An unsupervised machine-learning checkpoint-restart algorithm using Gaussian mixtures for particle-in-cell simulations

TL;DR

This paper introduces an unsupervised machine-learning checkpoint-restart algorithm for particle-in-cell simulations using Gaussian mixtures, achieving high compression with preserved physical properties and minimal impact on simulation fidelity.

Contribution

The paper presents a novel Gaussian mixture-based checkpoint-restart algorithm that conserves charge, momentum, and energy, enabling efficient data compression in particle-in-cell simulations.

Findings

Achieves compression factors over 75 times.

Preserves charge, momentum, and energy during restart.

No significant impact on simulation accuracy.

Abstract

We propose an unsupervised machine-learning checkpoint-restart (CR) lossy algorithm for particle-in-cell (PIC) algorithms using Gaussian mixtures (GM). The algorithm features a particle compression stage and a particle reconstruction stage, where a continuum particle distribution function is constructed and resampled, respectively. To guarantee fidelity of the CR process, we ensure the exact preservation of charge, momentum, and energy for both compression and reconstruction stages, everywhere on the mesh. We also ensure the preservation of Gauss' law after particle reconstruction. As a result, the GM CR algorithm is shown to provide a clean, conservative restart capability while potentially affording orders of magnitude savings in input/output requirements. We demonstrate the algorithm using a recently developed exactly energy- and charge-conserving PIC algorithm on physical problems of interest, with compression factors $\gtrsim75$ with no appreciable impact on the quality of the restarted dynamics.