Related papers: Deep Learning Analysis of Ions Accelerated at Shoc…
Fusion-graded plasmas are one of the physically complex systems, resulting in continuous establishment of plasma theories for unclarified physical phenomena in order to thoroughly control nuclear fusion reactors. Deep learning has drawn…
This work presents predictive hydrodynamic simulations empowered by artificial intelligence (AI) for laser driven implosion experiments, taking the double-cone ignition (DCI) scheme as an example. A Transformer-based deep learning model…
Ion acceleration due to the interaction between a short high-intensity laser pulse and a moderately overdense plasma target is studied using Eulerian Vlasov-Maxwell simulations. The effects of variations in the plasma density profile and…
Building on the notion of a particle physics detector as a camera and the collimated streams of high energy particles, or jets, it measures as an image, we investigate the potential of machine learning techniques based on deep learning…
Developing efficient and accurate algorithms for chemistry integration is a challenging task due to its strong stiffness and high dimensionality. The current work presents a deep learning-based numerical method called DeepCombustion0.0 to…
The simulation of ion-atom collisions remains a formidable challenge due to the complex interplay between electronic and nuclear degrees of freedom. We present a hybrid quantum-classical computing framework for simulating time-dependent…
The National Ignition Facility has recently achieved successful burning plasma and ignition using the inertial confinement fusion (ICF) approach. However, there are still many fundamental physics phenomena that are not well understood,…
Collisionless shock waves, found in supernova remnants, interstellar, stellar, and planetary environments, and laboratories, are one of nature's most powerful particle accelerators. This study combines in situ satellite measurements with…
We present the first plasma simulations obtained with the code dHybridR, a hybrid particle-in-cell code with fluid electrons and both thermal and energetic ions that retain relativistic dynamics. dHybridR is constructed to study…
Quantum materials research requires co-design of theory with experiments and involves demanding simulations and the analysis of vast quantities of data, usually including pattern recognition and clustering. Artificial intelligence is a…
An experimental investigation of collisionless shock ion acceleration is presented using a multicomponent plasma and a high-intensity picosecond duration laser pulse. Protons are the only accelerated ions when a near-critical-density plasma…
Colliding collisionless shocks appear in a great variety of astrophysical phenomena and are thought to be possible sources of particle acceleration in the Universe. To investigate the detailed dynamics of this phenomenon, we have performed…
The Coulomb logarithm often enters various plasma models and simulation methods for computing the transport and relaxation properties of plasmas. Traditionally, a classical pair collision picture was used to calculate the Coulomb logarithm…
We present a fast simulation application based on a Deep Neural Network, designed to create large analysis-specific datasets. Taking as an example the generation of W+jet events produced in sqrt(s)= 13 TeV proton-proton collisions, we train…
This research was motivated by the recent observations indicating very strong magnetic fields at some supernova remnant shocks, which suggests in-situ generation of magnetic turbulence. The dissertation presents a numerical model of…
Based on deep neural networks (DNNs), deep learning has been successfully applied to many problems, but its mechanism is still not well understood -- especially the reason why over-parametrized DNNs can generalize. A recent statistical…
Plasma processes close to SNR shocks result in the amplification of magnetic fields and in the acceleration of electrons, injecting them into the diffusive acceleration mechanism. The acceleration of electrons and the B field amplification…
We present our progress on the application of physics informed deep learning to reservoir simulation problems. The model is a neural network that is jointly trained to respect governing physical laws and match boundary conditions. The…
This paper presents a convolutional neural network (CNN)-based deep learning model, inspired from UNet with series of encoder and decoder units with skip connections, for the simulation of microwave-plasma interaction. The microwave…
A kinetic approach for the evolution of ultracold neutral plasmas including interionic correlations and the treatment of ionization/excitation and recombination/deexcitation by rate equations is described in detail. To assess the…