Using deep learning for the detection of UFOs within the JET tokamak

Authors:
Open Access
Publisher website
Google Scholar
Abstract
Components on the inner wall of fusion reactors are exposed to extremely high heat loads, and significant care must be taken to minimize the damage to these components during operation. UFOs, also known as transient impurity events, are small particles of dust within the tokamak vessel that can lead to plasma disruptions. These can cause serious damage to the device and remain a significant challenge for safe operations. This study presents a novel approach to track these UFO events by utilizing visual camera data from the Joint European Torus and a Convolutional Neural Network to identify UFOs within the tokamak. The model attained an accuracy of 95.1%, a precision of 95.4% for UFO detection, a recall of 95.1%, and a receiver operating characteristic curve area of 0.99. These metrics underscore the model's competence in reliably identifying UFOs with minimal false identifications. Consequently, this suggests the model's suitability for integration into UFO detection systems in tokamak environments, improving monitoring and efficiency, and potentially providing an avenue for real-time UFO detection in future research.
Funding Information
  • EUROfusion (101052200)
  • UK Atomic Energy Authority

This publication has 25 references indexed in Scilit: