Improved Surrogates in Inertial Confinement Fusion with Manifold and Cycle Consistencies
This work addresses the need for more reliable and efficient surrogate models in physics simulations like Inertial Confinement Fusion, though it is incremental as it builds on existing neural network methods with added consistency constraints.
The paper tackled the problem of improving surrogate models in Inertial Confinement Fusion by enforcing physical manifold and cyclic consistencies, resulting in surrogates with better predictive performance, resilience to sampling artifacts, and increased data efficiency, as demonstrated on a 1D semi-analytic simulator.
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/