Related papers: Linac_Gen: integrating machine learning and partic…
In this paper we discuss design considerations and beam dynamics challenges associated with laser-driven plasma-based accelerators as applied to multi-TeV-scale linear colliders. Plasma accelerators provide ultra-high gradients and…
The genomic evolution inherent to cancer relates directly to a renewed focus on the voluminous next generation sequencing (NGS) data, and machine learning for the inference of explanatory models of how the (epi)genomic events are…
We describe some of the challenges of particle accelerator control, highlight recent advances in neural network techniques, discuss some promising avenues for incorporating neural networks into particle accelerator control systems, and…
In order to dissipate long-lived radioactive waste, not only high ux proton accelerator but also electron linac have been proposed. A proton accelerator directly induces nuclear fission and mutation. On the other hand, electron beam has two…
Bayesian Neural Networks (BNNs) provide superior estimates of uncertainty by generating an ensemble of predictive distributions. However, inference via ensembling is resource-intensive, requiring additional entropy sources to generate…
Generative molecular design has moved from proof-of-concept to real-world applicability, as marked by the surge in very recent papers reporting experimental validation. Key challenges in explainability and sample efficiency present…
Accelerators produce too many signals for a small operations team to monitor in real time. In addition, many of these signals are only interpretable by subject matter experts with years of experience. As a result, changes in accelerator…
Large language model (LLM) inference has been a prevalent demand in daily life and industries. The large tensor sizes and computing complexities in LLMs have brought challenges to memory, computing, and databus. This paper proposes a…
Generative models excel in creating realistic images, yet their dependency on extensive datasets for training presents significant challenges, especially in domains where data collection is costly or challenging. Current data-efficient…
Cosmic-ray acceleration processes in astrophysical plasmas are often investigated with fully-kinetic or hybrid kinetic numerical simulations, which enable us to describe a detailed microphysics of particle energization mechanisms. Tracing…
Injected beam energy and energy spread are critical parameters affecting the performance of our rapid cycling synchrotron (RCS). A real-time energy monitoring system is being installed to examine the H- beam out of the Intense Pulsed…
Solving linear systems of polynomial equations is a ubiquitous problem in both mathematics and physics. The standard approach, Gaussian elimination, scales cubically with system size and often constitutes a computational bottleneck. The…
Traditional methods for biological shape inference, such as deep learning (DL) and active contour models, face important limitations in 3D. DL approaches require large annotated datasets, which are often impractical to obtain, while active…
We present the development and integration of a Machine Learning (ML)-based surrogate model, trained on Particle-In-Cell (PIC) simulations of laser-driven plasma wakefield acceleration source of electrons, into Geant4 simulation toolkit.…
Particle accelerators are among some of the largest science experiments in the world and can consist of thousands of components with a wide variety of input ranges. These systems can easily become unwieldy optimization problems during…
The superconducting (SC) High Intensity and Energy (HIE) ISOLDE linac will replace most of the existing accelerating infrastructure of the Radioactive ion beam EXperiment (REX) at CERN, however, the 101.28 MHz RFQ and 5 MV IH cavity will…
Biological function emerges from coupled constraints across sequence, structure, regulation, evolution, and cellular context, yet most foundation models in biology are trained within one modality or for a fixed forward task. We present…
Superconducting linacs are capable of producing intense, stable, high-quality electron beams that have found widespread applications in science and industry. The 9-cell 1.3-GHz superconducting standing-wave accelerating RF cavity originally…
Based on the particle-in-cell (PIC) plasma simulation method, the speed-limited PIC (SLPIC) method delivers faster kinetic plasma simulation in cases where the particle distributions evolve slowly compared with the maximum stable PIC…
We present a topology for linear accelerators (linacs) that permits larger degrees of freedom for the optimization of individual cavity shapes. The power is distributed to the cavities through a waveguide with periodic apertures that…