On the potential of physics-informed neural networks to solve inverse problems in tokamaks
Magnetic confinement nuclear fusion holds great promise as a source of clean and
sustainable energy for the future. However, achieving net energy from fusion reactors …
sustainable energy for the future. However, achieving net energy from fusion reactors …
A systematic investigation of radiation collapse for disruption avoidance and prevention on JET tokamak
To produce fusion reactions efficiently, thermonuclear plasmas have to reach extremely high
temperatures, which is incompatible with their coming into contact with material surfaces …
temperatures, which is incompatible with their coming into contact with material surfaces …
Stacking of predictors for the automatic classification of disruption types to optimize the control logic
Nowadays, disruption predictors, based on machine learning techniques, can perform well
but they typically do not provide any information about the type of disruption and cannot …
but they typically do not provide any information about the type of disruption and cannot …
Development of robust indicators for the identification of electron temperature profile anomalies and application to JET
Recent experience with metallic devices operating in ITER relevant regions of the
operational space, has shown that the disruptivity of these plasmas is unacceptably high …
operational space, has shown that the disruptivity of these plasmas is unacceptably high …
Detection of MARFEs using visible cameras for disruption prevention
In metallic devices, various forms of radiation collapse are one of the major causes of
plasma degradation leading to disruptions. Some of the most advanced scenarios, with …
plasma degradation leading to disruptions. Some of the most advanced scenarios, with …
Investigating the physics of tokamak global stability with interpretable machine learning tools
Featured Application Machine-learning-based techniques have been applied to disruption
prediction in Tokamaks and, by symbolic regression via genetic programming, physically …
prediction in Tokamaks and, by symbolic regression via genetic programming, physically …
Acceleration of an algorithm based on the maximum likelihood bolometric tomography for the determination of uncertainties in the radiation emission on JET using …
In recent years, a new tomographic inversion method based on the Maximum Likelihood
(ML) approach has been adapted to JET bolometry. Apart from its accuracy and reliability …
(ML) approach has been adapted to JET bolometry. Apart from its accuracy and reliability …
Dealing with artefacts in JET iterative bolometric tomography using masks
Bolometric tomography is a widely applied technique to infer important indirect quantities in
magnetically confined plasmas, such as the total radiated power. However, being an inverse …
magnetically confined plasmas, such as the total radiated power. However, being an inverse …
Fully convolutional spatio-temporal models for representation learning in plasma science
We have trained a fully convolutional spatio-temporal model for fast and accurate
representation learning in the challenging exemplar application area of fusion energy …
representation learning in the challenging exemplar application area of fusion energy …
Comparison of a fast low spatial resolution inversion method and peaking factors for the detection of anomalous radiation patterns and disruption prediction
The prediction of a disruptive event is a fundamental task for future fusion reactors. On
current tokamaks, most remedial actions have the aim of mitigating their effects, but in future …
current tokamaks, most remedial actions have the aim of mitigating their effects, but in future …