Related papers: Machine learning for analysis of plasma driven Ion…
Neural networks can be used to identify phases and phase transitions in condensed matter systems via supervised machine learning. Readily programmable through modern software libraries, we show that a standard feed-forward neural network…
In the past three decades, the development of nuclear physics facilities for fundamental and applied science purposes has required an increasing current of multicharged ion beams. Multiple ionization implies the formation of dense and…
A deep neural network (NN) is used to simultaneously detect laser beams in images and measure their center coordinates, radii and angular orientations. A dataset of images containing simulated laser beams and a dataset of images with…
Simulating the dynamics of ions near polarizable nanoparticles (NPs) using coarse-grained models is extremely challenging due to the need to solve the Poisson equation at every simulation timestep. Recently, a molecular dynamics (MD) method…
Ion extraction from DECRIS-PM source is simulated by using initial distributions of ions at the extraction aperture obtained with NAM-ECRIS code. Three-dimensional calculations of plasma emissive surface are done and ions are traced in the…
Ion acceleration driven by superintense laser pulses is attracting an impressive and steadily increasing effort. Motivations can be found in the potential for a number of foreseen applications and in the perspective to investigate novel…
Confined ion transport is involved in nanoporous ionic systems. However, it is challenging to mechanistically predict its electrical characteristics for rational system design and performance evaluation using electrical circuit model due to…
Sealed neutron tubes have a wide range of applications, and the ion source is their core component. Penning ion sources commonly suffer from issues such as uneven magnetic field distribution and a low proportion of monoatomic ions.…
Low-energy investigations on rare ion beams are often limited by the available intensity and purity of the ion species in focus. Here, we present the first application of a technique that combines in-flight production at relativistic…
We apply machine learning techniques in an attempt to predict and classify stellar properties from noisy and sparse time series data. We preprocessed over 94 GB of Kepler light curves from MAST to classify according to ten distinct physical…
Field ion microscopy (FIM) allows to image individual surface atoms by exploiting the effect of an intense electric field. Widespread use of atomic resolution imaging by FIM has been hampered by a lack of efficient image processing/data…
Nuclear materials are often demanded to function for extended time in extreme environments, including high radiation fluxes and transmutation, high temperature and temperature gradients, stresses, and corrosive coolants. They also have a…
With the rise of deep learning, there has been renewed interest within the process industries to utilize data on large-scale nonlinear sensing and control problems. We identify key statistical and machine learning techniques that have seen…
Neural simulation-based inference is a powerful class of machine-learning-based methods for statistical inference that naturally handles high-dimensional parameter estimation without the need to bin data into low-dimensional summary…
Ion beam has been used in cancer treatment, and has a unique preferable feature to deposit its main energy inside a human body so that cancer cell could be killed by the ion beam. However, conventional ion accelerator tends to be huge in…
Statistical learning algorithms are finding more and more applications in science and technology. Atomic-scale modeling is no exception, with machine learning becoming commonplace as a tool to predict energy, forces and properties of…
Multi-dimensional particle-in-cell simulations are used to study the generation of electrostatic shocks in plasma and the reflection of background ions to produce high-quality and high-energy ion beams. Electrostatic shocks are driven by…
Neural network models of real-world systems, such as industrial processes, made from sensor data must often rely on incomplete data. System states may not all be known, sensor data may be biased or noisy, and it is not often known which…
We demonstrate how deep convolutional neural networks can be trained to predict 2+1 D hydrodynamic simulation results for flow coefficients, mean-transverse-momentum and charged particle multiplicity from the initial energy density profile.…
A method for correcting smearing effects using machine learning technique is presented. Compared to the standard deconvolution approaches in high energy particle physics, the method can use more than one reconstructed variable to predict…