Uranium Oxide Synthetic Pathway Discernment through Unsupervised Morphological Analysis

Girard, Michael K.; Hagen, Alexander R.; Schwerdt, Ian J.; Gaumer, Madelyn E.; McDonald, Luther W.; Hodas, Nathan O.; Jurrus, Elizabeth R.

doi:10.1016/j.jnucmat.2021.152983

Uranium Oxide Synthetic Pathway Discernment through Unsupervised Morphological Analysis

Journal Article · 15 August 2021 · Journal of Nuclear Materials

DOI:https://doi.org/10.1016/j.jnucmat.2021.152983· OSTI ID:1810544

Girard, Michael K. ^[1]; Hagen, Alexander R. ^[1]; Schwerdt, Ian J. ^[1]; Gaumer, Madelyn E. ^[1]; McDonald, Luther W. ^[1]; ^[1]; ^[1]

BATTELLE (PACIFIC NW LAB)

We present a novel unsupervised machine learning method for quantitative representation of scanning electron micrographs and its applications and performance for nuclear forensic analysis of uranium ore concentrates. The method uses a vector quantizing variational autoencoder followed by a histogram operation to encode a micrograph into a single dimensional representation, called the latent vector. The method requires no extant labeling of the data and can be applied over large datasets of micrographs with minimal human interaction. The representations generated are broadly descriptive of each micrograph and the microstructure of the material imaged. In the case of uranium ore concentrate analysis, the representations were amenable to processing reagent and ore concentrate species classification with accuracy of 81:8%, which is competitive with state-of-the-art supervised networks. The representations were also used to classify previously unseen processing routes, were able to classify imaging parameters such as magnification (to 76:0% accuracy), were able to classify fine grained process parameters such as calcining temperature (to 74:4% accuracy), and their informatic properties indicate that they are generally descriptive of the image represented. This method can be applied across microstructure analysis fields to perform quantitative analysis without the need for labor intensive and possibly biased human analysis.

Research Organization:: Pacific Northwest National Lab. (PNNL), Richland, WA (United States)

Sponsoring Organization:: USDOE

DOE Contract Number:: AC05-76RL01830

OSTI ID:: 1810544

Report Number(s):: PNNL-SA-156254

Journal Information:: Journal of Nuclear Materials, Vol. 552

Country of Publication:: United States

Language:: English

References (30)

Determining uranium ore concentrates and their calcination products via image classification of multiple magnifications Ly, Cuong; Vachet, Clement; Schwerdt, Ian Journal of Nuclear Materials, Vol. 533 https://doi.org/10.1016/j.jnucmat.2020.152082	journal	May 2020
Nuclear Forensic Science: Correlating Measurable Material Parameters to the History of Nuclear Material Mayer, Klaus; Wallenius, Maria; Varga, Zsolt Chemical Reviews, Vol. 113, Issue 2 https://doi.org/10.1021/cr300273f	journal	October 2012
Nuclear Forensic Science: Analysis of Nuclear Material Out of Regulatory Control Kristo, Michael J.; Gaffney, Amy M.; Marks, Naomi Annual Review of Earth and Planetary Sciences, Vol. 44, Issue 1 https://doi.org/10.1146/annurev-earth-060115-012309	journal	June 2016
Uranium processing: A review of current methods and technology Edwards, C. R.; Oliver, A. J. JOM, Vol. 52, Issue 9 https://doi.org/10.1007/s11837-000-0181-2	journal	September 2000
Uranium oxide synthetic pathway discernment through thermal decomposition and morphological analysis Schwerdt, Ian J.; Hawkins, Casey G.; Taylor, Bryan Radiochimica Acta, Vol. 107, Issue 3 https://doi.org/10.1515/ract-2018-3033	journal	March 2019
Comparison of morphologies of a uranyl peroxide precursor and calcination products Tamasi, Alison L.; Cash, Leigh J.; Tyler Mullen, W. Journal of Radioanalytical and Nuclear Chemistry https://doi.org/10.1007/s10967-016-4692-x	journal	January 2016
The conversion of UO₂ via ammonium uranyl carbonate: Study of precipitation, chemical variation and powder properties Yi-Ming, Pan; Che-Bao, Ma; Nien-Nan, Hsu Journal of Nuclear Materials, Vol. 99, Issue 2-3, p. 135-147 https://doi.org/10.1016/0022-3115(81)90182-3	journal	September 1981
Significance of physical state of starting precipitate in growth of uranium dioxide particles Doi, H.; Ito, T. Journal of Nuclear Materials, Vol. 11, Issue 1 https://doi.org/10.1016/0022-3115(64)90124-2	journal	January 1964
Pseudomorphic decomposition of uranium peroxide into UO3 Cordfunke, E. H. P.; Van Der Giessen, A. A. Journal of Inorganic and Nuclear Chemistry, Vol. 25, Issue 5 https://doi.org/10.1016/0022-1902(63)80240-7	journal	May 1963
Attribution of uranium ore concentrates using elemental and anionic data Keegan, Elizabeth; Wallenius, Maria; Mayer, Klaus Applied Geochemistry, Vol. 27, Issue 8 https://doi.org/10.1016/j.apgeochem.2012.05.009	journal	August 2012
Identification of uranium signatures relevant for nuclear safeguards and forensics Varga, Zsolt; Krajkó, Judit; Peńkin, Maxim Journal of Radioanalytical and Nuclear Chemistry, Vol. 312, Issue 3 https://doi.org/10.1007/s10967-017-5247-5	journal	April 2017
Discrimination of uranium ore concentrates by chemometric data analysis to support provenance assessment for nuclear forensics applications El Haddad, Josette; Harhira, Aissa; Blouin, Alain Journal of Radioanalytical and Nuclear Chemistry, Vol. 317, Issue 1 https://doi.org/10.1007/s10967-018-5912-3	journal	May 2018
A novel nuclear forensic tool involving deposit type normalized rare earth element signatures Spano, Tyler L.; Simonetti, Antonio; Wheeler, Thomas Terra Nova, Vol. 29, Issue 5 https://doi.org/10.1111/ter.12275	journal	July 2017
Uraninite chemistry as forensic tool for provenance analysis Frimmel, Hartwig E.; Schedel, Sibylle; Brätz, Helene Applied Geochemistry, Vol. 48 https://doi.org/10.1016/j.apgeochem.2014.07.013	journal	September 2014
Interviewing a Silent (Radioactive) Witness through Nuclear Forensic Analysis Mayer, Klaus; Wallenius, Maria; Varga, Zsolt Analytical Chemistry, Vol. 87, Issue 23 https://doi.org/10.1021/acs.analchem.5b01623	journal	September 2015
Molybdenum isotope compositions of uranium ore concentrates by double spike MC-ICP-MS Rolison, John M.; Druce, Matthew; Shollenberger, Quinn R. Applied Geochemistry, Vol. 103 https://doi.org/10.1016/j.apgeochem.2019.03.001	journal	April 2019
Trace element and U isotope analysis of uraninite and ore concentrate: Applications for nuclear forensic investigations Spano, Tyler L.; Simonetti, Antonio; Balboni, Enrica Applied Geochemistry, Vol. 84 https://doi.org/10.1016/j.apgeochem.2017.07.003	journal	September 2017
Chemical and Sr isotopic characterization of North America uranium ores: Nuclear forensic applications Balboni, Enrica; Jones, Nina; Spano, Tyler Applied Geochemistry, Vol. 74 https://doi.org/10.1016/j.apgeochem.2016.08.016	journal	November 2016
Measurement of the sulphur isotope ratio (34S/32S) in uranium ore concentrates (yellow cakes) for origin assessment Han, Sun-Ho; Varga, Zsolt; Krajkó, Judit Journal of Analytical Atomic Spectrometry, Vol. 28, Issue 12 https://doi.org/10.1039/c3ja50231g	journal	January 2013
Nuclear forensic analysis of an unknown uranium ore concentrate sample seized in a criminal investigation in Australia Keegan, Elizabeth; Kristo, Michael J.; Colella, Michael Forensic Science International, Vol. 240 https://doi.org/10.1016/j.forsciint.2014.04.004	journal	July 2014
Expanding the nuclear forensic toolkit: chemical profiling of uranium ore concentrate particles by synchrotron X-ray microanalysis Crean, Daniel E.; Corkhill, Claire L.; Nicholls, Timothy RSC Advances, Vol. 5, Issue 107 https://doi.org/10.1039/C5RA14963K	journal	January 2015
Raman spectroscopy of uranium compounds and the use of multivariate analysis for visualization and classification Ho, Doris Mer Lin; Jones, Andrew E.; Goulermas, John Y. Forensic Science International, Vol. 251 https://doi.org/10.1016/j.forsciint.2015.03.002	journal	June 2015
Thermal decomposition of Australian uranium ore concentrates: characterisation of speciation and morphological changes following thermogravimetric analysis Ditcham, Tim G.; Wotherspoon, Andrew; Kirkbride, K. Paul Journal of Radioanalytical and Nuclear Chemistry, Vol. 310, Issue 2 https://doi.org/10.1007/s10967-016-4871-9	journal	June 2016
Quantifying Impurity Effects on the Surface Morphology of α-U ₃ O ₈ Hanson, Alexa B.; Lee, Rachel Nicholls; Vachet, Clement Analytical Chemistry, Vol. 91, Issue 15 https://doi.org/10.1021/acs.analchem.9b02013	journal	June 2019
Nuclear forensics investigation of morphological signatures in the thermal decomposition of uranyl peroxide Schwerdt, Ian J.; Olsen, Adam; Lusk, Robert Talanta, Vol. 176 https://doi.org/10.1016/j.talanta.2017.08.020	journal	January 2018
Quantifying Morphological Features of α-U ₃ O ₈ with Image Analysis for Nuclear Forensics Olsen, Adam M.; Richards, Bryony; Schwerdt, Ian Analytical Chemistry, Vol. 89, Issue 5 https://doi.org/10.1021/acs.analchem.6b05020	journal	February 2017
Microstructural classification of unirradiated LiAlO2 pellets by deep learning methods Pazdernik, Karl; LaHaye, Nicole L.; Artman, Conor M. Computational Materials Science, Vol. 181 https://doi.org/10.1016/j.commatsci.2020.109728	journal	August 2020
Deep Convolutional Neural Networks for Image Classification: A Comprehensive Review Rawat, Waseem; Wang, Zenghui Neural Computation, Vol. 29, Issue 9 https://doi.org/10.1162/neco_a_00990	journal	September 2017
Nuclear proliferomics: A new field of study to identify signatures of nuclear materials as demonstrated on alpha-UO3 Schwerdt, Ian J.; Brenkmann, Alexandria; Martinson, Sean Talanta, Vol. 186 https://doi.org/10.1016/j.talanta.2018.04.092	journal	August 2018
A Mathematical Theory of Communication Shannon, C. E. Bell System Technical Journal, Vol. 27, Issue 3 https://doi.org/10.1002/j.1538-7305.1948.tb01338.x	journal	July 1948

Similar Records

Investigation of process history and underlying phenomena associated with the synthesis of plutonium oxides using Vector Quantizing Variational Autoencoder

Journal Article · 2023 · Chemometrics and Intelligent Laboratory Systems · OSTI ID:1994774

Hainje, Connor M.; Nizinski, Cody A.; Jackson, Shane W.; +6 more

Beyond the hubble sequence – exploring galaxy morphology with unsupervised machine learning

Journal Article · 2021 · Monthly Notices of the Royal Astronomical Society · OSTI ID:1863222

Cheng, Ting-Yun; Huertas-Company, Marc; Conselice, Christopher J.; +3 more

Pulsed Thermal Tomography Nondestructive Examination of Additively Manufactured Reactor Materials and Components (Final Technical Report)

Technical Report · 2022 · OSTI ID:1923751

Heifetz, Alexander; Zhang, Xin; Saniie, Jafar; +3 more

Related Subjects

Scanning Electron Microscopy
Vector Quantizing Variational Autoencoder
Unsupervised Learning
Nuclear Forensic Analysis
machine learning

Uranium Oxide Synthetic Pathway Discernment through Unsupervised Morphological Analysis

Citation Formats

References (30)

Similar Records

Related Subjects