Improved Surrogates in Inertial Confinement Fusion with Manifold and Cycle Consistencies

Abstract

Neural networks have become very popular in surrogate modeling because of their ability to characterize arbitrary, high dimensional functions in a data driven fashion. This paper advocates for the training of surrogates that are consistent with the physical manifold -- i.e., predictions are always physically meaningful, and are cyclically consistent -- i.e., when the predictions of the surrogate, when passed through an independently trained inverse model give back the original input parameters. We find that these two consistencies lead to surrogates that are superior in terms of predictive performance, more resilient to sampling artifacts, and tend to be more data efficient. Using Inertial Confinement Fusion (ICF) as a test bed problem, we model a 1D semi-analytic numerical simulator and demonstrate the effectiveness of our approach. Code and data are available at https://github.com/rushilanirudh/macc/

10 pages, 6 figures

References in corpus (8)

• Explaining and Harnessing Adversarial Examples
• Physics-Constrained Deep Learning for High-dimensional Surrogate Modeling and Uncertainty Quantification without Labeled Data
• Bayesian Deep Convolutional Encoder-Decoder Networks for Surrogate Modeling and Uncertainty Quantification
• CyCADA: Cycle-Consistent Adversarial Domain Adaptation
• Deep UQ: Learning deep neural network surrogate models for high dimensional uncertainty quantification
• CaloGAN: Simulating 3D High Energy Particle Showers in Multi-Layer Electromagnetic Calorimeters with Generative Adversarial Networks
• Analyzing Inverse Problems with Invertible Neural Networks
• Latent Space Oddity: on the Curvature of Deep Generative Models