# GOES and OMNI >2 MeV Geostationary Electron Flux Forecasting Dataset (GOES-14/GOES-16, 2013-2025)

## Facts

- Provider: snowsadh
- License: CC-BY-4.0 (https://huggingface.co/datasets/snowsadh/goes-omni-electron-flux-forecasting)
- Size: 28 files
- Format: PNG, Parquet (in sampled files)
- Stored at: Hugging Face, https://huggingface.co/datasets/snowsadh/goes-omni-electron-flux-forecasting
- Access: public, readable without an account
- Category: Astronomy & Space
- Source: https://huggingface.co/datasets/snowsadh/goes-omni-electron-flux-forecasting
- Page: https://scigantic.com/archive/dc8e2e9c-bdae-5966-8808-fefdf14a1f31
- Keywords: Astronomy & Space, solar wind, weather forecasting, PNG, Parquet, Hugging Face

## About

A space-weather forecasting dataset that combines cross-calibrated NOAA GOES-14 and GOES-16 measurements of >2 MeV electron flux at geostationary orbit (the outer radiation belt "killer electrons" that charge satellites) with NASA/GSFC OMNI solar wind and geomagnetic drivers on a uniform five-minute UTC grid. The scientific-master configuration holds 1,326,459 rows from 2013-05-23 to 2025-12-31 with unscaled source measurements, instrument context, calibration factors and explicit missingness; the ml-ready configuration holds scaled causal features, validity flags, unscaled 30-minute, 6-hour and 12-hour flux targets, and leakage-safe chronological splits (train 2014 to mid-2023, validation to mid-2024, test to April 2025). GOES-14 (EPEAD) and GOES-16 records are spliced in 2017 with MLT-bin cross-calibration; GOES flux ends 2025-04-07. Parquet files load with the Hugging Face datasets library or pandas; DATA_DICTIONARY.md, SOURCES.md and preprocessing_meta.json document fields and provenance. The compiled data are CC BY 4.0 (processing scripts MIT); upstream NOAA and NASA data are public domain.

## Load the data

```python
from datasets import load_dataset
ds = load_dataset("snowsadh/goes-omni-electron-flux-forecasting")
print(ds)
```

## Data structure

File types in sampled files: PNG, Parquet

Example file: `data/ml-ready/test.parquet`

## Open it

- In a hosted notebook with the data mounted: https://scigantic.com/archive/dc8e2e9c-bdae-5966-8808-fefdf14a1f31
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/dc8e2e9c-bdae-5966-8808-fefdf14a1f31
- Over MCP: `get_schema_card` with id `dc8e2e9c-bdae-5966-8808-fefdf14a1f31` at https://api.scigantic.com/mcp

## Related topics

- [Parquet datasets](https://scigantic.com/topics/parquet)
- [Astronomy & Space datasets](https://scigantic.com/topics/astronomy-and-space)
- [PNG datasets](https://scigantic.com/topics/png)
- [Weather forecasting datasets](https://scigantic.com/topics/weather-forecasting)
- [Solar wind datasets](https://scigantic.com/topics/solar-wind)
