2022 Review of Data-Driven Plasma Science

Abstract

Data science and technology offer transformative tools and methods to science. This review article highlights latest development and progress in the interdisciplinary field of data-driven plasma science (DDPS). A large amount of data and machine learning algorithms go hand in hand. Most plasma data, whether experimental, observational or computational, are generated or collected by machines today. It is now becoming impractical for humans to analyze all the data manually. Therefore, it is imperative to train machines to analyze and interpret (eventually) such data as intelligently as humans but far more efficiently in quantity. Despite the recent impressive progress in applications of data science to plasma science and technology, the emerging field of DDPS is still in its infancy. Fueled by some of the most challenging problems such as fusion energy, plasma processing of materials, and fundamental understanding of the universe through observable plasma phenomena, it is expected that DDPS continues to benefit significantly from the interdisciplinary marriage between plasma science and data science into the foreseeable future.

arXiv comment112 pages (including 700+ references), 44 figures, submitted to IEEE Transactions on Plasma Science as a part of the IEEE Golden Anniversary Special Issue

References in corpus (136)

• Adam: A Method for Stochastic Optimization
• Conditional Generative Adversarial Nets
• Machine Learning for Fluid Mechanics
• Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning
• DeepXDE: A deep learning library for solving differential equations
• Machine learning and the physical sciences
• Sparsity and Incoherence in Compressive Sampling
• ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
• Unsupervised Learning of Video Representations using LSTMs
• Approximate Bayesian computation scheme for parameter inference and model selection in dynamical systems
• Moment Tensor Potentials: a class of systematically improvable interatomic potentials
• Turbulence Modeling in the Age of Data
• Machine learning phases of matter
• Hidden Physics Models: Machine Learning of Nonlinear Partial Differential Equations
• Machine learning accelerated computational fluid dynamics
• The UMIST database for astrochemistry 2012
• A Double-Pulsar System - A Rare Laboratory for Relativistic Gravity and Plasma Physics
• Machine Learning for Integrating Data in Biology and Medicine: Principles, Practice, and Opportunities
• Compressed Sensing MRI Reconstruction using a Generative Adversarial Network with a Cyclic Loss
• Discovering Phase Transitions with Unsupervised Learning
• A KInetic Database for Astrochemistry (KIDA)
• Convolutional Neural Networks as a Model of the Visual System: Past, Present, and Future
• PDE-Net 2.0: Learning PDEs from Data with A Numeric-Symbolic Hybrid Deep Network
• Deep UQ: Learning deep neural network surrogate models for high dimensional uncertainty quantification
• A Physics-Informed Machine Learning Approach for Solving Heat Transfer Equation in Advanced Manufacturing and Engineering Applications
• Deep Generative Design: Integration of Topology Optimization and Generative Models
• A spectral, quasi-cylindrical and dispersion-free Particle-In-Cell algorithm
• Physics-informed deep learning for incompressible laminar flows
• Acceleration of electrons in the plasma wakefield of a proton bunch
• De novo exploration and self-guided learning of potential-energy surfaces
• PDE-Net: Learning PDEs from Data
• Relativistic electron beams driven by kHz single-cycle light pulses
• Optimizing the Latent Space of Generative Networks
• Dimension-independent likelihood-informed MCMC
• Deep Decoder: Concise Image Representations from Untrained Non-convolutional Networks
• Partially Ionized Plasmas in Astrophysics
• TTHRESH: Tensor Compression for Multidimensional Visual Data
• Transformation of arbitrary distributions to the normal distribution with application to EEG test-retest reliability
• Compressed Sensing with Deep Image Prior and Learned Regularization
• Predicting Solar Flares Using a Long Short-Term Memory Network
• Bayesian optimization of a free-electron laser
• Automation and control of laser wakefield accelerators using Bayesian optimisation
• Geometric MCMC for Infinite-Dimensional Inverse Problems
• Predicting Solar Flares Using SDO/HMI Vector Magnetic Data Product and Random Forest Algorithm
• The data-driven future of high energy density physics
• Gaussian Process Regression Networks
• Fast modeling of turbulent transport in fusion plasmas using neural networks
• Machine learning applied to single-shot x-ray diagnostics in an XFEL
• Multilevel and multifidelity uncertainty quantification for cardiovascular hemodynamics
• SDRBench: Scientific Data Reduction Benchmark for Lossy Compressors
• Adaptive Leja sparse grid constructions for stochastic collocation and high-dimensional approximation
• Machine Learning for Orders of Magnitude Speedup in Multi-Objective Optimization of Particle Accelerator Systems
• Physics-constrained, low-dimensional models for MHD: First-principles and data-driven approaches
• Supervised Learning with Quantum-Inspired Tensor Networks
• Uniformly Accurate Machine Learning Based Hydrodynamic Models for Kinetic Equations
• Error Analysis of ZFP Compression for Floating-Point Data
• Uncovering turbulent plasma dynamics via deep learning from partial observations
• Coherent control of plasma dynamics
• Geodesic Monte Carlo on Embedded Manifolds
• Uncertainty Estimates for Theoretical Atomic and Molecular Data
• Quantifying Translation-Invariance in Convolutional Neural Networks
• ExoGAN: Retrieving Exoplanetary Atmospheres Using Deep Convolutional Generative Adversarial Networks
• Deep convolutional neural networks for multi-scale time-series classification and application to disruption prediction in fusion devices
• Predicting solar flares with machine learning: investigating solar cycle dependence
• Enhancing SDO/HMI images using deep learning
• An Ensemble of Bayesian Neural Networks for Exoplanetary Atmospheric Retrieval
• Contemporary machine learning: a guide for practitioners in the physical sciences
• Hybrid deep learning architecture for general disruption prediction across tokamaks
• Deep neural network Grad-Shafranov solver constrained with measured magnetic signals
• Algorithmic Guarantees for Inverse Imaging with Untrained Network Priors
• QDB: a new database of plasma chemistries and reactions
• Demonstration of stable long-term operation of a kilohertz laser-plasma accelerator
• Laser-accelerated, low divergence 15 MeV quasi-monoenergetic electron bunches at 1 kHz
• Multi-Objective Bayesian Optimization for Accelerator Tuning
• Deep learning for plasma tomography using the bolometer system at JET
• Machine learning for beam dynamics studies at the CERN Large Hadron Collider
• Adaptive 3D convolutional neural network-based reconstruction method for 3D coherent diffraction imaging
• Constructing a new predictive scaling formula for ITER's divertor heat-load width informed by a simulation-anchored machine learning
• SOFT: A synthetic synchrotron diagnostic for runaway electrons
• Machine learning plasma-surface interface for coupling sputtering and gas-phase transport simulations
• Physics-informed Gaussian Process for Online Optimization of Particle Accelerators
• Uncertainty quantification for proton-proton fusion in chiral effective field theory
• Generative Models for Low-Rank Video Representation and Reconstruction
• The Blind Implosion-Maker - Automated Inertial Confinement Fusion experiment design
• Neural network surrogate of QuaLiKiz using JET experimental data to populate training space
• Measuring the Electron Temperature and Identifying Plasma Detachment using Machine Learning and Spectroscopy
• Machine Learning Surrogate Models for Landau Fluid Closure
• Machine learning moment closure models for the radiative transfer equation I: directly learning a gradient based closure
• Deep learning based surrogate model for first-principles global simulations of fusion plasmas
• Using neural networks to accelerate the solution of the Boltzmann equation
• Multi-component Decomposition of Astronomical Spectra by Compressed Sensing
• Predicting Coronal Mass Ejections Using SDO/HMI Vector Magnetic Data Products and Recurrent Neural Networks
• Determining cross sections from transport coefficients using deep neural networks
• Gradient-based Optimization for Regression in the Functional Tensor-Train Format
• An application of survival analysis to disruption prediction via Random Forests
• Multiobjective optimization of the dynamic aperture for SLS 2.0 using surrogate models based on artificial neural networks
• Cognitive simulation models for inertial confinement fusion: Combining simulation and experimental data
• Incorporating Physical Knowledge into Machine Learning for Planetary Space Physics
• New closures for more precise modeling of Landau damping in the fluid framework
• Inferring Vector Magnetic Fields from Stokes Profiles of GST/NIRIS Using a Convolutional Neural Network
• Computed stereo lensless X-ray imaging
• Experiment data-driven modeling of tokamak discharge in EAST
• A stochastic kinetic scheme for multi-scale plasma transport with uncertainty quantification
• Robust, open-source removal of systematics in Kepler data
• Neural network representability of fully ionized plasma fluid model closures
• Accurate and confident prediction of electron beam longitudinal properties using spectral virtual diagnostics
• Plasma-MDS, a metadata schema for plasma science with examples from plasma technology
• DeepSun: Machine-Learning-as-a-Service for Solar Flare Prediction
• Temporal Feedback Control of High-Intensity Laser Pulses to Optimize Ultrafast Heating of Atomic Clusters
• Turbulence model reduction by deep learning
• Foreword to the Focus Issue on Machine Learning in Astronomy and Astrophysics
• A comparative study of structural similarity and regularization for joint inverse problems governed by PDEs
• Exploring Sensitivity of ICF Outputs to Design Parameters in Experiments Using Machine Learning
• Microparticle cloud imaging and tracking for data-driven plasma science
• Identifying magnetic reconnection in 2D Hybrid Vlasov Maxwell simulations with Convolutional Neural Networks
• Uncertainty Quantification for Virtual Diagnostic of Particle Accelerators
• Proof of concept of a fast surrogate model of the VMEC code via neural networks in Wendelstein 7-X scenarios
• Data-Free Likelihood-Informed Dimension Reduction of Bayesian Inverse Problems
• Astrophysics and Big Data: Challenges, Methods, and Tools
• Identifying and Tracking Solar Magnetic Flux Elements with Deep Learning
• Detecting Reconnection Events in Kinetic Vlasov Hybrid Simulations Using Clustering Techniques
• Adaptive low rank and sparse decomposition of video using compressive sensing
• Beyond optimization -- supervised learning applications in relativistic laser-plasma experiments
• Multi-beam Energy Moments of Multibeam Particle Velocity Distributions
• Detecting reconnection sites using the Lorentz Transformations for electromagnetic fields
• Characterizing magnetic reconnection regions using Gaussian mixture models on particle velocity distributions
• Analysis of beam position monitor requirements with Bayesian Gaussian regression
• Billion-pixel X-ray camera (BiPC-X)
• Multi-Beam Energy Moments of Compound Measured Ion Velocity Distributions
• Bayesian Approach for Linear Optics Correction
• SpaceML: Distributed Open-source Research with Citizen Scientists for the Advancement of Space Technology for NASA
• Near real-time streaming analysis of big fusion data
• Renormalized Mutual Information for Artificial Scientific Discovery
• Towards Accommodating Real-time Jobs on HPC Platforms
• Exploring Generative Physics Models with Scientific Priors in Inertial Confinement Fusion
• Adaptive Machine Learning for Time-Varying Systems: Low Dimensional Latent Space Tuning

Cited by in corpus (9)

• Condensed Matter Systems Exposed to Radiation: Multiscale Theory, Simulations, and Experiment
• Fast Dynamic 1D Simulation of Divertor Plasmas with Neural PDE Surrogates
• Physics-separating artificial neural networks for predicting initial stages of Al sputtering and thin film deposition in Ar plasma discharges
• A multifidelity Bayesian optimization method for inertial confinement fusion design
• A data management system for machine learning research of tokamak
• Physics-separating artificial neural networks for predicting sputtering and thin film deposition of AlN in Ar/N${}_2$ discharges on experimental timescales
• Semantic Information Management in Low-Temperature Plasma Science and Technology with VIVO
• Machine-learned trends in mirror configurations in the Large Plasma Device
• Parallelized Real-time Physics Codes for Plasma Control on DIII-D