Related papers: A machine-learning-based tool for last closed-flux…
High throughput and low latency data processing is essential for systems requiring live decision making, control, and machine learning-optimized data reduction. We focus on two distinct use cases for in-flight streaming data processing for…
Neural networks have emerged as a powerful paradigm for tasks in high energy physics, yet their opaque training process renders them as a black box. In contrast, the traditional cut flow method offers simplicity and interpretability but…
A technique, volumetric power optimization, is presented for enhancing the power output of magnetic confinement fusion devices. Applied to a tokamak, this approach involves shifting the burning plasma region to a larger plasma volume while…
Understanding plasma instabilities is essential for achieving sustainable fusion energy, with large-scale plasma simulations playing a crucial role in both the design and development of next-generation fusion energy devices and the…
Neural networks unintentionally memorize training data, creating privacy risks in federated learning (FL) systems, such as inference and reconstruction attacks on sensitive data. To mitigate these risks and to comply with privacy…
A comprehensive two-fluid nonlinear theory of magnetic reconnection driven at a single, tearing-stable, rational surface embedded in an H-mode tokamak plasma is presented. The surface is assumed to be resonant with one of the dominant…
Recent advances in high-temperature-superconductor technology have made substantially higher toroidal magnetic fields technologically accessible, reopening the design space for compact, high-field tokamak reactors. Because reactor…
High-Temperature Superconductors (HTS) such as YBa2Cu3O7-delta (YBCO) are essential for next-generation Tokamak fusion reactors, where Rare-Earth Barium Copper Oxides (REBCO) form the functional layers in HTS magnets. Because YBCO's…
Nuclear fusion devices are constantly under the threat of malfunctions coming from the damages of plasma-facing materials due to being affected by thermal heat loads. The frequent heat loads during some transient events in large-scale…
Controlling and monitoring plasma within a tokamak device is complex and challenging. Plasma off-normal events, such as disruptions, are hindering steady-state operation. For large devices, they can even endanger the machine's integrity and…
The properties of the boundary plasma in a tokamak are now recognized to play a key role in determining the achievable fusion power and the lifetimes of plasma-facing components. Accurate quantitative modeling and improved qualitative…
A four-field system of equations which includes the neoclassical flow damping effects and the lowest-order finite-Larmor-radius (FLR) corrections is deduced from a system of gyrofluid equations. The FLR corrections to the poloidal flow…
We investigate magnetic reconnection in systems simultaneously containing asymmetric (anti-parallel) magnetic fields, asymmetric plasma densities and temperatures, and arbitrary in-plane bulk flow of plasma in the upstream regions. Such…
An international experiment, ITER is proposed as the next essential and critical step on the path to demonstrating the scientific and technological feasibility of fusion energy. ITER would give unique opportunities to explore, in reactor…
Machine-learned interatomic potentials (MLPs) provide near density functional theory (DFT) accuracy at reduced computational cost, but their reliability depends on representative training data and often deteriorates in transition-state…
It is shown that a relevant control of Hamiltonian chaos is possible through suitable small perturbations whose form can be explicitly computed. In particular, it is possible to control (reduce) the chaotic diffusion in the phase space of a…
Noises, artifacts, and loss of information caused by the magnetic resonance (MR) reconstruction may compromise the final performance of the downstream applications. In this paper, we develop a re-weighted multi-task deep learning method to…
In this work, we demonstrate the deployment of a hardware-accelerated machine learning (ML) inference system integrated into a real-time processing at the DIII-D tokamak fusion reactor. The team has successfully deployed an AMD/Xilinx…
Force-free plasmas are a good approximation where the plasma pressure is tiny compared with the magnetic pressure, which is the case during the cold vertical displacement event (VDE) of a major disruption in a tokamak. On time scales long…
It is known that magnetic perturbations can mitigate edge localized modes (ELMs) in experiments, for example MAST (Kirk et al 2013 Nucl. Fusion 53 043007). One hypothesis is that the magnetic perturbations cause a three dimensional…