104 citations · 372 across the 16 of their papers we have counts for
16 papers
AI-Machine Learning-Enabled Tokamak Digital Twin
William Tang, Eliot Feibush, Ge Dong +9
In addressing the Department of Energy's April, 2022 announcement of a Bold Decadal Vision for delivering a Fusion Pilot Plant by 2035, associated software tools need to be develop…
FTL: Transfer Learning Nonlinear Plasma Dynamic Transitions in Low Dimensional Embeddings via Deep Neural Networks
Zhe Bai, Xishuo Wei, William Tang +3
Deep learning algorithms provide a new paradigm to study high-dimensional dynamical behaviors, such as those in fusion plasma systems. Development of novel model reduction methods,…
DeepSpeed4Science Initiative: Enabling Large-Scale Scientific Discovery through Sophisticated AI System Technologies
Shuaiwen Leon Song, Bonnie Kruft, Minjia Zhang +89
In the upcoming decade, deep learning may revolutionize the natural sciences, enhancing our capacity to model and predict natural occurrences. This could herald a new era of scient…
Reconstruction of tokamak plasma safety factor profile using deep learning
Xishuo Wei, Ge Dong, Shuying Sun +3
In tokamak operations, accurate equilibrium reconstruction is essential for reliable real-time control and realistic post-shot instability analysis. The safety factor (q) profile d…
Implementation of AI/Deep Learning Disruption Predictor into a Plasma Control System
William Tang, Ge Dong, Jayson Barr +17
This paper reports on advances to the state-of-the-art deep-learning disruption prediction models based on the Fusion Recurrent Neural Network (FRNN) originally introduced a 2019 N…
Applications and Techniques for Fast Machine Learning in Science
Allison McCarn Deiana, Nhan Tran, Joshua Agar +84
In this community review report, we discuss applications and techniques for fast machine learning (ML) in science -- the concept of integrating power ML methods into the real-time…
Deep learning based surrogate model for first-principles global simulations of fusion plasmas
Ge Dong, Xishuo Wei, Jian Bao +3
The accurate identification and control of plasma instabilities is important for successful fusion experiments. First-principles simulations which can provide physics based instabi…
Fully Convolutional Spatio-Temporal Models for Representation Learning in Plasma Science
Ge Dong, Kyle Gerard Felker, Alexey Svyatkovskiy +2
We have trained a fully convolutional spatio-temporal model for fast and accurate representation learning in the challenging exemplar application area of fusion energy plasma scien…
Training Distributed Deep Recurrent Neural Networks with Mixed Precision on GPU Clusters
Alexey Svyatkovskiy, Julian Kates-Harbeck, William Tang
In this paper, we evaluate training of deep recurrent neural networks with half-precision floats. We implement a distributed, data-parallel, synchronous training algorithm by integ…
Degenerate Variational Integrators for Magnetic Field Line Flow and Guiding Center Trajectories
C. Leland Ellison, John M. Finn, Joshua W. Burby +3
Symplectic integrators offer many advantages for the numerical solution of Hamiltonian differential equations, including bounded energy error and the preservation of invariant sets…
Modern Gyrokinetic Particle-In-Cell Simulation of Fusion Plasmas on Top Supercomputers
Bei Wang, Stephane Ethier, William Tang +4
The Gyrokinetic Toroidal Code at Princeton (GTC-P) is a highly scalable and portable particle-in-cell (PIC) code. It solves the 5D Vlasov-Poisson equation featuring efficient utili…
Initializing and stabilizing variational multistep algorithms for modeling dynamical systems
C. L. Ellison, J. W. Burby, J. M. Finn +2
Backward error initialization and parasitic mode control are well-suited for use in algorithms that arise from a discrete variational principle on phase-space dynamics. Dynamical s…
Gauge properties of the guiding center variational symplectic integrator
Jonathan Squire, Hong Qin, William M. Tang
Variational symplectic algorithms have recently been developed for carrying out long-time simulation of charged particles in magnetic fields. As a direct consequence of their deriv…
Geometric integration of the Vlasov-Maxwell system with a variational particle-in-cell scheme
Jonathan Squire, Hong Qin, William M. Tang
A fully variational, unstructured, electromagnetic particle-in-cell integrator is developed for integration of the Vlasov-Maxwell equations. Using the formalism of Discrete Exterio…
The Hamiltonian structure and Euler-Poincaré formulation of the Vlasov-Maxwell and gyrokinetic systems
J. Squire, H. Qin, W. M. Tang +1
We present a new variational principle for the gyrokinetic system, similar to the Maxwell-Vlasov action presented in Ref. 1. The variational principle is in the Eulerian frame and…
Simulating Gyrokinetic Microinstabilities in Stellarator Geometry with GS2
J. A. Baumgaertel, E. A. Belli, W. Dorland +6
The nonlinear gyrokinetic code GS2 has been extended to treat non-axisymmetric stellarator geometry. Electromagnetic perturbations and multiple trapped particle regions are allowed…