Related papers: Machine Learning for Electron-Scale Turbulence Mod…
In this study, global nonlinear electromagnetic gyrokinetic simulations are conducted to investigate turbulence in the Internal transport barrier (ITB) region of the EAST tokamak discharge with weakly reversed magnetic shear. Linear…
In this paper we study the efficacy of combining machine-learning methods with projection-based model reduction techniques for creating data-driven surrogate models of computationally expensive, high-fidelity physics models. Such surrogate…
A geometrical method is used for the analysis of stochastic processes in plasma turbulence. Distances between thermodynamic states can be computed according the thermodynamic length methodology which allows the use of a Riemannian metric on…
A systematic study of the impact of impurities on the turbulent heat fluxes is presented for the stellarator Wendelstein 7-X (W7-X) and, for comparison, the Large Helical Device and ITER. By means of nonlinear multispecies gyrokinetic…
We develop a transferable machine learning model which predicts structural relaxation from amorphous supercooled liquid structures. The trained networks are able to predict dynamic heterogeneity across a broad range of temperatures and time…
A combined convolutional autoencoder-recurrent neural network machine learning model is presented to analyse and forecast the dynamics and low-order statistics of the local convective heat flux field in a two-dimensional turbulent…
Computer aided engineering of multi-time-scale plasma systems which exhibit a quasi-steady state solution are challenging due to the large number of time steps required to reach convergence. Machine learning techniques combined with…
H-mode operation of tokamak fusion plasmas free of dangerous Type 1 edge-localized-modes (ELMs) requires a non-ELM mechanism for saturating the edge pedestal growth. One possible mechanism is turbulent transport. We introduce a transport…
A deep neural network was developed for the purpose of predicting thermal conductivity with a case study performed on neutron irradiated nuclear fuel. Traditional thermal conductivity modeling approaches rely on existing theoretical…
A wavelet-based machine learning method is proposed for predicting the time evolution of homogeneous isotropic turbulence where vortex tubes are preserved. Three-dimensional convolutional neural networks and long short-term memory are…
In reactor-relevant plasmas, neoclassical transport drives an outward particle flux in the core of large stellarators and predicts strongly hollow density profiles. However, this theoretical prediction is contradicted by experiments. In…
Machine learning has emerged as a potent computational tool for expediting research and development in solid oxide fuel cell electrodes. The effective application of machine learning for performance prediction requires transforming…
In this article we detail the use of machine learning for spatiotemporally dynamic turbulence model classification and hybridization for the large eddy simulations (LES) of turbulence. Our predictive framework is devised around the…
Machine learning models have emerged as a very effective strategy to sidestep time-consuming electronic-structure calculations, enabling accurate simulations of greater size, time scale and complexity. Given the interpolative nature of…
Reliable prediction of turbulent flows is an important necessity across different fields of science and engineering. In Computational Fluid Dynamics (CFD) simulations, the most common type of models are eddy viscosity models that are…
The scaling of turbulent heat flux with respect to electrostatic potential is examined in the framework of a reduced ($4$D) kinetic system describing electrostatic turbulence in magnetized plasmas excited by the ion temperature gradient…
We present a wall model for large-eddy simulation that incorporates surface-roughness effects and is applicable across low- and high-speed flows, for both transitional and fully rough conditions. The model, implemented using an artificial…
We present a set of neural network models that reproduce the dynamics of electron fluxes in the range of 50 keV $\sim$ 1 MeV in the outer radiation belt. The Outer Radiation belt Electron Neural net model for Medium energy…
Magnetohydrodynamic (MHD) turbulence plays a central role in many astrophysical processes in the interstellar medium (ISM), including star formation and cosmic-ray transport and acceleration. MHD turbulence can be decomposed into three…
The advent of computational material sciences has paved the way for data-driven approaches for modeling and fabrication of materials. The prediction of properties like the glass-forming ability (GFA) by using the variation in alloy…