Klein featured by NNSA for cutting-edge work in AI for national security

-

-

Natalie Klein

-

Natalie Klein of Statistical Sciences (CCS-6) recently had her work featured in an NNSA article on a national collaboration to drive next-generation in artificial intelligence (AI) for nonproliferation. Her project, titled “One-Shot Target Detection Via Physics-Informed Training,” investigates one of the common challenges faced in AI for a specific domain of knowledge, which is a lack of usable data.

Klein and her team worked to train a deep neural network to reliably characterize materials on the ground, even in the absence of such comprehensive training images from hyperspectral data. To overcome this lack of data, the team generated its own synthetic data using the team’s domain-specific knowledge of physics and chemistry. Informed by this generated data, the network was then able to accurately detect materials, even when faced with new and authentic data containing novel materials and unseen environmental conditions.

Klein anticipates the model could be applied to quickly detect materials in new data without needing to account for environmental conditions that may influence the signatures. This type of airborne detection could be used to recognize nuclear materials in support of nonproliferation efforts.