Vignesh Gopakumar Stanislas Pamela Lorenzo Zanisi
Classical sequential models employed in time-series prediction rely on learning the mappings from the past to the future instances by way of a hidden state. The Hidden states characterise the historical information and encode the required temporal dependencies. However, most existing sequential models operate within finite-dimensional Euclidean spa…
PreprintAndrew Lahiff Shaun de Witt Miguel Caballer Giuseppe La Roca Stanislas Pamela David Coster
Access to both High Throughput Computing (HTC) and High Performance Computing (HPC) facilities is vitally important to the fusion community, not only for plasma modelling but also for advanced engineering and design, materials research, rendering, uncertainty quantification and advanced data analytics for engineering operations. The computing re…
Preprint PublishedSiobhan Smith Stanislas Pamela Howard Wilson Guido Huijsmans
Edge localised modes (ELMs) are magneto-hydrodynamic (MHD) instabilities that drive filamentary plasma eruptions in high confinement tokamak discharges [1]. Gaining an improved understanding of ELMs is important [2]; in future fusion reactors such as ITER, ELM heat fluxes will need to be limited to ensure durability of divertor materials [3]. A …
Preprint PublishedChristopher Ham Andrew Kirk Stanislas Pamela Howard Wilson
Fusion is one of very few options for sustainable, baseload power to the grid that is necessary to meet the energy needs of future generations. The tokamak is the most advanced approach to fusion and, with the construction of ITER, we are approaching power plant conditions. While commercialisation of this key technology is a main driver for tokamak…
Preprint Published