Beyond optimization—supervised learning applications in relativistic laser-plasma experiments

We explore the applications of a variety of machine learning techniques in relativistic laser-plasma experiments beyond optimization purposes. With the trained supervised learning models, the beam charge of electrons produced in a laser wakefield accelerator is predicted given the laser wavefront ch...

Full description

Saved in:
Bibliographic Details
Published in:Physics of plasmas 2021-08, Vol.28 (8)
Main Authors: Lin, Jinpu, Qian, Qian, Murphy, Jon, Hsu, Abigail, Hero, Alfred, Ma, Yong, Thomas, Alexander G. R., Krushelnick, Karl
Format: Article
Language:English
Subjects:
adaptive optics
Anomalies
artificial neural networks
CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSICS
Data analysis
Deformable mirrors
Error analysis
Formability
Gaussian processes
Genetic algorithms
Laser plasma interactions
Lasers
Machine learning
Optimization
Physics
plasma acceleration
Plasma interactions
Plasma physics
Prediction models
regression analysis
Relativistic effects
statistical analysis
Statistical correlation
Supervised learning
Wave fronts
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We explore the applications of a variety of machine learning techniques in relativistic laser-plasma experiments beyond optimization purposes. With the trained supervised learning models, the beam charge of electrons produced in a laser wakefield accelerator is predicted given the laser wavefront change caused by a deformable mirror. Feature importance analysis using the trained models shows that specific aberrations in the laser wavefront are favored in generating higher beam charges, which reveals more information than the genetic algorithms and the statistical correlation do. The predictive models enable operations beyond merely searching for an optimal beam charge. The quality of the measured data is characterized, and anomaly detection is demonstrated. The model robustness against measurement errors is examined by applying a range of virtual measurement error bars to the experimental data. This work demonstrates a route to machine learning applications in a highly nonlinear problem of relativistic laser-plasma interaction for in-depth data analysis to assist physics interpretation.
ISSN:1070-664X
1089-7674
DOI:10.1063/5.0047940