{"success":true,"data":{"author":"Polymathic AI (The Well); Daniel Fortunato, Flatiron Institute CCM and CCB","bucketAccessType":"public","bucketName":"polymathic-ai/gray_scott_reaction_diffusion","bucketPrefix":"","category":"Physics","cloudProvider":"huggingface","createdAt":"2026-11-14T01:01:19.768Z","description":"2D simulations of the Gray-Scott equations, coupled reaction-diffusion equations for two chemical species A and B whose feed rate f and kill rate k select qualitatively different patterns: gliders, bubbles, mazes, worms, spirals and spots. Solved in MATLAB with Chebfun using a Fourier spectral method in space and ETDRK4 time stepping on a periodic [-1, 1] by [-1, 1] domain; each trajectory has 1,001 time steps of 128 by 128 images to t = 10,000. Fields are the concentrations of A and B. The datasheet lists 1,200 trajectories (6 parameter sets times 200 initial conditions) and flags trajectories that reach a stationary state. Listing data/ (measured 2026-11-13) shows train/ (6 files, 126 GB, one per pattern regime, named by f and k), valid/ and test/ (6 files, 15.9 GB each); about 158 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: Gray-Scott Reaction-Diffusion Turing Patterns","id":"6faf177f-dd95-5a08-86a4-86ff5d51878b","license":"CC-BY-4.0","licenseEvidenceUrl":"https://arxiv.org/html/2412.00568","objectCountEstimate":27,"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/gray_scott_reaction_diffusion\")"},{"language":"python-hub","snippet":"from huggingface_hub import snapshot_download\nsnapshot_download(repo_id=\"polymathic-ai/gray_scott_reaction_diffusion\", repo_type=\"dataset\")"}],"caveats":["HuggingFace metadata: author=polymathic-ai, license:cc-by-4.0, downloads=1943"],"format":"mixed","generatedAt":"2026-11-14T01:01:21.327Z","layout":{"example":"data/test/gray_scott_reaction_diffusion_bubbles_F_0.098_k_0.057.hdf5","pattern":"{repoId}/{filename}"},"mountPath":"/mnt/archive","sampleHeaders":[{"bytes":"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","encoding":"hex","key":"data/test/gray_scott_reaction_diffusion_bubbles_F_0.098_k_0.057.hdf5","truncatedAt":512}],"sampleObjects":["data/stats.yaml","data/test/gray_scott_reaction_diffusion_bubbles_F_0.098_k_0.057.hdf5","data/test/gray_scott_reaction_diffusion_gliders_F_0.014_k_0.054.hdf5","data/test/gray_scott_reaction_diffusion_maze_F_0.029_k_0.057.hdf5","data/test/gray_scott_reaction_diffusion_spirals_F_0.018_k_0.051.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    \"gray_scott_reaction_diffusion\",\n)\ntrain_dataloader = datamodule.train_dataloader()\n\nfor batch in dataloader:\n    # Process training batch\n    ...\n```\n\n# Pattern formation in the Gray-Scott reaction-diffusion equations\n\n**One line description of the data:** Stable Turing patterns emerge from randomness, with drastic qualitative differences in pattern dynamics depending on the equation parameters.\n\n**Longer description of the data:** The Gray-Scott equations are a set of coupled reaction-diffusion equations describing two chemical species, \\\\(A\\\\) and \\\\(B\\\\), whose concentrations vary in space and time. The two parameters \\\\(f\\\\) and \\\\(k\\\\) control the “feed” and “kill” rates in the reaction. A zoo of qualitatively different static and dynamic patterns in the solutions are possible depending on these two parameters. There is a rich landscape of pattern formation hidden in these equations.\n\n**Associated paper**: None.\n\n**Domain expert**: [Daniel Fortunato](https://danfortunato.com/), CCM and CCB, Flatiron Institute.\n\n**Code or software used to generate the data**: [Github repository](https://github.com/danfortunato/spectral-gray-scott) (MATLAB R2023a, using the stiff PDE integrator implemented in Chebfun. The Fourier spectral method is used in space (with nonlinear terms evaluated pseudospectrally), and the exponential time-differencing fourth-order Runge-Kutta scheme (ETDRK4) is used in time.)\n\n**Equation describing the data**\n\n$$\n\\begin{align*}\n\\frac{\\partial A}{\\partial t} &= \\delta_A\\Delta A - AB^2 + f(1-A) \\\\ \\frac{\\partial B}{\\partial t} &= \\delta_B\\Delta B - AB^2 - (f+k)B\n\\end{align*}\n$$\n\nThe dimensionless parameters describing the behavior are: \\\\(f\\\\) the rate at which \\\\(A\\\\) is replenished (feed rate), \\\\(k\\\\) the rate at which \\\\(B\\\\) is removed from the system, and  \\\\(\\delta_A, \\delta_B\\\\) the diffusion coefficients of both species.\n\n\n![Gif](https://users.flatironinstitute.org/~polymathic/data/the_well/datasets/gray_scott_reaction_diffusion/gif/concentration_A_normalized.gif)\n\n| Dataset    | FNO | TFNO  | Unet | CNextU-net\n|:-:|:-:|:-:|:-:|:-:|\n| `gray_scott_reaction_diffusion` | \\\\(\\mathbf{0.1365}\\\\)  | 0.3633 | 0.2252|\\\\(\\mathbf{0.1761}\\\\)|\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:** 1001 time-steps of 128 \\\\(\\times\\\\) 128 images.\n\n**Fields available in the data:** The concentration of two chemical species \\\\(A\\\\) and \\\\(B\\\\).\n\n**Number of trajectories:** 6 sets of parameters, 200 initial conditions per set = 1200.\n\n**Estimated size of the ensemble of all simulations:** 153.8 GB.\n\n**Grid type:** uniform, cartesian coordinates.\n\n**Initial conditions:** Two types of initial conditions generated: random Fourier series and random clusters of Gaussians.\n\n**Boundary conditions:** periodic.\n\n**Simulation time-step:** 1 second.\n\n**Data are stored separated by ( \\\\(\\Delta t\\\\)):** 10 seconds.\n\n**Total time range ( \\\\(t_{min}\\\\) to \\\\(t_{max}\\\\)):** \\\\(t_{min} =0\\\\), \\\\(t_{max} = 10,000\\\\).\n\n**Spatial domain size ( \\\\(L_x\\\\), \\\\(L_y\\\\)):** \\\\([-1,1]\\times[-1,1]\\\\).\n\n**Set of coefficients or non-dimensional parameters evaluated:** All simulations used \\\\(\\delta_u = 2.10^{-5}\\\\) and \\\\(\\delta_v = 1.10^{-5}\\\\).\n\"Gliders\": \\\\(f = 0.014, k = 0.054\\\\). \"Bubbles\": \\\\(f = 0.098, k =0.057\\\\). \"Maze\": \\\\(f= 0.029, k = 0.057\\\\). ","encoding":"utf8","key":"README.md","name":"README.md","size":9070,"truncated":true}],"sourceObjectKey":"data/test/gray_scott_reaction_diffusion_bubbles_F_0.098_k_0.057.hdf5","starterCell":"from huggingface_hub import hf_hub_download\npath = hf_hub_download(repo_id=\"polymathic-ai/gray_scott_reaction_diffusion\", filename=\"data/test/gray_scott_reaction_diffusion_bubbles_F_0.098_k_0.057.hdf5\", repo_type=\"dataset\")\nprint(path)","starterSamplePath":"data/test/gray_scott_reaction_diffusion_bubbles_F_0.098_k_0.057.hdf5","totalObjects":27},"summary":"2D simulations of the Gray-Scott equations, coupled reaction-diffusion equations for two chemical species A and B whose feed rate f and kill rate k select qualitatively different…","title":"The Well: Gray-Scott Reaction-Diffusion Turing Patterns","updatedAt":"2026-11-14T02:43:07.606Z","visibility":"public","websiteUrl":"https://polymathic-ai.org/the_well/"}}