On learning latent dynamics of the AUG plasma state

Abstract

In this work, we demonstrate the utility of state representation learning applied to modeling the time evolution of electron density and temperature profiles at ASDEX-Upgrade (AUG). The proposed model is a deep neural network which learns to map the high dimensional profile observations to a lower dimensional state. The mapped states, alongside the original profile's corresponding machine parameters are used to learn a forward model to propagate the state in time. We show that this approach is able to predict AUG discharges using only a selected set of machine parameters. The state is then further conditioned to encode information about the confinement regime, which yields a simple baseline linear classifier, while still retaining the information needed to predict the evolution of profiles. We then discuss the potential use cases and limitations of state representation learning algorithms applied to fusion devices.

arXiv comment9 pages, 11 figures, 4th International Conference on Data-Driven Plasma Sciences

References in corpus (13)

• Adam: A Method for Stochastic Optimization
• Deep learning for universal linear embeddings of nonlinear dynamics
• Learning Latent Dynamics for Planning from Pixels
• State Representation Learning for Control: An Overview
• Mastering Diverse Domains through World Models
• DIVA: Domain Invariant Variational Autoencoders
• Deep Variational Bayes Filters: Unsupervised Learning of State Space Models from Raw Data
• Switching Linear Dynamics for Variational Bayes Filtering
• Data-driven model for divertor plasma detachment prediction
• Plasma Confinement Mode Classification Using a Sequence-to-Sequence Neural Network With Attention
• Capturing Label Characteristics in VAEs
• Developing Deep Learning Algorithms for Inferring Upstream Separatrix Density at JET
• Latent Neural Stochastic Differential Equations for Change Point Detection