A Neural Score-Based Particle Method for the Vlasov-Maxwell-Landau System

TL;DR

This paper introduces a neural score-based particle method for simulating the Vlasov-Maxwell-Landau system, improving accuracy and efficiency over previous kernel-based methods in plasma modeling.

Contribution

It replaces the kernel-based score estimator with a neural network trained via implicit score matching, achieving better accuracy, stability, and computational efficiency.

Findings

SBTM preserves momentum and energy, dissipates entropy.

Outperforms the blob method in accuracy and long-time relaxation.

Runs 50% faster with 4x lower peak memory on benchmarks.

Abstract

Plasma modeling is central to the design of nuclear fusion reactors, yet simulating collisional plasma kinetics from first principles remains a formidable computational challenge: the Vlasov-Maxwell-Landau (VML) system describes six-dimensional phase-space transport under self-consistent electromagnetic fields together with the nonlinear, nonlocal Landau collision operator. A recent deterministic particle method for the full VML system estimates the velocity score function via the blob method, a kernel-based approximation with $O(n^2)$ cost. In this work, we replace the blob score estimator with score-based transport modeling (SBTM), in which a neural network is trained on-the-fly via implicit score matching at $O(n)$ cost. We prove that the approximated collision operator preserves momentum and kinetic energy, and dissipates an estimated entropy. We also characterize the unique global steady state of the VML system and its electrostatic reduction, providing the ground truth for numerical validation. On three canonical benchmarks -- Landau damping, two-stream instability, and Weibel instability -- SBTM is more accurate than the blob method, achieves correct long-time relaxation to Maxwellian equilibrium where the blob method fails, and delivers $50\%$ faster runtime with $4\times$ lower peak memory.