Neural operator transformers capture bifurcating drift wave turbulence in fusion plasma simulations

TL;DR

This paper introduces a transformer-based neural operator surrogate model that accurately emulates complex drift-wave turbulence dynamics in fusion plasma simulations, enabling faster and more robust predictions of plasma behavior.

Contribution

The study presents a novel neural operator model that captures multiscale turbulence bifurcations in plasma, outperforming traditional simulation methods in speed and robustness.

Findings

Accurately predicts turbulence and transition processes over long time horizons.

Robust to out-of-distribution and rare dynamical events.

Enables fast, AI-driven modeling of plasma turbulence.

Abstract

Self-consistent modeling of turbulence-driven transport is critical for optimizing confinement in magnetically confined fusion plasmas, such as in tokamaks and stellarators. In particular, capturing the long-term co-evolution of turbulence, flow, and background plasma profiles remains computationally challenging. Direct numerical simulation of these multiscale, highly nonlinear processes is often demanding and impractical for real-time control or design optimization. To address this bottleneck, we investigate transformer-based neural operator PDE surrogates for emulating the dynamics of drift-wave turbulence bifurcation mediated by zonal flows, using the modified Hasegawa-Wakatani (MHW) model as a prototypical system. We find that the finetuned neural operator model has excellent performance in capturing the multi-spatiotemporal-scales of MHW turbulence bifurcation and is robust to testing on rare and out-of-distribution dynamics. Specifically, we demonstrate that a single unified model accurately predicts both quasi-steady-state turbulence and a wide range of dynamical transition processes, such as nonlinear saturation, spontaneous suppression of turbulence and the emergence of macroscopic zonal flows, over time horizons vastly exceeding the local turbulence correlation time. This computationally efficient approach establishes a strong foundation for fast, AI-based modeling of complex, multiscale phenomena in magnetized fusion plasmas.