Related papers: Diagnostics for Linac Optimization With Machine Le…

With the increasing brightness of Light sources, including the Diffraction-Limited brightness upgrade of APS and the high-repetition-rate upgrade of LCLS, the proposed experiments therein are becoming increasingly complex. For instance,…

The Proton Improvement Plan-II (PIP-II) [1] has been developed at Fermilab to provide powerful proton beams to the laboratorys experiments. An 800-MeV superconducting linear accelerator-a centerpiece of the project-is currently under…

The KEK 8-GeV electron / 3.5-GeV positron linac has been operated with very different beam specifications for downstream rings, KEKB, PF and PF-AR. For the reliable operation among these beam modes intelligent beam switching and beam…

Machine learning (ML) has become an integral component of high energy physics data analyses and is likely to continue to grow in prevalence. Physicists are incorporating ML into many aspects of analysis, from using boosted decision trees to…

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…

Standard deep learning methods, such as Ensemble Models, Bayesian Neural Networks and Quantile Regression Models provide estimates to prediction uncertainties for data-driven deep learning models. However, they can be limited in their…

This paper presents the first large-scale real-world evaluation for using LiDAR data to guide the mmWave beam prediction task. A machine learning (ML) model that leverages the LiDAR sensory data to predict the current and future beams was…

The linear accelerator (LINAC) at the Los Alamos Neu-tron Science Center (LANSCE) consists of Pre-buncher, Main-Buncher, low-energy beam transport (LEBT), four 201.25-MHz Drift Tube Linacs (DTLs) and forty-four 805-MHz Coupled Cavity Linacs…

Fermilab has developed a novel concept for an industrial electron linac using Nb3Sn coating technology and conduction cooling. These conduction-cooled linacs can generate electron beam energies up to 10 MeV in continuous-wave operation and…

During the recent years of LHC operation, we analysed the situation of beam instrumentation and the need to optimize it for beam-beam studies. The most important beam instrumentation devices will be highlighted and modifications or…

In this work, we demonstrate the deployment of a hardware-accelerated machine learning (ML) inference system integrated into a real-time processing at the DIII-D tokamak fusion reactor. The team has successfully deployed an AMD/Xilinx…

Beam selection for millimeter-wave links in a vehicular scenario is a challenging problem, as an exhaustive search among all candidate beam pairs cannot be assuredly completed within short contact times. We solve this problem via a novel…

Beam steering is the process involving the calibration of the angle and position at which a particle accelerator's electron beam is incident upon the x-ray target with respect to the rotation axis of the collimator. Beam Steering is an…

Laser machining is a highly flexible non-contact manufacturing technique that has been employed widely across academia and industry. Due to nonlinear interactions between light and matter, simulation methods are extremely crucial, as they…

Project-X is the proposed high intensity proton facility to be built at Fermilab, US. Its Superconducting Linac, to be used at first stage of acceleration, will be operated in continuous wave (CW) mode. The Linac is divided into three…

This work proposes a maximum likelihood (ML)-based parameter estimation framework for a millimeter wave (mmWave) integrated sensing and communication (ISAC) system in a multi-static configuration using energy-efficient hybrid digital-analog…

Machine learning models of accelerator systems (`surrogate models') are able to provide fast, accurate predictions of accelerator physics phenomena. However, approaches to date typically do not include measured input diagnostics, such as…

Machine-learning (ML) models in flow cytometry have the potential to reduce error rates, increase reproducibility, and boost the efficiency of clinical labs. While numerous ML models for flow cytometry data have been proposed, few studies…

We outline the design of beam experiments for the electron linac at the Fermilab Accelerator Science and Technology (FAST) facility and for the Integrable Optics Test Accelerator (IOTA), based on synchrotron light emitted by the electrons…

The Linac Coherent Light Source changes configurations multiple times per day, necessitating fast tuning strategies to reduce setup time for successive experiments. To this end, we employ a Bayesian approach to transport optics tuning to…