Fusion data science
ITER and future fusion reactors will be very complex machines that will rely heavily on advanced control systems. In turn, plasma control depends crucially on plasma diagnostics that are required to provide reliable measurements of key plasma parameters, which is an important challenge owing to the particularly harsh environment of fusion plasmas. In addition, there is still an important lack of understanding of various aspects of tokamak and stellarator physics, necessitating a data-driven approach in many cases. Probability theory and machine learning methods have a major role to play in plasma control and plasma diagnosis, in increasing the understanding of the physics of magnetized fusion plasmas and in designing new fusion machines. State-of-the-art techniques for studying and controlling stochastic plasma phenomena, for analyzing data patterns, for modeling error propagation and for integrated data analysis have been introduced in fusion science since the last 20 years. The research unit Nuclear Fusion has been involved in this domain since the start of this important new trend and we have acquired a strong expertise at the front of this domain, ranging over several research activities. The research is based on solid mathematical foundations involving Bayesian probability theory and information geometry. We also employ various machine learning methods, including neural networks and deep learning.
Why fusion?
Nuclear fusion reactions involve the fusing of light elements (such as hydrogen) to form heavier ones (such as helium). Nuclear fusion is the process that powers the stars, transforming mass into energy according to Einstein's formula E = mc2.
The worldwide research on controlled thermonuclear fusion aims to realize fusion on earth, as a means to produce energy in a way that is both clean and safe. Fusion produces no greenhouse gases, no toxic or long-lived radioactive waste (only the reactor structure becomes slightly activated after a while) and neither is there any danger of major nuclear accidents like Tsjernobyl or Fukushima. Fusion is one of the few options available for sustainable energy production, to counter global warming and yet meet the steadily increasing energy demands of the 21st century. Contrary to solar and wind energy, fusion has the potential to provide large and local sources of continuous base-load power everywhere in the world.
Through the European Consortium for the Development of Fusion Energy (EUROfusion), the European Union maintains an ambitious research program targeted at realizing fusion electricity by 2050. The main focus of the research is on magnetic confinement fusion, in particular the tokamak concept, whereby the fusion reactions take place in a hot plasma confined by strong magnetic fields. In collaboration with fusion research centres all over the world, this is presently culminating in the ongoing construction of the international fusion device ITER at the Cadarache site near Aix-en-Provence in France, as well as the design of the first fusion demonstration reactor DEMO.
Inside view of the vacuum vessel of the JET tokamak. © EUROfusion
Plasma in the COMPASS tokamak. © IPP.CR
Nightfall over the ITER construction site. © ITER Organization
Our roots
At the UGent department of Applied Physics, the research unit Nuclear Fusion has been involved in fusion research since over forty years. Growing out of the long-standing expertise of the group in fusion diagnostics and experimentation on various fusion devices across Europe, the research presently concentrates on the rich area of fusion data science.