Using Sparse Gaussian Processes for Predicting Robust Inertial Confinement Fusion Implosion Yields

Abstract

Here we present the application of an advanced Sparse Gaussian Process based machine learning algorithm to the challenge of predicting the yields of inertial confinement fusion (ICF) experiments. The algorithm is used to investigate the parameter space of an extremely robust ICF design for the National Ignition Facility, the `Simplest Design'; deuterium-tritium gas in a plastic ablator with a Gaussian, Planckian drive. In particular we show that i) GPz has the potential to decompose uncertainty on predictions into uncertainty from lack of data and shot-to-shot variation, ii) permits the incorporation of science-goal specific cost-sensitive learning e.g. focussing on the high-yield parts of parameter space and iii) is very fast and effective in high dimensions.

9 pages, 7 figures. Accepted for IEEE Transactions on Plasma Science Special Issue on Machine Learning, Data Science and Artificial Intelligence in Plasma Research

References in corpus (7)

• FPEOS: A First-Principles Equation of State Table of Deuterium for Inertial Confinement Fusion Applications
• GPz: Non-stationary sparse Gaussian processes for heteroscedastic uncertainty estimation in photometric redshifts
• Photometric redshifts for the next generation of deep radio continuum surveys - I: Template fitting
• A Sparse Gaussian Process Framework for Photometric Redshift Estimation
• Improving Photometric Redshift Estimation using GPz: size information, post processing and improved photometry
• The Blind Implosion-Maker - Automated Inertial Confinement Fusion experiment design
• Loss-Calibrated Approximate Inference in Bayesian Neural Networks

Cited by in corpus (6)

• The data-driven future of high energy density physics
• Augmenting machine learning photometric redshifts with Gaussian mixture models
• Exploring Sensitivity of ICF Outputs to Design Parameters in Experiments Using Machine Learning
• Beyond optimization -- supervised learning applications in relativistic laser-plasma experiments
• Optimizing Laser-Plasma Interactions for Ion Acceleration using Particle-in-Cell Simulations and Evolutionary Algorithms
• High-Energy Density Hohlraum Design Using Forward and Inverse Deep Neural Networks