{"success":true,"data":{"author":"Polymathic AI (The Well); Yan-Fei Jiang and Jared Goldberg (Flatiron Institute CCA), Jeff Shen (Princeton)","bucketAccessType":"public","bucketName":"polymathic-ai/convective_envelope_rsg","bucketPrefix":"","category":"Physics","cloudProvider":"huggingface","createdAt":"2026-11-14T01:01:19.153Z","description":"3D radiation hydrodynamic simulations of the turbulent, low-density convective envelope of red supergiant stars, the progenitors of many core-collapse supernovae, computed with Athena++. The grid is spherical, uniform in log r, theta and phi, covering a wedge of the star from about 300 to 6,700 solar radii with dr/r near 0.01; each trajectory has 100 time steps of 256 by 128 by 256 cells. Fields are energy, density, pressure and velocity. The datasheet lists 29 trajectories, which are cuts of one long simulation. Listing data/ (measured 2026-11-13) shows train/ (23 files), valid/ (3 files) and test/ (3 files) of 20.15 GB each, one trajectory per file; about 584 GB in the repository. Files are HDF5 in the common The Well format; open them with the_well package (WellDataModule with base path hf://datasets/polymathic-ai/) or directly with h5py. Part of The Well (Ohana et al., NeurIPS 2024 Datasets and Benchmarks, arXiv:2412.00568); released under CC-BY-4.0, cite The Well and the simulation's source papers.","displayTitle":"The Well: Red Supergiant Convective Envelope (3D Radiation Hydrodynamics)","id":"39c35cbe-70f4-51bf-b937-319eaf2eb803","license":"CC-BY-4.0","licenseEvidenceUrl":"https://arxiv.org/html/2412.00568","objectCountEstimate":38,"probeStatus":"ok","referenceUrl":"https://arxiv.org/abs/2412.00568","region":"us","schemaCard":{"accessHints":[{"language":"python-datasets","snippet":"from datasets import load_dataset\nds = load_dataset(\"polymathic-ai/convective_envelope_rsg\")"},{"language":"python-hub","snippet":"from huggingface_hub import snapshot_download\nsnapshot_download(repo_id=\"polymathic-ai/convective_envelope_rsg\", repo_type=\"dataset\")"}],"caveats":["HuggingFace metadata: author=polymathic-ai, license:cc-by-4.0, downloads=1668"],"format":"mixed","generatedAt":"2026-11-14T01:01:22.668Z","layout":{"example":"data/test/convective_envelope_rsg_trajectories_11.hdf5","pattern":"{repoId}/{filename}"},"mountPath":"/mnt/archive","sampleHeaders":[{"bytes":"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","encoding":"hex","key":"data/test/convective_envelope_rsg_trajectories_11.hdf5","truncatedAt":512}],"sampleObjects":["convective_envelope_rsg.yaml","data/stats.yaml","data/test/convective_envelope_rsg_trajectories_11.hdf5","data/test/convective_envelope_rsg_trajectories_17.hdf5","data/test/convective_envelope_rsg_trajectories_20.hdf5"],"sidecars":[{"bytes":"---\nlanguage:\n- en\nlicense: cc-by-4.0\ntags:\n- physics\n\ntask_categories:\n- time-series-forecasting\n- other\ntask_ids:\n- multivariate-time-series-forecasting\n---\n\nThis Dataset is part of [The Well Collection](https://huggingface.co/papers/2412.00568).\n\n# How To Load from HuggingFace Hub\n\n1. Be sure to have `the_well` installed (`pip install the_well`)\n2. Use the `WellDataModule` to retrieve data as follows:\n\n```python\nfrom the_well.data import WellDataModule\n\n# The following line may take a couple of minutes to instantiate the datamodule\ndatamodule = WellDataModule(\n    \"hf://datasets/polymathic-ai/\",\n    \"convective_envelope_rsg\",\n)\ntrain_dataloader = datamodule.train_dataloader()\n\nfor batch in dataloader:\n    # Process training batch\n    ...\n```\n\n# Red Supergiant Convective Envelope\n\n**One line description of the data:** 3D radiation hydrodynamic simulations of the convective envelope of red supergiant stars.\n\n**Longer description of the data:** Massive stars evolve into red supergiants, which have large radii and luminosities, and low-density, turbulent, convective envelopes. These simulations model the (inherently 3D) convective properties and gives insight into the progenitors of supernovae explosions.\n\n**Associated paper**: [Paper](https://iopscience.iop.org/article/10.3847/1538-4357/ac5ab3).\n\n**Domain experts**: [Yan-Fei Jiang](https://jiangyanfei1986.wixsite.com/yanfei-homepage) (CCA, Flatiron Institute), [Jared Goldberg](https://jaredagoldberg.wordpress.com/) (CCA, Flatiron Institute), [Jeff Shen](https://jshen.net) (Princeton University).\n\n**Code or software used to generate the data**: [Athena++](https://www.athena-astro.app/).\n\n**Equations**\n\n$$\n\\begin{align*}\n\\frac{\\partial\\rho}{\\partial t}+\\mathbf{\\nabla}\\cdot(\\rho\\mathbf{v})&=0\\\\\n\\frac{\\partial(\\rho\\mathbf{v})}{\\partial t}+\\mathbf{\\nabla}\\cdot({\\rho\\mathbf{v}\\mathbf{v}+{{\\sf P_{\\rm gas}}}}) &=-\\mathbf{G}_r-\\rho\\mathbf{\\nabla}\\Phi \\\\\n\\frac{\\partial{E}}{\\partial t}+\\mathbf{\\nabla}\\cdot\\left[(E+ P_{\\rm gas})\\mathbf{v}\\right] &= -c G^0_r -\\rho\\mathbf{v}\\cdot\\mathbf{\\nabla}\\Phi\\\\\n\\frac{\\partial I}{\\partial t}+c\\mathbf{n}\\cdot\\mathbf{\\nabla} I &= S(I,\\mathbf{n})\n\\end{align*}\n$$\n\nwhere\n\n- \\\\(\\rho\\\\) = gas density.\n- \\\\(\\mathbf{v}\\\\) = flow velocity.\n- \\\\({\\sf P_{\\rm gas}}\\\\) = gas pressure tensor.\n- \\\\(P_{\\rm gas}\\\\) = gas pressure scalar.\n- \\\\(E\\\\) = total gas energy density: \\\\(E = E_g + \\rho v^2 / 2\\\\), where \\\\(E_g = 3 P_{\\rm gas} / 2\\\\) = gas internal energy density.\n- \\\\(G^0_r\\\\) and \\\\(\\mathbf{G}_r\\\\) = time-like and space-like components of the radiation four-force.\n- \\\\(I\\\\) = frequency integrated intensity, which is a function of time, spatial coordinate, and photon propagation direction \\\\(\\mathbf{n}\\\\).\n- \\\\(\\mathbf{n}\\\\) = photon propagation direction.\n\n![Gif](https://users.flatironinstitute.org/~polymathic/data/the_well/datasets/convective_envelope_rsg/gif/density_normalized.gif)\n\n|          Dataset          | FNO  |      TFNO       | Unet | CNextU-net |\n| :-----------------------: | :--: | :-------------: | :--: | :--------: |\n| `convective_envelope_rsg` | \\\\(\\mathbf{0.0269}\\\\) | 0.0283 | 0.0555 | 0.0799 |\n\nTable: VRMSE metrics on test sets (lower is better). Best results are shown in bold. VRMSE is scaled such that predicting the mean value of the target field results in a score of 1.\n\n## About the data\n\n**Dimension of discretized data:** 100 time-steps of 256 \\\\(\\times\\\\) 128 \\\\(\\times\\\\) 256 images per trajectory.\n\n**Fields available in the data:** energy (scalar field), density (scalar field), pressure (scalar field), velocity (vector field).\n\n**Number of trajectories:** 29 (they are cuts of one long trajectory, long trajectory available on demand).\n\n**Estimated size of the ensemble of all simulations:** 570 GB.\n\n**Grid type:** spherical coordinates, uniform in \\\\((\\log r, \\theta,\\phi)\\\\). Simulations are done for a portion of a sphere (not the whole sphere), so the simulation volume is like a spherical cake slice.\n\n**Initial and boundary conditions:** The temperature at the inner boundary (IB) is first set to equal that of the appropriate radius ","encoding":"utf8","key":"README.md","name":"README.md","size":8398,"truncated":true}],"sourceObjectKey":"data/test/convective_envelope_rsg_trajectories_11.hdf5","starterCell":"from huggingface_hub import hf_hub_download\npath = hf_hub_download(repo_id=\"polymathic-ai/convective_envelope_rsg\", filename=\"data/test/convective_envelope_rsg_trajectories_11.hdf5\", repo_type=\"dataset\")\nprint(path)","starterSamplePath":"data/test/convective_envelope_rsg_trajectories_11.hdf5","totalObjects":38},"summary":"3D radiation hydrodynamic simulations of the turbulent, low-density convective envelope of red supergiant stars, the progenitors of many core-collapse supernovae, computed with…","title":"The Well: Red Supergiant Convective Envelope (3D Radiation Hydrodynamics)","updatedAt":"2026-11-14T02:49:33.463Z","visibility":"public","websiteUrl":"https://polymathic-ai.org/the_well/"}}