-
UKAEA-CCFE-PR(25)2782022
Physics-Informed Neural Networks have shown unique utility in parameterising the solution of a well-defined partial differential equation using automatic differentiation and residual losses. Though they provide theoretical guarantees of convergence, in practice the required training regimes tend to be exacting and demanding. Through the course o…
-
UKAEA-CCFE-PR(22)562022
Parareal is a well-studied algorithm for numerically integrating systems of time-dependent differential equations by parallelising the temporal domain. Given some initial values at each temporal sub-interval, the algorithm iteratively locates a solution in a fixed number of iterations using a predictor-corrector, stopping once a tolerance is met. T…
-
UKAEA-CCFE-PR(20)1232019
We propose a method for data-driven modelling of the temporal evolution of the plasma and neutral characteristics at the edge of a Tokamak using neural networks. Our method proposes a novel fully convolutional network that is capable of predicting the time evolution of the physics parameters along the two-dimensional representation of the poloid…
-
UKAEA-CCFE-PR(21)652018
This paper explores the application of the parareal algorithm to simulations of ELMs in ITER plasma. The primary focus of this research is identifying the parameters that lead to optimum performance. Since the plasma dynamics vary extremely fast during an ELM cycle, a straightforward application of the algorithm is not possible and a modification t…
-
UKAEA-CCFE-PR(19)662019
We use deep neural networks to classify time series generated by discrete and continuous dynamical systems based on their chaotic behavior. Our approach to circumvent the lack of precise models for some of the most challenging real-life applications is to train different neural networks on a data set from a dynamical system with a basic or low-dime…
-
UKAEA-CCFE-PR(18)272018
This paper explores the application of the parareal algorithm to simulations of ELMs in ITER plasma. The primary focus of this research is identifying the parameters that lead to optimum performance. Since the plasma dynamics vary extremely fast during an ELM cycle, a straightforward application of the algorithm is not possible and a modification t…
Showing 1 - 6 of 6 UKAEA Paper Results
Page 1 of 1