RDE-72 is the first open dataset of full 2D spatial fields from Rotating Detonation Engine (RDE) CFD simulations. It combines 12 high-fidelity OpenFOAM reactingFoam cases with 60 synthetic cases generated via a Conditional Variational Autoencoder (CVAE). The dataset was authored by SM-Bello and was last updated on Hugging Face in May 2026.
Use Cases
- Train neural surrogate models based on the provided 2D spatial fields from CFD simulations.
- Map the operating envelope of Rotating Detonation Engines based on the combined high-fidelity and synthetic cases.
- Benchmark generative models for synthetic data in fluid dynamics based on the CVAE-generated cases.
- Study spatiotemporal combustion dynamics based on the full 2D spatial field data.
Strengths
- First open dataset providing full 2D spatial fields for RDEs, unlike prior datasets limited to bulk statistics.
- Combines 12 high-fidelity OpenFOAM reactingFoam cases with 60 synthetic cases generated via a CVAE.
- Specifically designed to enable neural surrogate modeling and operating envelope mapping.
Limitations
- Column-level documentation is absent; field semantics must be inferred after download.
- Row count is unknown, which may limit suitability assessment.
- Description metadata is limited; actual data quality requires manual inspection after download.
Provenance
- Source
- SM-Bello on Hugging Face
- Collection Method
- Combines high-fidelity OpenFOAM CFD simulations with synthetic cases generated via a Conditional Variational Autoencoder (CVAE).
- Freshness
- Last updated 2026-05-20 20:00:24; freshness should be verified.