# BOOSTR Fermilab Booster Gradient Magnet Power Supply (GMPS) Regulation Time Series, Dec 2019 to Feb 2020 (reduced copy)

## Facts

- Provider: Diana Kafkes and Jason St. John (Fermi National Accelerator Laboratory); reduced copy by Emulated Inc
- License: CC-BY-4.0 (https://zenodo.org/records/4382663)
- Size: 81 files
- Format: Parquet (in sampled files)
- Stored at: Hugging Face, https://huggingface.co/datasets/Emulated-Inc/sci-booster-gmps-regulation-forecast
- Access: public, readable without an account
- Category: Physics
- Source: https://arxiv.org/abs/2101.08359
- Page: https://scigantic.com/archive/819106e0-9034-56c0-88f4-fed4568047e2
- Keywords: Physics, time series, Parquet, Hugging Face

## About

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).

## Load the data

```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

Example file: `example_windows.parquet`

## Open it

- In a hosted notebook with the data mounted: https://scigantic.com/archive/819106e0-9034-56c0-88f4-fed4568047e2
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/819106e0-9034-56c0-88f4-fed4568047e2
- Over MCP: `get_schema_card` with id `819106e0-9034-56c0-88f4-fed4568047e2` at https://api.scigantic.com/mcp

## Related topics

- [Parquet datasets](https://scigantic.com/topics/parquet)
- [Time series datasets](https://scigantic.com/topics/time-series)
- [Physics datasets](https://scigantic.com/topics/physics)
