Get Started

From setup to first submission

Six sample shots, a desktop visualizer, and four reference baselines. Newcomers without fusion expertise can reach a working submission in well under an hour.

The path

Four steps

1 · Install

~2 min
Python with pandas, pyarrow, and plotly. That’s enough to load and plot a shot.

2 · Explore

Visual
Open a sample shot in the dFL desktop visualizer to see flux contours, coil currents, and Thomson profiles interactively.

3 · Model

Baselines
Start from a reference baseline — PCA + Ridge fits in under a tenth of a second.

4 · Submit

Codabench
Package predictions as one .npz per machine and submit to the public leaderboard.
Load a shot

Quickstart

Each Parquet file holds a single shot. The target efit_psirz is a list of 65×65 flux maps — one per efit_times slice. The two golden rules: resample inputs onto EFIT times, and never interpolate the targets.

The starter kit's experiments.py (scikit-learn) and experiments_torch.py (PyTorch) reproduce the baselines end-to-end, and submission_skeleton.py plus validate_submission.py get you from a trained model to a validated submission.

Starter Kit & Baselines (GitHub) Dataset (Hugging Face) 
import pandas as pd
import numpy as np

# One row per shot; every series/profile is a nested array in that row.
df = pd.read_parquet("d3d_shot_203702.parquet")

# Target: a sequence of 65x65 poloidal flux maps, one per EFIT time slice.
psirz  = df["efit_psirz"].iloc[0]     # list of 2D grids
efit_t = np.array(df["efit_times"].iloc[0])   # ms — diverted frames only,
                                              # so NOT evenly spaced

# Input example: an F-coil current (kA-turn) on the shared magnetics clock.
f1a   = np.array(df["magnetics_F1A"].iloc[0])
mag_t = np.array(df["magnetics_time"].iloc[0])

# Resample INPUTS onto EFIT times — never interpolate the targets.
f1a_on_efit = np.interp(efit_t, mag_t, f1a)
See the data

The dFL visualizer

dFL (Data Fusion Labeler) is a cross-platform desktop app for inspecting multi-rate scientific data. Point it at the challenge’s fusion_data_provider.py plugin and it auto-discovers the sample shots, then renders flux contours, Thomson heatmaps, coil currents, and the X-point gap interactively — no fusion background required.

Binaries for Apple Silicon, Windows, and Linux are available from the dFL download page.

Download dFL macOS · Windows · Linux
Reference pipelines

Four baselines, simplest to deepest

All implemented in scikit-learn and PyTorch and released as runnable scripts in the starter kit. Every one trains in under two hours on a single commodity GPU or CPU.

PCA + Ridge

<0.1 s
20-component PCA of training flux maps; RidgeCV maps the 21-dim DIII-D input to PCA coefficients. SSIM 0.84 on the demo set.

PCA + Random Forest

Interpretable
A RandomForestRegressor over the same PCA coefficients captures nonlinear coil coupling, and its feature importances are directly inspectable.

MLP on PCA targets

MSE 0.005
3-layer fully-connected network (~41k params) over PCA coefficients — works with limited data.

Convolutional decoder

~5M params
FC encoder → ConvTranspose2d upsampling to 65×65; demonstrates the capacity-vs-data tradeoff.
Output space matters more than model size. The same MLP scores MSE 0.005 on PCA targets (~41k params) but 0.239 predicting raw pixels (~5M params) on small data. Compress the target first.
Baseline architecture: inputs to PCA-compressed flux coefficients to reconstructed 65x65 map.
A representative baseline: compress the flux map with PCA, regress the coefficients, reconstruct.
Make a submission

Submission format

Package your predictions (flux maps plus q95 and betaN) as .npz files indexed by shot and EFIT timestamp, plus a small manifest.json. You do not submit anything else — the LCFS contour, magnetic axis, shape, volume and li are all derived from your flux map by the scorer. Submit through Codabench, which scores against the hidden test set and updates the leaderboard automatically.

A small manifest.json travels with your predictions, but the scorer finds them by filename — keep the two .npz named exactly as the config names.

Submissions are capped at 5 per day and 100 total per team to discourage leaderboard probing. See Rules & Evaluation for the full scoring breakdown.

Leaderboard & Submission (Codabench) Rules & evaluation →