Improved surrogates in inertial confinement fusion with manifold and cycle consistencies

Citations Over Time

Abstract

Neural networks have become the method of choice 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 1) consistent with the physical manifold, resulting in physically meaningful predictions, and 2) cyclically consistent with a jointly trained inverse model; i.e., backmapping predictions through the inverse results in the original input parameters. We find that these two consistencies lead to surrogates that are superior in terms of predictive performance, are 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 one-dimensional semianalytic numerical simulator and demonstrate the effectiveness of our approach.

Related Papers

• → On physics-informed data-driven isotropic and anisotropic constitutive models through probabilistic machine learning and space-filling sampling(2022)111 cited
• → Improved Surrogates in Inertial Confinement Fusion with Manifold and Cycle Consistencies(2019)41 cited
• → Gravitational wave surrogates through automated machine learning(2022)13 cited
• → Operator compression with deep neural networks(2022)7 cited
• → Non-intrusive double-greedy parametric model reduction by interpolation of frequency-domain rational surrogates(2021)