Author: Paul Rivenberg | Plasma Science and Fusion Center<\/p>\n
To make fusion energy a viable resource for the world\u2019s energy grid, researchers need to understand the turbulent motion of plasmas: a mix of ions and electrons swirling around in reactor vessels. The plasma particles, following magnetic field lines in toroidal chambers known as tokamaks, must be confined long enough for fusion devices to produce significant gains in net energy, a challenge when the hot edge of the plasma (over 1 million degrees Celsius) is just centimeters away from the much cooler solid walls of the vessel.<\/p>\n
Abhilash Mathews, a PhD candidate in the Department of Nuclear Science and Engineering<\/a> working at MIT\u2019s Plasma Science and Fusion Center (PSFC), believes this plasma edge to be a particularly rich source of unanswered questions. A turbulent boundary, it is central to understanding plasma confinement, fueling, and the potentially damaging heat fluxes that can strike material surfaces \u2014 factors that impact fusion reactor designs.<\/p>\n To better understand edge conditions, scientists\u00a0focus on modeling turbulence at this boundary using numerical simulations that will help predict the plasma’s behavior. However, \u201cfirst principles\u201d simulations of this region are among the most challenging and time-consuming computations in fusion research. Progress could be accelerated if researchers could develop \u201creduced\u201d computer models that run much faster, but with quantified levels of accuracy.<\/p>\n For decades, tokamak physicists have regularly used a reduced \u201ctwo-fluid theory\u201d rather than higher-fidelity models to simulate boundary plasmas in experiment, despite uncertainty about accuracy. In a pair of recent publications, Mathews begins directly testing the accuracy of this reduced plasma turbulence model in a new way: he combines physics with machine learning.<\/p>\n \u201cA successful theory is supposed to predict what you’re going to observe,\u201d explains Mathews, \u201cfor example, the temperature, the density, the electric potential, the flows. And it\u2019s the relationships between these variables that fundamentally define a turbulence theory. What our work essentially examines is the dynamic relationship between two of these variables: the turbulent electric field and the electron pressure.\u201d<\/p>\n In the first paper,<\/a> published in Physical Review E<\/em>, Mathews employs a novel deep-learning technique that uses artificial neural networks to build representations of the equations governing the reduced fluid theory. With this framework, he demonstrates a way to compute the turbulent electric field from an electron pressure fluctuation in the plasma consistent with the reduced fluid theory. Models commonly used to relate the electric field to pressure break down when applied to turbulent plasmas, but this one is robust even to noisy pressure measurements.<\/p>\n In the second paper<\/a>, published in Physics of Plasmas<\/em>, Mathews further investigates this connection, contrasting it against higher-fidelity turbulence simulations. This first-of-its-kind comparison of turbulence across models has previously been difficult \u2014 if not impossible \u2014 to evaluate precisely. Mathews finds that in plasmas relevant to existing fusion devices, the reduced fluid model’s predicted turbulent fields are consistent with high-fidelity calculations. In this sense, the reduced turbulence theory works. But to fully validate it, \u201cone should check every connection between every variable,\u201d says Mathews.<\/p>\n Mathews\u2019 advisor, Principal Research Scientist Jerry Hughes, notes that plasma turbulence is notoriously difficult to simulate, more so than the familiar turbulence seen in air and water. \u201cThis work shows that, under the right set of conditions, physics-informed machine-learning techniques can paint a very full picture of the rapidly fluctuating edge plasma, beginning from a limited set of observations. I\u2019m excited to see how we can apply this to new experiments, in which we essentially never observe every quantity we want.\u201d<\/p>\n These physics-informed deep-learning methods pave new ways in testing old theories and expanding what can be observed from new experiments. David Hatch, a research scientist at the Institute for Fusion Studies at the University of Texas at Austin, believes these applications are the start of a promising new technique.<\/p>\n \u201cAbhi\u2019s work is a major\u00a0achievement with the potential for broad application,\u201d he says. \u201cFor example, given limited diagnostic measurements of a specific plasma quantity, physics-informed machine learning could infer additional plasma quantities in a nearby domain, thereby augmenting the information provided by a given diagnostic. The technique also opens new strategies for model validation.\u201d<\/p>\n Mathews sees exciting research ahead.<\/p>\n \u201cTranslating these techniques into fusion experiments for real edge plasmas is one goal we have in sight, and work is currently underway,\u201d he says. \u201cBut this is just the beginning.\u201d<\/p>\n Mathews was\u00a0supported in this work\u00a0by the\u00a0Manson Benedict Fellowship,\u00a0Natural Sciences and Engineering Research Council of Canada,\u00a0and\u00a0U.S. Department of Energy Office of Science under the Fusion Energy Sciences program.\u200b<\/p>\n<\/div>\n Go to Source<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"