Skip to main navigation
Skip to search
Skip to main content
Princeton University Home
Help & FAQ
Link opens in a new tab
Search content at Princeton University
Home
Profiles
Research units
Facilities
Projects
Research output
Press/Media
Machine learning-based real-time kinetic profile reconstruction in DIII-D
Ricardo Shousha
, Jaemin Seo
, Keith Erickson
, Zichuan Xing
,
Sang Kyeun Kim
, Joseph Abbate
,
Egemen Kolemen
PPPL Tokamak Expermntl Science
PPPL Engineering
Mechanical & Aerospace Engineering
Andlinger Center for Energy & the Environment
Research output
:
Contribution to journal
›
Article
›
peer-review
34
Link opens in a new tab
Scopus citations
Overview
Fingerprint
Fingerprint
Dive into the research topics of 'Machine learning-based real-time kinetic profile reconstruction in DIII-D'. Together they form a unique fingerprint.
Sort by
Weight
Alphabetically
Keyphrases
Machine Learning Based
100%
Kinetic Profile
100%
Kinetic Equilibrium Reconstruction
100%
Profile Reconstruction
100%
Real-time Kinetics
100%
Plasma Control System
50%
Multilayer Perceptron
50%
Convolutional Layer
50%
Thomson Scattering
25%
Carbon Ions
25%
Electron Temperature
25%
Electron Density
25%
Scalar
25%
Encoder
25%
Scattered Data
25%
D Plasma
25%
Real-time Control
25%
Plasma Control
25%
Temperature Profile
25%
Current Density
25%
Human Bias
25%
Plasma Instabilities
25%
Real Environment
25%
Timing Analysis
25%
Toroidal Current
25%
Motional Stark Effect
25%
Reconstruction Method
25%
Charge Exchange Recombination
25%
Plasma Boundary
25%
Rotational Profile
25%
Real-time Plasma Control
25%
Machine Learning Models
25%
Physical Analysis
25%
Data Exchange
25%
Deep Neural Network
25%
Dropout Training
25%
Upsampling
25%
Ion Impurity
25%
Fusion Tokamak
25%
Objective Results
25%
Latent Feature Extraction
25%
Output Profile
25%
Engineering
Control System
100%
Convolutional Layer
100%
Learning System
100%
Perceptron
100%
Tokamak Device
50%
Feature Extraction
50%
Future Application
50%
Output Level
50%
Electron Energy
50%
Deep Neural Network
50%
Carrier Concentration
50%
Real time control
50%
Physics
Plasma Control
100%
Machine Learning
100%
Neural Network
66%
Electron Energy
33%
Thomson Scattering
33%
Electron Density
33%
Tokamak Device
33%
Magnetohydrodynamic Stability
33%
Stark Effect
33%
Physical Analysis
33%
Deep Neural Network
33%
Earth and Planetary Sciences
Real Time
100%
Machine Learning
100%
Plasma Control
50%
Control System
33%
Self Organizing Systems
33%
Electron Energy
16%
Electron Density
16%
Current Density
16%
Tokamak Device
16%
Stark Effect
16%
Magnetohydrodynamic Stability
16%
Physical Analysis
16%
Pattern Recognition
16%
Machine Learning Model
16%
Data Exchange
16%
Material Science
Multilayer
100%
Density
50%
Carrier Concentration
50%