# Multimodal Universe: PLAsTiCC Simulated LSST Light Curves

## Facts

- Provider: Multimodal Universe Collaboration (Polymathic AI, UniverseTBD)
- License: CC-BY-4.0 (https://zenodo.org/records/2539456)
- Size: 1,567 files
- Format: PNG, Parquet (in sampled files)
- Stored at: Hugging Face, https://huggingface.co/datasets/UniverseTBD/mmu_plasticc
- Access: public, readable without an account
- Category: Astronomy & Space
- Source: https://arxiv.org/abs/2412.02527
- Page: https://scigantic.com/archive/9b0f54a5-dc16-5c8e-bc5e-41378e177cd8
- Keywords: Astronomy & Space, spectroscopy, time series, PNG, Parquet, Hugging Face

## About

Simulated light curves from PLAsTiCC, the Photometric LSST Astronomical Time-series Classification Challenge, which mimics observations by the Vera C. Rubin Observatory Legacy Survey of Space and Time (LSST), packaged as part of the Multimodal Universe collection of machine-learning-ready astronomical data. The modality is multi-band time series: each of 7,001,476 objects has a light curve of time, flux and flux error per observation in the u, g, r, i, z and Y bands, with host-galaxy photometric and spectroscopic redshifts, true redshift and an object type label (for example SNII, AGN, TDE). The README lists 8 columns in 1,509 HEALPix partitions and 3.9 GiB on disk, and notes that ra and dec are random numbers, not real coordinates. Listing the repository (measured 2026-11-13) shows the main catalog folder mmu_plasticc/ (dataset/, hats.properties, partition_info.csv, point_map.fits), the margin catalog mmu_plasticc_10arcs/ and collection.properties; about 4.1 GB in all. Data are a HATS catalog: Apache Parquet partitioned by HEALPix tile, with a 10 arcsecond margin catalog for cross-matching. Open with LSDB (lsdb.open_catalog on the Hugging Face URL, with cone searches and crossmatch), or read the Parquet with pandas, pyarrow, dask or DuckDB. Uses include photometric transient classification and light-curve representation learning. Part of the Multimodal Universe (arXiv:2412.02527); released under CC-BY-4.0, cite the Multimodal Universe paper and the original survey.

## Load the data

```python
from datasets import load_dataset
ds = load_dataset("UniverseTBD/mmu_plasticc")
print(ds)
```

## Data structure

File types in sampled files: PNG, Parquet

Example file: `mmu_plasticc/dataset/Norder=10/Dir=10580000/Npix=10583404.parquet`

## Open it

- In a hosted notebook with the data mounted: https://scigantic.com/archive/9b0f54a5-dc16-5c8e-bc5e-41378e177cd8
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/9b0f54a5-dc16-5c8e-bc5e-41378e177cd8
- Over MCP: `get_schema_card` with id `9b0f54a5-dc16-5c8e-bc5e-41378e177cd8` at https://api.scigantic.com/mcp

## Related topics

- [Parquet datasets](https://scigantic.com/topics/parquet)
- [Time series datasets](https://scigantic.com/topics/time-series)
- [Astronomy & Space datasets](https://scigantic.com/topics/astronomy-and-space)
- [Spectroscopy datasets](https://scigantic.com/topics/spectroscopy)
- [PNG datasets](https://scigantic.com/topics/png)
