IllustrisTNG SKIRT SDSS provides preprocessed synthetic galaxy images derived from the IllustrisTNG cosmological simulations. Raw multi-band FITS images were produced with the SKIRT Monte Carlo radiative transfer code in SDSS photometric bands and processed into 128 × 128 RGB images. The dataset, created by HITS-AIN and last updated on 2026-05-07, is designed as training data for the Spherinator/HiPSter framework but is suitable for general-purpose galaxy-morphology tasks.
Use Cases
- Training machine learning models for galaxy morphology classification based on synthetic RGB images.
- Developing generative models for realistic galaxy images based on cosmological simulation data.
- Validating and comparing cosmological simulations against observational data using processed synthetic images.
- Benchmarking computer vision algorithms on standardized 128x128 pixel astronomical images.
Strengths
- Images are derived from the established IllustrisTNG cosmological simulations, providing a physically grounded source.
- Data is preprocessed into a standardized 128 × 128 RGB format ready for machine-learning applications.
- Images are produced using the SKIRT Monte Carlo radiative transfer code, simulating realistic photometric bands.
Limitations
- Description metadata is limited; actual data quality requires manual inspection after download.
- Column-level documentation is absent; field semantics must be inferred after download.
- Row count is unknown, which may limit suitability assessment for large-scale training.
Provenance
- Source
- HITS-AIN via Hugging Face, derived from IllustrisTNG simulations.
- Collection Method
- Synthetic images generated via SKIRT Monte Carlo radiative transfer code from cosmological simulations, then processed.
- Time Range
- null
- Freshness
- Last updated 2026-05-07 14:00:32; freshness should be verified.
- Geography
- null