BOOSTR Fermilab Booster Gradient Magnet Power Supply (GMPS) Regulation Time Series, Dec 2019 to Feb 2020 (reduced copy)
- Provider
- Diana Kafkes and Jason St. John (Fermi National Accelerator Laboratory); reduced copy by Emulated Inc
- License
- CC-BY-4.0 (source)
- Size
- 81 files
- Format
- Parquet (in sampled files)
- Stored at
- Hugging Face (https://huggingface.co/datasets/Emulated-Inc/sci-booster-gmps-regulation-forecast)
- Access
- Free and public. No account with the data provider is needed.
- Category
- Physics
- Source
- https://arxiv.org/abs/2101.08359
About this dataset
Cycle-by-cycle control-system time series from the Booster, the 15 Hz rapid-cycling synchrotron at Fermilab, taken from BOOSTR (Booster Operation Optimization Sequential Time-Series for Regression) by Diana Kafkes and Jason St. John. BOOSTR was released to support machine-learning control of the Gradient Magnet Power Supply (GMPS), the power-supply regulation loop of the Booster magnets. This reduced copy keeps 12 of the 55 device series (including B:IMINER, B:VIMIN, B:VIMAX, B:VIPHAS, B:LINFRQ, I:IB and B:ACMNPG) for 2 December 2019 to 18 February 2020, joined on shared Event0C-aligned timestamps (NaN where a device has no reading at a cycle), sorted by time and stored as float32, one Parquet file per UTC day, plus example_windows.parquet with history windows from 16 to 18 February 2020. 79 Parquet files, about 1.4 GB (measured 2026-11-21); read with pandas or polars. Use it for time-series forecasting and reinforcement-learning control of power electronics. CC BY 4.0, as the source Zenodo record (DOI 10.5281/zenodo.4382663); cite Kafkes and St. John, Data 6(4):42 (2021).
How to load this dataset in Python
from datasets import load_dataset
ds = load_dataset("Emulated-Inc/sci-booster-gmps-regulation-forecast")
print(ds)Data structure
File types in sampled files: Parquet
Files
Example file: example_windows.parquet
Analyze this dataset without downloading it
On Scigantic, BOOSTR Fermilab Booster Gradient Magnet Power Supply (GMPS) Regulation Time Series, Dec 2019 to Feb 2020 (reduced copy) opens in a hosted JupyterLab notebook with the data already mounted, so you can read files where they are stored instead of copying them first. Each notebook includes an AI assistant that can see the mounted files and write and run analysis code. Open the dataset page to launch a notebook, or browse the full catalog.
This page is also available as Markdown and as JSON.
Related Physics datasets
- CMS Open Data HH to 4b: Run 2 Collision Data, Hemisphere-Mixed Pseudo-Data and Simulation for Multijet Background Modelling
- The Well: Acoustic Scattering Through Mazes
- NeuralConvection 2D: Boussinesq-to-Compressible Natural Convection Tensors for Fourier Neural Operators (Menglik, Shao, Hyde)
- Tensile2d: 2D Quasi-Static Non-Linear Structural Mechanics under Geometric Variations (PLAID)
- The Well: Active Matter, Rod-like Active Particles in a Stokes Fluid
- TIDE Stratified Turbulence (Buoyancy): 3D Incompressible Navier-Stokes DNS at 256^3 (Dai et al.)
- The Well: Rayleigh-Benard Convection (2D)
- PDEBench 1D Advection Equation Solutions