• Promotor: Prof. Geert Verdoolaege
  • Supervisor: Dr. Yangyang Zhang, Dr. Azarakhsh Jalalvand
  • Study programs: Master of Science in Engineering Physics, Master of Science in Physics and Astronomy, Master of Science in Teaching in Science and Technology (Physics and Astronomy), European Master of Science in Nuclear Fusion and Engineering Physics, Master of Science in Information Engineering Technology
  • Location: Technicum, at home

Problem setting

The worldwide research on controlled thermonuclear fusion aims to realize a source of energy on earth that is limitless, clean and safe. It is a large-scale enterprise that mimics the power source of the stars. Ghent University is involved in fusion R&D by developing data science methods and numerical models for understanding and predicting the complex science and technology of fusion devices based on magnetic plasma confinement.

Reconstruction of space-resolved measurements of the electron density in fusion plasmas is essential for plasma control and physics studies. One of the most accurate measurement systems (diagnostics) for such a task is based on Thomson scattering (TS). However, TS is not always available due to the complexity of the system and its high cost. For reconstructing detailed density profiles on future fusion reactors, it would be extremely useful to be able to rely on simpler, less costly measurement systems.

Objectives

The primary aim of this thesis project is to leverage machine learning for reconstructing highly detailed density profiles in tokamaks based on measurements of interferometry. The method relies on neural networks, as pioneered in [1]. Specifically, the objectives will be:

  1. Study the super-resolution method proposed in [1].
  2. Obtain data of interferometry and TS from a tokamak, like JET, EAST, DIII-D,…
  3. Design and implement a neural network to perform the learning task.
  4. Validate the method on the machine on which the model was trained and generalize to data from another machine.

References
[1] A. Jalalvand et al., Multimodal Super-Resolution: Discovering hidden physics and its application to fusion plasmas, arXiv:2405.05908, 2024