# SuryaBench Solar Wind Forecasting: Hourly OMNI Solar Wind Speed, Density and IMF at L1 (2010-2024)

## Facts

- Provider: NASA-IBM AI4Science (Surya / SuryaBench team); Vishal Upendran (SETI Institute)
- License: CC-BY-4.0 (https://huggingface.co/datasets/nasa-ibm-ai4science/Surya-bench-solarwind)
- Size: 7 files
- Format: CSV, PNG (in sampled files)
- Stored at: Hugging Face, https://huggingface.co/datasets/nasa-ibm-ai4science/Surya-bench-solarwind
- Access: public, readable without an account
- Category: Astronomy & Space
- Source: https://github.com/NASA-IMPACT/Surya
- Page: https://scigantic.com/archive/8743582c-403c-5c04-b41c-f6e08a501dcd
- Keywords: Astronomy & Space, heliophysics, solar wind, benchmark, CSV, PNG, Hugging Face

## About

Hourly solar wind plasma and interplanetary magnetic field (IMF) parameters at the Sun-Earth L1 point, derived from NASA's OMNI dataset and packaged by Vishal Upendran (SETI Institute) as the solar wind task of SuryaBench, the benchmark suite for the NASA-IBM Surya heliophysics foundation model. Each of the 119,225 hourly rows from 13 May 2010 to 31 December 2024 gives solar wind speed V (km/s, the primary forecast target), IMF Bx in GSE and By and Bz in GSM coordinates (nT) and proton number density N (per cubic cm). The task is to forecast near-Earth solar wind speed several days ahead from full-disk SDO EUV and magnetogram observations of coronal holes and active regions, such as the Surya core stack on s3://nasa-surya-bench, or from past in-situ values. CSV splits follow the shared SuryaBench calendar: train.csv (15 February to 31 December of 2010 to 2019), validation.csv (15 to 31 January), leaky_validation.csv (1 to 14 January and 1 to 14 February) and test.csv (2020 to 2024). About 2 MB; load with pandas or Hugging Face datasets. CC-BY-4.0 as stated in the card; cite the OMNI dataset (NASA SPDF) as the source of the measurements.

## Load the data

```python
import pandas as pd
df = pd.read_csv("hf://datasets/nasa-ibm-ai4science/Surya-bench-solarwind/leaky_validation.csv")
df.head()
```

## Data structure

File types in sampled files: CSV, PNG

Example file: `leaky_validation.csv`

## Open it

- In a hosted notebook with the data mounted: https://scigantic.com/archive/8743582c-403c-5c04-b41c-f6e08a501dcd
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/8743582c-403c-5c04-b41c-f6e08a501dcd
- Over MCP: `get_schema_card` with id `8743582c-403c-5c04-b41c-f6e08a501dcd` at https://api.scigantic.com/mcp

## Related topics

- [CSV datasets](https://scigantic.com/topics/csv)
- [Benchmark datasets](https://scigantic.com/topics/benchmark)
- [Astronomy & Space datasets](https://scigantic.com/topics/astronomy-and-space)
- [PNG datasets](https://scigantic.com/topics/png)
- [Heliophysics datasets](https://scigantic.com/topics/heliophysics)
- [Solar wind datasets](https://scigantic.com/topics/solar-wind)
