Tracking blobs in the turbulent edge plasma of a tokamak fusion device

Abstract

The analysis of turbulence in plasmas is fundamental in fusion research. Despite extensive progress in theoretical modeling in the past 15 years, we still lack a complete and consistent understanding of turbulence in magnetic confinement devices, such as tokamaks. Experimental studies are challenging due to the diverse processes that drive the high-speed dynamics of turbulent phenomena. This work presents a novel application of motion tracking to identify and track turbulent filaments in fusion plasmas, called blobs, in a high-frequency video obtained from Gas Puff Imaging diagnostics. We compare four baseline methods (RAFT, Mask R-CNN, GMA, and Flow Walk) trained on synthetic data and then test on synthetic and real-world data obtained from plasmas in the Tokamak à Configuration Variable (TCV). The blob regime identified from an analysis of blob trajectories agrees with state-of-the-art conditional averaging methods for each of the baseline methods employed, giving confidence in the accuracy of these techniques. By making a dataset and benchmark publicly available, we aim to lower the entry barrier to tokamak plasma research, thereby greatly broadening the community of scientists and engineers who might apply their talents to this endeavor.

The role of RF-induced E×B flows in the mitigation of scrape-off-layer convective transport during ion cyclotron resonance heating

“…We then applied a machine learning-based blob tracking algorithm [28] to high-resolution GPI videos in order to directly observe the impact of RF-induced radially-sheared poloidal flows on blob propagation in the SOL. We have shown that these radially sheared flows can slow down, stretch, and destroy the radially moving blobs.…”

“…To study the interaction of these E × B flows with SOL filaments, we apply a newly developed machine learning-based blob tracking algorithm [28] to the GPI data from the two discharges over a time window of 47 ms. Of the four baseline methods implemented, we choose to use the RAFT model, as it was shown to perform best in [28]. In total, the algorithm detects 780 blobs in the case without ICRF and 942 blobs in the case with ICRF.…”

“…In section 3, we demonstrate a method for controlling ICRF-induced E×B flows and establish, for the first time, a correlation between the amplitude of these flows and the mitigation of intermittent fluctuations in the far SOL. In section 4, we use highresolution GPI videos and a novel blob-tracking algorithm [28] to directly observe the process of blob shearing by ICRFinduced flows. Conclusions will be given in section 5.…”

Estimating cross-field particle transport at the outer midplane of TCV by tracking filaments with machine learning

“…The pattern recognition and tracking from images is a wellknown task in ML, and has been implemented for blobtracking in GPI data [17]. Four benchmarked models were trained with synthetic GPI data and two of the models show excellent performance on real GPI data, both in shape prediction and blob regime identification.…”

“…In particular, the contribution of blobs of different sizes to the cross-field particle transport is investigated, as they belong to different turbulent regimes depending on their sizes [7,15]. To obtain the distribution of blob sizes, we use gas puff imaging (GPI) data with our newly developed machine learning (ML) model for blob-tracking [16,17], which tracks the shapes and trajectories of individual blobs frame-by-frame. We used the ML blob-tracking to estimate the cross-field particle transport, assuming that the light emission in the GPI data corresponds to the radial convective motion, and that the far-SOL transport is essentially convective, not diffusive [18].…”