaluation of the standard normal variate method for Laser-Induced Breakdown Spectroscopy data treatment applied to the discrimination of painting layers Syvilay, D.; Wilkie-Chancellier, N.; Trichereau, B. Spectrochimica Acta Part B: Atomic Spectroscopy, Vol. 114 https://doi.org/10.1016/j.sab.2015.09.022	journal	December 2015
Multivariate approach to the chemical mapping of uranium in sandstone-hosted uranium ores analyzed using double pulse Laser-Induced Breakdown Spectroscopy Klus, Jakub; Mikysek, Petr; Prochazka, David Spectrochimica Acta Part B: Atomic Spectroscopy, Vol. 123 https://doi.org/10.1016/j.sab.2016.08.014	journal	September 2016
Critical review and advices on spectral-based normalization methods for LIBS quantitative analysis Guezenoc, Julian; Gallet-Budynek, Anne; Bousquet, Bruno Spectrochimica Acta Part B: Atomic Spectroscopy, Vol. 160 https://doi.org/10.1016/j.sab.2019.105688	journal	October 2019
Laser-induced breakdown spectroscopy assisted by machine learning for olive oils classification: The effect of the experimental parameters Bellou, Elli; Gyftokostas, Nikolaos; Stefas, Dimitrios Spectrochimica Acta Part B: Atomic Spectroscopy, Vol. 163 https://doi.org/10.1016/j.sab.2019.105746	journal	January 2020
Limit of detection. A closer look at the IUPAC definition Long, Gary L.; Winefordner, J. D. Analytical Chemistry, Vol. 55, Issue 7 https://doi.org/10.1021/ac00258a001	journal	June 1983
Phonon and magnetic structure in δ-plutonium from density-functional theory Söderlind, Per; Zhou, F.; Landa, A. Scientific Reports, Vol. 5, Issue 1 https://doi.org/10.1038/srep15958	journal	October 2015
A novel approach for the quantitative analysis of multiple elements in steel based on laser-induced breakdown spectroscopy (LIBS) and random forest regression (RFR) Zhang, Tianlong; Liang, Long; Wang, Kang J. Anal. At. Spectrom., Vol. 29, Issue 12 https://doi.org/10.1039/C4JA00217B	journal	January 2014
LIBS development methodology for forensic nuclear materials analysis Bhatt, Bobby; Hudson Angeyo, Kalambuka; Dehayem-Kamadjeu, Alix Analytical Methods, Vol. 10, Issue 7 https://doi.org/10.1039/C7AY02520C	journal	January 2018
Investigation of handheld laser induced breakdown spectroscopy (HH LIBS) for the analysis of beryllium on swipe surfaces Manard, Benjamin T.; Schappert, Michael F.; Wylie, E. Miller Analytical Methods, Vol. 11, Issue 6 https://doi.org/10.1039/C8AY02473A	journal	January 2019
Comparison of machine learning techniques to optimize the analysis of plutonium surrogate material via a portable LIBS device Rao, Ashwin P.; Jenkins, Phillip R.; Auxier II, John D. Journal of Analytical Atomic Spectrometry, Vol. 36, Issue 2 https://doi.org/10.1039/D0JA00435A	journal	January 2021
Rapid quantitative analysis of trace elements in plutonium alloys using a handheld laser-induced breakdown spectroscopy (LIBS) device coupled with chemometrics and machine learning Rao, Ashwin P.; Jenkins, Phillip R.; Vu, Dung M. Analytical Methods, Vol. 13, Issue 30 https://doi.org/10.1039/D1AY00826A	journal	January 2021
Towards the determination of the geographical origin of yellow cake samples by laser-induced breakdown spectroscopy and chemometrics Sirven, Jean-Baptiste; Pailloux, Agnès; M'Baye, Yacine Journal of Analytical Atomic Spectrometry, Vol. 24, Issue 4 https://doi.org/10.1039/b821405k	journal	January 2009
Identification of a physical metallurgy surrogate for the plutonium—1 wt. % gallium alloy Gibbs, Frank E. Plutonium futures-The science (Topical conference on Plutonium and actinides), AIP Conference Proceedings https://doi.org/10.1063/1.1292217	conference	January 2000
Image recognition using convolutional neural network combined with ensemble learning algorithm Mo, Weilong; Luo, Xiaoshu; Zhong, Yexiu Journal of Physics: Conference Series, Vol. 1237, Issue 2 https://doi.org/10.1088/1742-6596/1237/2/022026	journal	June 2019
Basic Enhancement Strategies When Using Bayesian Optimization for Hyperparameter Tuning of Deep Neural Networks Cho, Hyunghun; Kim, Yongjin; Lee, Eunjung IEEE Access, Vol. 8 https://doi.org/10.1109/ACCESS.2020.2981072	journal	January 2020
Kernel Regression for Image Processing and Reconstruction Takeda, Hiroyuki; Farsiu, Sina; Milanfar, Peyman IEEE Transactions on Image Processing, Vol. 16, Issue 2 https://doi.org/10.1109/TIP.2006.888330	journal	February 2007
Analysis of material collected on swipes using laser-induced breakdown spectroscopy Chinni, Rosemarie; Cremers, David A.; Multari, Rosalie Applied Optics, Vol. 49, Issue 13 https://doi.org/10.1364/AO.49.00C143	journal	January 2010
Detection of uranyl fluoride and sand surface contamination on metal substrates by hand-held laser-induced breakdown spectroscopy Shattan, Michael B.; Miller, Dorothy J.; Cook, Matthew T. Applied Optics, Vol. 56, Issue 36 https://doi.org/10.1364/AO.56.009868	journal	January 2017
Investigation of Selected Baseline Removal Techniques as Candidates for Automated Implementation Schulze, Georg; Jirasek, Andrew; Yu, Marcia M. L. Applied Spectroscopy, Vol. 59, Issue 5 https://doi.org/10.1366/0003702053945985	journal	May 2005
Laser-Induced Breakdown Spectroscopy (LIBS), Part I: Review of Basic Diagnostics and Plasma—Particle Interactions: Still-Challenging Issues within the Analytical Plasma Community Hahn, David W.; Omenetto, Nicoló Applied Spectroscopy, Vol. 64, Issue 12 https://doi.org/10.1366/000370210793561691	journal	December 2010
In Situ Semi-Quantitative Analysis of Polluted Soils by Laser-Induced Breakdown Spectroscopy (LIBS) Ismaël, Amina; Bousquet, Bruno; Michel-Le Pierrès, Karine Applied Spectroscopy, Vol. 65, Issue 5 https://doi.org/10.1366/10-06125	journal	May 2011
Laser-Induced Breakdown Spectroscopy (LIBS), Part II: Review of Instrumental and Methodological Approaches to Material Analysis and Applications to Different Fields Hahn, David W.; Omenetto, Nicoló Applied Spectroscopy, Vol. 66, Issue 4 https://doi.org/10.1366/11-06574	journal	April 2012
Automated Quantitative Spectroscopic Analysis Combining Background Subtraction, Cosmic Ray Removal, and Peak Fitting James, Timothy M.; Schlösser, Magnus; Lewis, Richard J. Applied Spectroscopy, Vol. 67, Issue 8 https://doi.org/10.1366/12-06766	journal	August 2013
Characterization of Cast Metals with Probability Distribution Functions Steinzig, M.; Harlow, F. H. MRS Proceedings, Vol. 538 https://doi.org/10.1557/PROC-538-185	journal	January 1998
Kernel Regression in Empirical Microeconomics Blundell, Richard; Duncan, Alan The Journal of Human Resources, Vol. 33, Issue 1 https://doi.org/10.2307/146315	journal	January 1998

Similar Records

Implementation of stacked ensemble machine learning for the detection of surrogate plutonium contamination in soil via LIBS

Journal Article · 2025 · Applied Optics · OSTI ID:2574118

Anderson, Paige E.; Braun, Janos I.; Borrero Negrón, Justin I.; +2 more

Analytical comparisons of handheld LIBS and XRF devices for rapid quantification of gallium in a plutonium surrogate matrix

Journal Article · 2022 · Journal of Analytical Atomic Spectrometry · OSTI ID:2202628

Rao, Ashwin P.; Jenkins, Phillip R.; Auxier II, John D.; +2 more

Comparison of machine learning techniques to optimize the analysis of plutonium surrogate material via a portable LIBS device

Journal Article · 2020 · Journal of Analytical Atomic Spectrometry · OSTI ID:1870632

Rao, Ashwin P.; Jenkins, Phillip R.; Auxier II, John D.; +1 more

Title: Development of advanced machine learning models for analysis of plutonium surrogate optical emission spectra

Citation Formats

References (40)

Similar Records

Related Subjects