Related papers: Integration of Machine Learning-Based Plasma Accel…
We explore the possibility of fully replacing a plasma physics kinetic simulator with a graph neural network-based simulator. We focus on this class of surrogate models given the similarity between their message-passing update mechanism and…
Particle transport simulations are a cornerstone of high-energy physics (HEP), constituting a substantial part of the computing workload performed in HEP. To boost the simulation throughput and energy efficiency, GPUs as accelerators have…
We describe a novel technique, based on image compression and machine learning, for transverse phase space tomography in two degrees of freedom in an accelerator beamline. The technique has been used in the CLARA accelerator test facility…
Simulations play a key role for inference in collider physics. We explore various approaches for enhancing the precision of simulations using machine learning, including interventions at the end of the simulation chain (reweighting), at the…
We have investigated numerically the coupling between a 10 \si{MeV} electron bunch of high charge (\SI{> 100}{pc}) with a laser generated accelerating plasma wave. Our results show that a high efficiency coupling can be achieved using a…
The acceleration gradients generated in a laser- or beam-driven plasma wakefield accelerator are typically three orders of magnitude greater than those produced by a conventional accelerator, and hence plasma accelerators can open a route…
The simulation of high-energy physics collision events is a key element for data analysis at present and future particle accelerators. The comparison of simulation predictions to data allows looking for rare deviations that can be due to…
We propose to use tightly focused lasers to generate high quality electron beams in laser wakefield accelerators. In this scheme, the expansion of the laser beam after the focal position enlarges the size of wakefield bubble, which reduces…
Accelerating particles to high energies in plasma wakefields is considered to be a promising technique with good energy efficiency and high gradient. While important progress has been made in plasma-based electron acceleration, positron…
This study focuses on implementing a real-time control system for a particle accelerator facility that performs high energy physics experiments. A critical operating parameter in this facility is beam loss, which is the fraction of…
Machine learning (ML) has emerged as a pervasive tool in science, engineering, and beyond. Its success has also led to several synergies with molecular dynamics (MD) simulations, which we use to identify and characterize the major…
Machine learning (ML) surrogate models are increasingly used in engineering analysis and design to replace computationally expensive simulation models, significantly reducing computational cost and accelerating decision-making processes.…
We demonstrate experimentally the resonant excitation of plasma waves by trains of laser pulses. We also take an important first step to achieving an energy recovery plasma accelerator by showing that unused wakefield energy can be removed…
The photon flux resulting from high-energy electron beam interactions with high field systems, such as in the upcoming FACET-II experiments at SLAC National Accelerator Laboratory, may give deep insight into the electron beam's underlying…
We propose a simple, but efficient and accurate machine learning (ML) model for developing high-dimensional potential energy surface. This so-called embedded atom neural network (EANN) approach is inspired by the well-known empirical…
We propose a hybrid laser-driven ion acceleration scheme using a combination target of a solid foil and a density-tailored background plasma. In the first stage, a sub-relativistic proton beam can be generated by the radiation pressure…
Constructing datasets representative of the target domain is essential for training effective machine learning models. Active learning (AL) is a promising method that iteratively extends training data to enhance model performance while…
Laser wakefield accelerators promise to revolutionise many areas of accelerator science. However, one of the greatest challenges to their widespread adoption is the difficulty in control and optimisation of the accelerator outputs due to…
We propose a preliminary analytical procedure in 4 steps (based on an improved fully relativistic plane hydrodynamic model) to tailor the initial density of a cold diluted plasma to the laser pulse profile so as to control wave-breaking…
An effective theory of laser--plasma based particle acceleration is presented. Here we treated the plasma as a continuous medium with an index of refraction $n_{m}$ in which a single electron propagates. Because of the simplicity of this…