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

2026-03-26

AI Summary

This work addresses the computational challenges of efficiently simulating collisional plasmas governed by the six-dimensional Vlasov–Maxwell–Landau (VML) system by proposing a neural network–driven Spectral-Based Transport Modeling (SBTM) approach. Within a particle-in-cell framework, SBTM learns fractional moments in velocity space online with linear complexity, marking the first integration of neural fractional estimation into the full VML system to accurately approximate the Landau collision operator. The method rigorously preserves momentum and kinetic energy conservation while ensuring correct entropy dissipation, with validation against the global Maxwellian steady state. In benchmark tests—including Landau damping, two-stream instability, and Weibel instability—SBTM achieves higher accuracy and more faithful relaxation dynamics than conventional blob-based methods, while accelerating runtime by 50% and reducing peak memory usage by a factor of four.

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.

Problem

• Vlasov-Maxwell-Landau system
• plasma kinetics
• collisional plasma
• score-based particle method
• computational challenge

Innovation

• score-based transport modeling
• neural particle method
• Vlasov-Maxwell-Landau system
• implicit score matching
• collisional plasma simulation