TokEye: Fast Signal Extraction for Fluctuating Time Series via Offline Self-Supervised Learning From Fusion Diagnostics to Bioacoustics

TL;DR

TokEye is a fast, self-supervised framework that automates extraction of modes from noisy, high-dimensional time series data in fusion and other fields, enabling real-time analysis and large-scale database creation.

Contribution

It introduces a novel self-supervised signal extraction method with a neural network surrogate for rapid, real-time mode identification across multiple diagnostics in fusion devices.

Findings

Achieves 0.5s inference latency for real-time mode detection

Successfully applied to data from DIII-D, TJ-II, and non-fusion spectrograms

Enables automated large-scale database generation for plasma control

Abstract

Next-generation fusion facilities like ITER face a "data deluge," generating petabytes of multi-diagnostic signals daily that challenge manual analysis. We present a "signals-first" self-supervised framework for the automated extraction of coherent and transient modes from high-noise time-frequency data across a variety of sensors. We also develop a general-purpose method and tool for extracting coherent, quasi-coherent, and transient modes for fluctuation measurements in tokamaks by employing non-linear optimal techniques in multichannel signal processing with a fast neural network surrogate on fast magnetics, electron cyclotron emission, CO2 interferometers, and beam emission spectroscopy measurements from DIII-D. Results are tested on data from DIII-D, TJ-II, and non-fusion spectrograms. With an inference latency of 0.5 seconds, this framework enables real-time mode identification and large-scale automated database generation for advanced plasma control. Repository is in https://github.com/PlasmaControl/TokEye.