US government research is developing artificial intelligence technologies which will allow agencies to track “malicious actors” looking to circumvent international nuclear nonproliferation safeguards.
New research from Pacific Northwest National Laboratory (PNNL) uses machine learning, data analytics, and artificial reasoning to make threat detection and forensic analysis in the nuclear domain easier and faster, say researchers.
Agencies including the International Atomic Energy Agency (IAEA) currently employ monitoring techniques to ensure nuclear materials subject to agreements are not used to produce nuclear weapons, and forensics methods to determine the origin of nuclear materials recovered by law enforcement, but these techniques are often time and labour-intensive.
“Preventing nuclear proliferation requires vigilance,” says PNNL nonproliferation analyst Benjamin Wilson and a former safeguards inspector for the IAEA. “It involves labour, from audits of nuclear materials to investigations into who is handling nuclear materials. Data analytics-driven techniques can be leveraged to make this easier.”
With support from the National Nuclear Security Administration (NNSA), the Mathematics for Artificial Reasoning in Science (MARS) Initiative, and the Department of Defense, PNNL researchers are working on several projects to make nuclear nonproliferation and safeguards more effective.
The IAEA monitors nuclear facilities to make sure nuclear materials are not diverted to nuclear weapons. This typically involves regular inspections and sample collection for subsequent destructive assays. “We could save a lot of time and labour costs if we could create a system that detects abnormalities automatically from the facilities process data,” says Wilson.
Artificial intelligence helps answer nuclear questions
In a study published in The International Journal of Nuclear Safeguards and Non-Proliferation, Wilson worked with researchers from Sandia National Laboratories to build a virtual replica of a reprocessing facility. They then trained a machine learning model to detect process data patterns representing the diversion of nuclear materials. In this simulated environment, the model showed encouraging results. “Though it is unlikely that this approach would be used in the near future, our system provides a promising start to complement existing safeguards,” says Wilson.
PNNL data scientists Megha Subramanian and Alejandro Zuniga along with Benjamin Wilson, Kayla Duskin and Rustam Goychayev are working to make this task easier through research which was featured in The International Journal of Nuclear Safeguards and Non-Proliferation. “We wanted to create a way for researchers to ask nuclear domain-specific questions and receive correct answers,” says Subramanian.
PNNL researchers, in collaboration with the University of Utah, Lawrence Livermore National Laboratory, and Los Alamos National Laboratory, developed a way to use machine learning to aid in the forensic analysis of nuclear samples. Their method uses electron microscopy images to compare microstructures as samples contain subtle differences that can be identified using machine learning.
“Imagine that synthesising nuclear materials was like baking cookies,” says Elizabeth Jurrus, MARS initiative lead. “Two people can use the same recipe and end up with different-looking cookies. It’s the same with nuclear materials.”
Though it may take some time before agencies like the IAEA adopt machine learning techniques into their nuclear threat detection process, it is clear that these technologies can impact and streamline the process.
“Though we don’t expect machine learning to replace anyone’s job, we see it as a way to make their jobs easier,” said Jurrus. “We can use machine learning to identify important information so that analysts can focus on what is most significant.”