a student working in a lab

Artificial intelligence on the hunt for illegal nuclear materials

a student who works in a laboratory

Nuclear engineering doctoral student Sean Martinson works on the purification of plutonium solutions in a protective glove box at Sunil Chirayath’s nuclear forensics lab.


Justin Elizalde/Texas A&M Engineering

Millions of shipments of nuclear and other radiological materials are transported in the US every year for good reasons, including healthcare, power generation, research and manufacturing. But there remains the threat that adversaries in possession of stolen or illegally produced nuclear materials or weapons will try to smuggle them across borders for nefarious purposes.

Texas A&M University researchers are making it harder for them to succeed.

When border agents intercept illegal nuclear materials, investigators need to know who produced them and where they came from. Fortunately, nuclear materials contain certain forensic markers that can reveal valuable information, much like fingerprints can identify criminals.

For example, when scientists examine the concentration of certain key contaminating isotopes in separated plutonium samples, they can determine three distinct features of the sample’s history: the type of nuclear reactor that produced it, how long the plutonium or uranium was in the reactor, and how long ago it was produced.

Current statistical methods allow them to determine these three attributes using a generated database that stores the required information as a mathematical variation of these attributes for different types of nuclear reactors and get a good idea of ​​who made the material.

“But what if researchers get a mixed plutonium sample?” said Sunil Chirayath, author of a new study on nuclear forensics recently published in the journal Nuclear Sciences and Engineering “Suppose the opponent mixes materials from two nuclear reactors at two different times and that material is cooled at different times. A bad actor could do this intentionally to cover it up.”

Mixed samples of nuclear material are significantly more challenging to identify using traditional methods. In a real-life situation, the extra time required could have a catastrophic impact on the global community.

To improve the process, said Chirayath, an associate professor in the Department of Nuclear Engineering and director of the Texas A&M Engineering Experiment Station’s Center for Nuclear Safety Science and Policy Initiativestogether with his research team has developed a methodology using machine learning, a type of artificial intelligence.

He can produce identifying marks through simulations and then store that data in a 3D database. Each attribute is one level of the database, and a standard computer can quickly process the data and lead investigators to the reactor type that produced the plutonium sample — and possibly the suspects — by connecting other puzzle pieces collected through traditional forensics.

To date, Texas A&M has conducted three experiments with uranium irradiation using three different reactor types and post-irradiation studies. Without knowing the origin of the samples, doctoral researcher Patrick O’Neal successfully identified where each of the plutonium samples was produced using machine learning.

The work is done through a consortium of national laboratories and universities funded by the National Nuclear Security Administration of the United States Department of Energy. The consortium focuses on developing new methods for detecting and countering nuclear proliferation and on training the next generation of nuclear security professionals. Chirayath’s team will soon conduct another radiation treatment and the associated post-radiation research with funding already in place.

The next step is to bring this machine learning method to high-level government labs, where researchers can work with much larger samples of nuclear material. University labs are constrained by stricter radiation safety limits.

Chirayath is convinced that efforts to prevent nuclear proliferation are paying off. The International Treaty on the Non-Proliferation of Nuclear Weapons arose out of concerns about nuclear weapons, and all but four countries – India, Israel, Pakistan and South Sudan – have signed it. North Korea signed it, but later walked away from it.

Chirayath also notes that with the increase in nuclear power production comes a greater risk that the technology will be used to create weapons capable of mass destruction.

“We need to ensure that materials are not diverted from peaceful uses,” he said. “We need to double down on our tools and methodologies, but it’s not just technical tools. We also need to double down on our policies and agreements to prevent proliferation.”

Leave a Comment

Your email address will not be published.