The Challenge

Inferring magnetic geometry without magnetic diagnostics

A deceptively simple but scientifically rigorous inverse problem — and a probe of how far machine learning can be pushed toward truly machine-agnostic plasma state estimation.

Why this matters

The diagnostics that built tokamak control are about to fail

Magnetic confinement fusion is transitioning from physics-exploration tokamaks to a new generation of reactor-class devices — SPARC, ARC, CFETR — designed to demonstrate net energy gain. These machines will deliver neutron fluxes more than an order of magnitude higher than any existing facility.

In that environment the very diagnostics that have underpinned tokamak control for half a century — Mirnov coils, pickup loops, Rogowski coils mounted near the vessel walls — face severe degradation. Radiation-induced EMF and conductivity produce drift voltages that exceed the signal of interest in long pulses, and structural transmutation slashes sensor lifetime to a fraction of a commercial plant’s operating hours.

The equilibrium-reconstruction problem doesn’t disappear — it becomes more important. Strip the magnetic signals from the classic EFIT code and it loses essentially all of its constraints: the capability we will most demand of next-generation devices is the one our existing toolkit cannot deliver.

Example poloidal flux map ψ(R,Z) with nested magnetic flux surfaces.
A poloidal flux map ψ(R,Z): nested contours are magnetic flux surfaces; the outermost closed surface is the plasma boundary.

“Can machine learning, trained on present-day machines, learn an equilibrium representation that survives the loss of magnetic diagnostics?”

The research question
The task

What you are given, and what you predict

For a held-out shot, you receive non-magnetic diagnostic inputs at every EFIT timestamp and predict the equilibrium.

Inputs (non-magnetic)

  • Coil currents — 18 F-coils, ohmic solenoid (ECOILA) and toroidal-field coil (bcoil) on DIII-D; 10 P-coils, solenoid, toroidal-field (TF) and error-field (EFPS) coils on MAST. 21 signals on DIII-D, 14 on MAST.
  • Thomson scattering — electron temperature Te and density ne profiles (core & edge views).
  • Plasma current Ip.
  • X-point gap dsep — diverted vs. limited indicator.

Outputs (the equilibrium)

  • Full flux map ψ̂(R,Z) on a 65×65 grid.
  • Last closed flux surface (LCFS) contour — the plasma boundary.
  • Five scalars — normalized beta βN, internal inductance li, edge safety factor q95, and the magnetic-axis coordinates (Raxis, Zaxis).
The honest stress test

Cross-machine generalization, not just a train/test split

Comparison of DIII-D conventional D-shaped plasma and MAST spherical kidney-bean plasma cross-sections.
DIII-D’s conventional D-shape vs. MAST’s spherical, low-aspect-ratio geometry.

A second award targets the harder question: train on DIII-D and transfer zero-shot to the topologically distinct MAST. The two machines differ in coil layout, flux geometry, and diagnostics.

Our pilot baseline makes the difficulty explicit: a naïve coil-mapping transfer scores SSIM 0.83 on DIII-D but only 0.10 on MAST. We frame that collapse as a failure on purpose — it is a far more honest measure of generalization than a within-machine split, and a direct test of whether a model captures the universal physics of the Grad–Shafranov equation or merely one device’s engineering minutiae.

Two tracks, one leaderboard

Open and compute-light

Compute-light track

Accessible
Train end-to-end in under two hours on a single GPU or CPU. The reference ridge regression and small CNN fit comfortably. This is a recognition for accessible solutions — for educators and resource-constrained teams — not a quarantine.

Open track

Unconstrained
No compute limits. Transformer-scale models, diffusion approaches, and neural operators are all welcome. Same data, same submission format, same leaderboard as compute-light.
Why it’s useful

Where a learned equilibrium pays off

Diagnostic-loss redundancy

A backup ML reconstruction provides a safe shutdown trajectory when a present-day machine suffers a transient magnetic-sensor failure.

Reactor primary inference

In SPARC and successors, kinetic diagnostics may outlast magnetic ones — making coil-and-profile inference the dominant equilibrium pipeline.

Real-time control

EFIT runs at ~10–100 ms latencies. A learned surrogate could plausibly run at sub-millisecond inference, fast enough for the modes EFIT can’t catch.

Physics interpretation

Kinetic-equilibrium reconstruction already fuses Thomson and magnetic data; this challenge explores the limit where the magnetic terms are removed entirely.