Big Data Meets Big Lasers: Controlling Proton Acceleration from Ultra-Intense Laser Interactions
Loading...
Date
2024-05
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
The Ohio State University
Abstract
Ultra-intense laser interactions can be used to generate protons, which have a multitude of potential uses. Attempts have been made in previous studies to apply machine learning methods to predict the resulting proton energies from laser-driven ion acceleration, but they have typically been highly constrained in the amount of data they were able to utilize. By generating a synthetic dataset based on an improved version of a model found in Fuchs et al. [7], we aim to evaluate the performance of machine learning models near the “real-time” threshold of training on more than 1,000 shots per second for kilohertz repetition rate systems. The results of this project are currently being utilized to create an automated system of data acquisition and analysis in a laboratory setting.
Description
Keywords
Big Data, Machine Learning, High-Energy Density Physics, Laser-Matter Interactions