3 citations · 10 across the 9 of their papers we have counts for
11 papers
Is Your AI Fast Enough to Run a Fusion Reactor?
Nathaniel Chen, Andrew Rothstein, Ricardo Shousha +4
Machine learning models are increasingly used in feedback control loops for nuclear fusion, where inference speed and predictable timing are critical. We summarize lessons from mod…
Robust Control of ECH Deposition Profiles on DIII-D
A. Rothstein, H. J. Farre-Kaga, K. Yasoda +5
Electron Cyclotron Heating (ECH) is a key actuator in DIII-D and future tokamaks that provides auxiliary heating, localized current drive for scenario development and MHD stability…
Offline Reinforcement Learning for Rotation Profile Control in Tokamaks
Rohit Sonker, Hiro Josep Farre Kaga, Jiayu Chen +5
Tokamaks remain leading candidates for achieving practical fusion energy, yet many important control problems inside these devices are still difficult or unsolved. One such challen…
TokEye: Fast Signal Extraction for Fluctuating Time Series via Offline Self-Supervised Learning From Fusion Diagnostics to Bioacoustics
Nathaniel Chen, Kouroche Bouchiat, Peter Steiner +6
Next-generation fusion facilities like ITER face a "data deluge," generating petabytes of multi-diagnostic signals daily that challenge manual analysis. We present a "signals-first…
Enabling Integrated AI Control on DIII-D: A Control System Design with State-of-the-art Experiments
Andrew Rothstein, Hiro Joseph Farre-Kaga, Jalal Butt +7
We present the design and application of a general algorithm for Prediction And Control using MAchiNe learning (PACMAN) in DIII-D. Machine learing (ML)-based predictors and control…
Control of pedestal-top electron density using RMP and gas puff at KSTAR
Minseok Kim, S. K. Kim, A. Rothstein +20
We report the experimental results of controlling the pedestal-top electron density by applying resonant magnetic perturbation with the in-vessel control coils and the main gas puf…
Regulation Compliant AI for Fusion: Real-Time Image Analysis-Based Control of Divertor Detachment in Tokamaks
Nathaniel Chen, Cheolsik Byun, Azarakash Jalalvand +7
While artificial intelligence (AI) has been promising for fusion control, its inherent black-box nature will make compliant implementation in regulatory environments a challenge. T…
Multi-Timescale Dynamics Model Bayesian Optimization for Plasma Stabilization in Tokamaks
Rohit Sonker, Alexandre Capone, Andrew Rothstein +3
Machine learning algorithms often struggle to control complex real-world systems. In the case of nuclear fusion, these challenges are exacerbated, as the dynamics are notoriously c…
Assessing the Numerical Stability of Physics Models to Equilibrium Variation through Database Comparisons
A. Rothstein, V. Ailiani, K. Krogen +7
High fidelity kinetic equilibria are crucial for tokamak modeling and analysis. Manual workflows for constructing kinetic equilibria are time consuming and subject to user error, m…
TorbeamNN: Machine learning based steering of ECH mirrors on KSTAR
Andrew Rothstein, Minseok Kim, Minho Woo +12
We have developed TorbeamNN: a machine learning surrogate model for the TORBEAM ray tracing code to predict electron cyclotron heating and current drive locations in tokamak plasma…
Interpreting AI for Fusion: an application to Plasma Profile Analysis for Tearing Mode Stability
Hiro J Farre-Kaga, Andrew Rothstein, Rohit Sonker +6
AI models have demonstrated strong predictive capabilities for various tokamak instabilities--including tearing modes (TM), ELMs, and disruptive event--but their opaque nature rais…