Identifying chemically similar multiphase nanoprecipitates in compositionally complex non-equilibrium oxides via machine learning

Keyou S. Mao; Tyler J. Gerczak; Jason M. Harp; Casey S. McKinney; Timothy G. Lach; Omer Karakoc; Andrew T. Nelson; Kurt A. Terrani; Chad M. Parish; Philip D. Edmondson

doi:10.1038/s43246-022-00244-4

Identifying chemically similar multiphase nanoprecipitates in compositionally complex non-equilibrium oxides via machine learning

Keyou S. Mao, Tyler J. Gerczak, Jason M. Harp, Casey S. McKinney, Timothy G. Lach, Omer Karakoc, Andrew T. Nelson, Kurt A. Terrani, Chad M. Parish, Philip D. Edmondson

Research output: Contribution to journal › Article › peer-review

4 Scopus citations

Abstract

Characterizing oxide nuclear fuels is difficult due to complex fission products, which result from time-evolving system chemistry and extreme operating environments. Here, we report a machine learning-enhanced approach that accelerates the characterization of spent nuclear fuels and improves the accuracy of identifying nanophase fission products and bubbles. We apply this approach to commercial, high-burnup, irradiated light-water reactor fuels, demonstrating relationships between fission product precipitates and gases. We also gain understanding of the fission versus decay pathways of precipitates across the radius of a fuel pellet. An algorithm is provided for quantifying the chemical segregation of the fission products with respect to the high-burnup structure, which enhances our ability to process large amounts of microscopy data, including approaching the atomistic-scale. This may provide a faster route for achieving physics-based fuel performance modeling.

Original language	English
Article number	21
Journal	Communications Materials
Volume	3
Issue number	1
DOIs	https://doi.org/10.1038/s43246-022-00244-4
State	Published - Dec 2022

Funding

This research was sponsored by the Transformational Challenge Reactor program and supported by the US Department of Energy (DOE), Office of Nuclear Energy and Office of Science, Fusion Energy Sciences. This research was conducted, in part, using instrumentation (FEI Talos F200X S/TEM) supported by the US DOE, Office of Nuclear Energy, Fuel Cycle Research and Development and the Nuclear Science User Facilities. A portion of this research was conducted at ORNL’s Center for Nanophase Materials Sciences, a DOE Office of Science User Facility. This research was supported in part by the Oak Ridge National Laboratory (ORNL) postdoc development funds and an appointment to the ORNL Higher Education Research Experience Program, sponsored by the US DOE and administered by the Oak Ridge Institute for Science and Education. The authors are indebted to a multitude of facilities and support personnel at ORNL that enabled fuel specimen handling, preparation, and extraction from the hot cell. Specifically, the assistance of staff of the Low Activation Materials Design and Analysis Laboratory and Irradiated Fuels Examination Laboratory is gratefully acknowledged. K.D. Linton and J.W. Werden offered their critical support and advice. The authors also would like to thank L.R. Scime and R.L. Seibert for discussing the results, providing fruitful comments, and reviewing the paper.

Funders	Funder number
Fuel Cycle Research and Development
U.S. Department of Energy
Office of Science
Office of Nuclear Energy
Fusion Energy Sciences
Oak Ridge National Laboratory
Oak Ridge Institute for Science and Education

Access to Document

10.1038/s43246-022-00244-4

Cite this

Mao, K. S., Gerczak, T. J., Harp, J. M., McKinney, C. S., Lach, T. G., Karakoc, O., Nelson, A. T., Terrani, K. A., Parish, C. M., & Edmondson, P. D. (2022). Identifying chemically similar multiphase nanoprecipitates in compositionally complex non-equilibrium oxides via machine learning. Communications Materials, 3(1), Article 21. https://doi.org/10.1038/s43246-022-00244-4

@article{d30db4b568414661923ce5fa9954ee92,

title = "Identifying chemically similar multiphase nanoprecipitates in compositionally complex non-equilibrium oxides via machine learning",

abstract = "Characterizing oxide nuclear fuels is difficult due to complex fission products, which result from time-evolving system chemistry and extreme operating environments. Here, we report a machine learning-enhanced approach that accelerates the characterization of spent nuclear fuels and improves the accuracy of identifying nanophase fission products and bubbles. We apply this approach to commercial, high-burnup, irradiated light-water reactor fuels, demonstrating relationships between fission product precipitates and gases. We also gain understanding of the fission versus decay pathways of precipitates across the radius of a fuel pellet. An algorithm is provided for quantifying the chemical segregation of the fission products with respect to the high-burnup structure, which enhances our ability to process large amounts of microscopy data, including approaching the atomistic-scale. This may provide a faster route for achieving physics-based fuel performance modeling.",

author = "Mao, {Keyou S.} and Gerczak, {Tyler J.} and Harp, {Jason M.} and McKinney, {Casey S.} and Lach, {Timothy G.} and Omer Karakoc and Nelson, {Andrew T.} and Terrani, {Kurt A.} and Parish, {Chad M.} and Edmondson, {Philip D.}",

note = "Publisher Copyright: {\textcopyright} 2022, The Author(s).",

year = "2022",

month = dec,

doi = "10.1038/s43246-022-00244-4",

language = "English",

volume = "3",

journal = "Communications Materials",

issn = "2662-4443",

publisher = "Nature Research",

number = "1",

}

TY - JOUR

T1 - Identifying chemically similar multiphase nanoprecipitates in compositionally complex non-equilibrium oxides via machine learning

AU - Mao, Keyou S.

AU - Gerczak, Tyler J.

AU - Harp, Jason M.

AU - McKinney, Casey S.

AU - Lach, Timothy G.

AU - Karakoc, Omer

AU - Nelson, Andrew T.

AU - Terrani, Kurt A.

AU - Parish, Chad M.

AU - Edmondson, Philip D.

PY - 2022/12

Y1 - 2022/12

N2 - Characterizing oxide nuclear fuels is difficult due to complex fission products, which result from time-evolving system chemistry and extreme operating environments. Here, we report a machine learning-enhanced approach that accelerates the characterization of spent nuclear fuels and improves the accuracy of identifying nanophase fission products and bubbles. We apply this approach to commercial, high-burnup, irradiated light-water reactor fuels, demonstrating relationships between fission product precipitates and gases. We also gain understanding of the fission versus decay pathways of precipitates across the radius of a fuel pellet. An algorithm is provided for quantifying the chemical segregation of the fission products with respect to the high-burnup structure, which enhances our ability to process large amounts of microscopy data, including approaching the atomistic-scale. This may provide a faster route for achieving physics-based fuel performance modeling.

AB - Characterizing oxide nuclear fuels is difficult due to complex fission products, which result from time-evolving system chemistry and extreme operating environments. Here, we report a machine learning-enhanced approach that accelerates the characterization of spent nuclear fuels and improves the accuracy of identifying nanophase fission products and bubbles. We apply this approach to commercial, high-burnup, irradiated light-water reactor fuels, demonstrating relationships between fission product precipitates and gases. We also gain understanding of the fission versus decay pathways of precipitates across the radius of a fuel pellet. An algorithm is provided for quantifying the chemical segregation of the fission products with respect to the high-burnup structure, which enhances our ability to process large amounts of microscopy data, including approaching the atomistic-scale. This may provide a faster route for achieving physics-based fuel performance modeling.

UR - http://www.scopus.com/inward/record.url?scp=85128356993&partnerID=8YFLogxK

U2 - 10.1038/s43246-022-00244-4

DO - 10.1038/s43246-022-00244-4

M3 - Article

AN - SCOPUS:85128356993

SN - 2662-4443

VL - 3

JO - Communications Materials

JF - Communications Materials

IS - 1

M1 - 21

ER -

Identifying chemically similar multiphase nanoprecipitates in compositionally complex non-equilibrium oxides via machine learning

Abstract

Funding

Access to Document

Other files and links

Fingerprint

Cite this