Adapting a machine learning method for the source discrimination of plutonium samples mixed from multiple reactor types

Patrick J. O'Neal; Sunil S. Chirayath

doi:10.1016/j.anucene.2025.111271

Adapting a machine learning method for the source discrimination of plutonium samples mixed from multiple reactor types

Patrick J. O'Neal, Sunil S. Chirayath

Nondestructive Measurement Science and T

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

Abstract

Plutonium (Pu) samples that are sourced from multiple, different reactor types present a challenge to nuclear forensics investigations. Previous studies have developed a nuclear forensics methodology capable of identifying a Pu sample's reactor type of origin using isotope ratios as features in machine learning classification models. However, the models could only attribute Pu sourced from a single reactor type. The methodology was adapted to discriminate between Pu produced from the six original single reactor type classes and twelve new classes comprised of binary mixtures of the six original reactor type classes. This adaptation was a success, with a support vector machine (SVM) identified as the most suitable model type for the task. The model's sensitivity to different groups of features was examined and the model was also validated with data from experimentally produced Pu samples, in both single reactor type and mixed reactor type cases.

Original language	English
Article number	111271
Journal	Annals of Nuclear Energy
Volume	218
DOIs	https://doi.org/10.1016/j.anucene.2025.111271
State	Published - Aug 2025

Funding

The work performed was funded by the Consortium for Monitoring, Technology, and Verification under Department of Energy (DOE) National Nuclear Security Administration (NNSA) award number DE-NA0003920 . The opinions expressed in this article are the authors\u2019 own and do not necessarily state or reflect the view of the NNSA , the DOE, or the United States Government or any agency thereof. Neither the United States Government nor any agency thereof, nor any of their employees, makes any warranty, express or limited, or assumes any legal liability or responsibility for the accuracy, completeness, or usefulness of any information, apparatus, product, or process disclosed, or represents that its use would not infringe privately owned rights. Reference herein to any specific commercial product, process, or service by trade name, trademark, manufacturer, or otherwise does not necessarily constitute or imply its endorsement, recommendation, or favoring by the United States Government or any agency thereof.

Keywords

Machine Learning
Plutonium Forensics
Reactor Type

Access to Document

10.1016/j.anucene.2025.111271

Cite this

@article{898f986e47b349c395b9a631260ed719,

title = "Adapting a machine learning method for the source discrimination of plutonium samples mixed from multiple reactor types",

abstract = "Plutonium (Pu) samples that are sourced from multiple, different reactor types present a challenge to nuclear forensics investigations. Previous studies have developed a nuclear forensics methodology capable of identifying a Pu sample's reactor type of origin using isotope ratios as features in machine learning classification models. However, the models could only attribute Pu sourced from a single reactor type. The methodology was adapted to discriminate between Pu produced from the six original single reactor type classes and twelve new classes comprised of binary mixtures of the six original reactor type classes. This adaptation was a success, with a support vector machine (SVM) identified as the most suitable model type for the task. The model's sensitivity to different groups of features was examined and the model was also validated with data from experimentally produced Pu samples, in both single reactor type and mixed reactor type cases.",

keywords = "Machine Learning, Plutonium Forensics, Reactor Type",

author = "O'Neal, {Patrick J.} and Chirayath, {Sunil S.}",

note = "Publisher Copyright: {\textcopyright} 2025",

year = "2025",

month = aug,

doi = "10.1016/j.anucene.2025.111271",

language = "English",

volume = "218",

journal = "Annals of Nuclear Energy",

issn = "0306-4549",

publisher = "Elsevier",

}

TY - JOUR

T1 - Adapting a machine learning method for the source discrimination of plutonium samples mixed from multiple reactor types

AU - O'Neal, Patrick J.

AU - Chirayath, Sunil S.

PY - 2025/8

Y1 - 2025/8

N2 - Plutonium (Pu) samples that are sourced from multiple, different reactor types present a challenge to nuclear forensics investigations. Previous studies have developed a nuclear forensics methodology capable of identifying a Pu sample's reactor type of origin using isotope ratios as features in machine learning classification models. However, the models could only attribute Pu sourced from a single reactor type. The methodology was adapted to discriminate between Pu produced from the six original single reactor type classes and twelve new classes comprised of binary mixtures of the six original reactor type classes. This adaptation was a success, with a support vector machine (SVM) identified as the most suitable model type for the task. The model's sensitivity to different groups of features was examined and the model was also validated with data from experimentally produced Pu samples, in both single reactor type and mixed reactor type cases.

AB - Plutonium (Pu) samples that are sourced from multiple, different reactor types present a challenge to nuclear forensics investigations. Previous studies have developed a nuclear forensics methodology capable of identifying a Pu sample's reactor type of origin using isotope ratios as features in machine learning classification models. However, the models could only attribute Pu sourced from a single reactor type. The methodology was adapted to discriminate between Pu produced from the six original single reactor type classes and twelve new classes comprised of binary mixtures of the six original reactor type classes. This adaptation was a success, with a support vector machine (SVM) identified as the most suitable model type for the task. The model's sensitivity to different groups of features was examined and the model was also validated with data from experimentally produced Pu samples, in both single reactor type and mixed reactor type cases.

KW - Machine Learning

KW - Plutonium Forensics

KW - Reactor Type

UR - http://www.scopus.com/inward/record.url?scp=105000483265&partnerID=8YFLogxK

U2 - 10.1016/j.anucene.2025.111271

DO - 10.1016/j.anucene.2025.111271

M3 - Article

AN - SCOPUS:105000483265

SN - 0306-4549

VL - 218

JO - Annals of Nuclear Energy

JF - Annals of Nuclear Energy

M1 - 111271

ER -

Adapting a machine learning method for the source discrimination of plutonium samples mixed from multiple reactor types

Abstract

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this