A sequence-based multi-task variational autoencoder with a transformer encoder learns an interpretable 2D latent space for JET plasma state monitoring, achieving a 96.2% disruption prediction success rate with warning times close to expert labels.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
physics.plasm-ph 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Towards Transparent and Accurate Plasma State Monitoring at JET
A sequence-based multi-task variational autoencoder with a transformer encoder learns an interpretable 2D latent space for JET plasma state monitoring, achieving a 96.2% disruption prediction success rate with warning times close to expert labels.