
Artificial intelligence applied to nuclear forensics via deep learning
Nuclear forensics aims to investigate the origin and history of nuclear or radioactive materials via analytical techniques. Using electron microscopy images, we performed deep learning analysis to assess multiple calcination conditions and processing routes of nuclear samples. We applied, compared and fine-tuned via transfer learning state-of-the-art convolutional neural networks, performing numerous image classification and regression tasks. In addition to applying standard neural network architectures (ResNet, DenseNet), we implemented parallel networks to study multi-magnification acquisitions, and quantified model uncertainty during inference.