Machine learning for the complex, multi-scale datasets in fusion energy

ML/AI techniques, particularly based on deep learning, will increasingly be used to accelerate scientific discovery for fusion experiment and simulation. Fusion energy devices have many disparate diagnostic instruments, capturing a broad range of interacting physics phenomena over multiple time and spatial scales. Also, fusion experiments are increasingly built to run longer pulses, with a goal of eventually running a reactor continuously. The confluence of these facts leads to large, complex datasets with phenomena manifest over long sequences. A key challenge is enabling scientists/engineers to utilize these datasets, for example to automatically catalog events of interest, predict the onset of phenomena such as tokamak disruptions, and enable comparisons to models/simulation. Given the size, multiple modalities, and multiscale nature of fusion data, deep learning models are attractive, but at these scales requires utilizing HPC resources. Many ML/AI techniques not fully utilized now will demand even more HPC resources, such as self-supervised learning to help fusion scientists create AI models with less labelled data, and advanced sequence models which use less GPU memory at the expense of increased compute. Additionally, deep learning models will enable faster, more in-depth analysis than previously available, such as extracting physics model parameters from data using conditional variational autoencoders, instead of slower techniques such as Markov chain Monte Carlo (MCMC). Comparison to simulation will also be enhanced through direct acceleration of simulation kernels using deep learning. These ML/AI techniques will give fusion scientists faster results, allowing more efficient machine use, and faster scientific discovery.