datamatters24/orbital-chaos-nasa-ssc

---
license: mit
task_categories:
- time-series-forecasting
language:
- en
tags:
- orbital-mechanics
- space-weather
- iss
- nasa
- solar-wind
- geomagnetic
- spacecraft
size_categories:
- 1M<n<10M
---

# Orbital Chaos — NASA SSC Spacecraft Position Dataset

4.8 million spacecraft position records paired with solar wind measurements, covering 2023–2025 at 1-minute resolution. Built to support machine learning research on orbital prediction under varying space weather conditions.

## Dataset Contents

| Spacecraft | Orbit Type | Records | Purpose |
|---|---|---|---|
| ISS | LEO ~408 km | 1.58M | Primary prediction target |
| DSCOVR | L1 Lagrange | 131K | Solar wind leading indicator |
| MMS-1 | Highly elliptical | 1.54M | Magnetosphere reference |

## Features

**Orbital:** XYZ position (km), velocity components, altitude, orbital period

**Solar Wind (OMNI Database):**
- Interplanetary magnetic field (IMF) Bx, By, Bz components
- Solar wind flow speed and proton density
- Kp geomagnetic index
- Dst index (storm intensity measure)

**Key:** Solar wind measured at L1 arrives at Earth ~45 minutes later — providing a natural leading indicator for atmospheric drag perturbations.

## Why This Dataset

Standard orbital propagation tools (SGP4) use static atmospheric models that fail during geomagnetic storms. When the Sun fires a coronal mass ejection, the upper atmosphere heats and expands — creating extra drag that SGP4 cannot predict. During the severe May 2024 storm (Dst = -406 nT), prediction errors spiked significantly across all standard tools.

This dataset enables training models that learn the relationship between upstream solar wind conditions and resulting orbital perturbations.

## Data Sources

- **Spacecraft positions:** NASA Satellite Situation Center (SSC) Web Services
- **Solar wind:** OMNI High Resolution Data (NASA/GSFC)
- **Format:** Parquet, compatible with HuggingFace Datasets, Dask, Polars

## Usage

```python
from datasets import load_dataset

ds = load_dataset("datamatters24/orbital-chaos-nasa-ssc")
iss_data = ds.filter(lambda x: x["spacecraft"] == "ISS")
```