# NeuralConvection 3D: Boussinesq-to-Compressible Natural Convection in a Cube for Fourier Neural Operators (Menglik, Shao, Hyde)

## Facts

- Provider: Nurshat Menglik, Alex Shao, David Hyde
- License: CC-BY-4.0 (https://huggingface.co/datasets/NurshatMenglik/NeuralConvection_3D_TrainTest)
- Size: 24 files
- Format: CSV (in sampled files)
- Stored at: Hugging Face, https://huggingface.co/datasets/NurshatMenglik/NeuralConvection_3D_TrainTest
- Access: public, readable without an account
- Category: Physics
- Source: https://arxiv.org/abs/2606.25259
- Page: https://scigantic.com/archive/cea88f73-970b-5c63-ae48-826e7e7cd7ec
- Keywords: Physics, CSV, Hugging Face

## About

Training and test tensors for the 3D Fourier Neural Operator (FNO) surrogate in "A Neural Surrogate Approach for Simulating Natural Convection Problems" (Menglik, Shao and Hyde, arXiv:2606.25259). Each pair maps a steady Boussinesq natural-convection (buoyancy-driven) field in the unit cube to the fully compressible field for the same randomized wall-temperature problem, both solved on one 24-cubed mesh. X.pt and Y.pt are float32 PyTorch tensors of shape (N, 5, 24, 24, 24) with channels u_x, u_y, u_z, temperature and pressure, axes (x, y, z) and gravity along -y. Splits: train (1,000 samples with 2 to 5 Voronoi cells of wall temperature per active wall, with a 900/100 train/validation split file), test_in_distribution (50), test_ood (50, 6 to 9 Voronoi cells per wall) and test_legacy (50 classical hot/cold side-wall cubes). Rayleigh number runs from 1e2 to 1e5, the range where this grid reproduces reference Nusselt numbers within one percent, with Prandtl number 0.71; both members share buoyancy (free-fall) units. per_sample.csv and MANIFEST.json record parameters and conventions; flagged_samples.json lists 24 low-Ra pairs with solver drift. Load with torch.load. Released under CC BY 4.0; cite arXiv:2606.25259.

## Load the data

```python
import pandas as pd
df = pd.read_csv("hf://datasets/NurshatMenglik/NeuralConvection_3D_TrainTest/test_in_distribution/per_sample.csv")
df.head()
```

## Data structure

File types in sampled files: CSV

Example file: `test_in_distribution/per_sample.csv`

## Open it

- In a hosted notebook with the data mounted: https://scigantic.com/archive/cea88f73-970b-5c63-ae48-826e7e7cd7ec
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/cea88f73-970b-5c63-ae48-826e7e7cd7ec
- Over MCP: `get_schema_card` with id `cea88f73-970b-5c63-ae48-826e7e7cd7ec` at https://api.scigantic.com/mcp

## Related topics

- [CSV datasets](https://scigantic.com/topics/csv)
- [Physics datasets](https://scigantic.com/topics/physics)
