{"success":true,"data":{"author":"Neil Ashton et al. (caemldatasets.org)","bucketAccessType":"public","bucketName":"neashton/drivaerml","bucketPrefix":"","category":"Physics","cloudProvider":"huggingface","createdAt":"2026-11-14T14:15:22.950Z","description":"DrivAerML is a high-fidelity computational fluid dynamics dataset for machine learning in automotive aerodynamics, published by Neil Ashton and colleagues, with the CFD workflow by UpstreamCFD. It contains 500 parametrically morphed variants of the DrivAer notchback generic road car, each simulated with scale-resolving hybrid RANS-LES in OpenFOAM v2212 on industrial-scale unstructured meshes. Measured 2026-11-14, the repository root holds run_N folders plus openfoam_meshes/; each run folder contains the STL and STEP geometry, geometry parameters and reference values (CSV), a boundary VTP surface file with native polygon areas (NPY), volume fields, slice data, time-averaged forces and moments, and images. The publisher lists about 31 TB stored, and 16 run ids are documented as non-public. It is a reference benchmark for surrogate models of surface pressure, wall shear stress, drag and lift (for example in NVIDIA PhysicsNeMo). Open VTP/VTU files with PyVista, VTK or ParaView and CSVs with pandas. Licensed CC-BY-SA-4.0; cite Ashton et al., arXiv:2408.11969.","displayTitle":"DrivAerML: High-Fidelity CFD Dataset for Road-Car External Aerodynamics","id":"773be70e-3808-51cb-a792-e504d5ccb2bb","license":"CC-BY-SA-4.0","licenseEvidenceUrl":"https://caemldatasets.org/drivaerml/","objectCountEstimate":100000,"probeStatus":"ok","referenceUrl":"https://arxiv.org/abs/2408.11969","region":"us","schemaCard":{"accessHints":[{"language":"python-datasets","snippet":"from datasets import load_dataset\nds = load_dataset(\"neashton/drivaerml\")"},{"language":"python-hub","snippet":"from huggingface_hub import snapshot_download\nsnapshot_download(repo_id=\"neashton/drivaerml\", repo_type=\"dataset\")"}],"caveats":["HuggingFace metadata: author=neashton, license:cc-by-sa-4.0, downloads=101724"],"format":"mixed","generatedAt":"2026-11-14T14:15:28.830Z","layout":{"example":"force_mom_all.csv","pattern":"{repoId}/{filename}"},"mountPath":"/mnt/archive","sampleHeaders":[{"bytes":"run,cd,cl,clf,clr,cs\n1,3.035117e-01,6.772802e-02,-3.728616e-02,1.050142e-01,4.766758e-02\n2,2.811713e-01,4.545340e-02,-3.757807e-02,8.303147e-02,3.035559e-03\n3,2.580971e-01,9.539138e-03,-1.214874e-01,1.310265e-01,1.850013e-02\n4,2.882351e-01,4.952113e-02,-8.949596e-02,1.390171e-01,2.848573e-02\n5,2.453419e-01,-4.907301e-02,-9.896183e-02,4.988882e-02,-1.021062e-02\n6,2.646273e-01,-3.842136e-02,-1.275001e-01,8.907874e-02,1.012350e-02\n7,2.659051e-01,-4.953184e-03,-4.644796e-02,4.149477e-02,2.893948e-03\n8,2.950137e","encoding":"utf8","key":"force_mom_all.csv","truncatedAt":512}],"sampleObjects":["force_mom_all.csv","force_mom_constref_all.csv","geo_parameters_all.csv","openfoam_meshes/run_0/0/U","openfoam_meshes/run_0/0/p"],"sidecars":[{"bytes":"Attribution-ShareAlike 4.0 International\n\n=======================================================================\n\nCreative Commons Corporation (\"Creative Commons\") is not a law firm and\ndoes not provide legal services or legal advice. Distribution of\nCreative Commons public licenses does not create a lawyer-client or\nother relationship. Creative Commons makes its licenses and related\ninformation available on an \"as-is\" basis. Creative Commons gives no\nwarranties regarding its licenses, any material licensed under their\nterms and conditions, or any related information. Creative Commons\ndisclaims all liability for damages resulting from their use to the\nfullest extent possible.\n\nUsing Creative Commons Public Licenses\n\nCreative Commons public licenses provide a standard set of terms and\nconditions that creators and other rights holders may use to share\noriginal works of authorship and other material subject to copyright\nand certain other rights specified in the public license below. The\nfollowing considerations are for informational purposes only, are not\nexhaustive, and do not form part of our licenses.\n\n     Considerations for licensors: Our public licenses are\n     intended for use by those authorized to give the public\n     permission to use material in ways otherwise restricted by\n     copyright and certain other rights. Our licenses are\n     irrevocable. Licensors should read and understand the terms\n     and conditions of the license they choose before applying it.\n     Licensors should also secure all rights necessary before\n     applying our licenses so that the public can reuse the\n     material as expected. Licensors should clearly mark any\n     material not subject to the license. This includes other CC-\n     licensed material, or material used under an exception or\n     limitation to copyright. More considerations for licensors:\n    wiki.creativecommons.org/Considerations_for_licensors\n\n     Considerations for the public: By using one of our public\n     licenses, a licensor grants the public permission to use the\n     licensed material under specified terms and conditions. If\n     the licensor's permission is not necessary for any reason--for\n     example, because of any applicable exception or limitation to\n     copyright--then that use is not regulated by the license. Our\n     licenses grant only permissions under copyright and certain\n     other rights that a licensor has authority to grant. Use of\n     the licensed material may still be restricted for other\n     reasons, including because others have copyright or other\n     rights in the material. A licensor may make special requests,\n     such as asking that all changes be marked or described.\n     Although not required by our licenses, you are encouraged to\n     respect those requests where reasonable. More considerations\n     for the public:\n    wiki.creativecommons.org/Considerations_for_licensees\n\n=======================================================================\n\nCreative Commons Attribution-ShareAlike 4.0 International Public\nLicense\n\nBy exercising the Licensed Rights (defined below), You accept and agree\nto be bound by the terms and conditions of this Creative Commons\nAttribution-ShareAlike 4.0 International Public License (\"Public\nLicense\"). To the extent this Public License may be interpreted as a\ncontract, You are granted the Licensed Rights in consideration of Your\nacceptance of these terms and conditions, and the Licensor grants You\nsuch rights in consideration of benefits the Licensor receives from\nmaking the Licensed Material available under these terms and\nconditions.\n\n\nSection 1 -- Definitions.\n\n  a. Adapted Material means material subject to Copyright and Similar\n     Rights that is derived from or based upon the Licensed Material\n     and in which the Licensed Material is translated, altered,\n     arranged, transformed, or otherwise modified in a manner requiring\n     permission under the Copyright and Similar Rights held by the\n     Licensor. For purposes of this Public License, where the Licensed\n     Material is a musical work, p","encoding":"utf8","key":"LICENSE.txt","name":"LICENSE.txt","size":20138,"truncated":true},{"bytes":"---\nviewer: false\nlicense: cc-by-sa-4.0\n---\n\nDrivAerML: High-Fidelity Computational Fluid Dynamics Dataset for Road-Car External Aerodynamics\n-------\n\nContact: \n----------\nNeil Ashton (contact@caemldatasets.org)\n\nWebsite:\n----------\nhttps://caemldatasets.org\n\nSummary:\n-------\n\nMachine Learning (ML) has the potential to revolutionise the field of automotive aerodynamics, enabling split-second flow predictions early in the design process. \nHowever, the lack of open-source training data for realistic road cars, using high-fidelity CFD methods, represents a barrier to their development.\nTo address this, a high-fidelity open-source (CC-BY-SA) public dataset for automotive aerodynamics has been generated, based on 500 parametrically morphed variants of the widely-used DrivAer notchback generic vehicle. Mesh generation and scale-resolving CFD was executed using consistent and validated automatic workflows representative of the industrial state-of-the-art. Geometries and rich aerodynamic data are published in open-source formats. To our knowledge, this is the first large, public-domain dataset for complex automotive configurations generated using high-fidelity CFD. \n\nCFD Solver:\n----------\nAll cases were run using the open-source finite-volume code OpenFOAM v2212 with custom modifications by UpstreamCFD. Please see the paper below for full details on the code and validation:\n\nHow to cite this dataset:\n----------------\nIn order to cite the use of this dataset please cite the paper below which contains full details on the dataset.\n\n''\n@article{ashton2024drivaer,\n    title = {{DrivAerML: High-Fidelity Computational Fluid Dynamics Dataset for Road-Car External Aerodynamics}},\n    year = {2024},\njournal = {arxiv.org},\n    url={https://arxiv.org/abs/2408.11969},\n    author = {Ashton, N., Mockett, C., Fuchs, M., Fliessbach, L., Hetmann, H., Knacke, T., Schonwald, N.,\nSkaperdas, V., Fotiadis, G., Walle, A., Hupertz, B., and Maddix, D}\n}\n''\n\nFiles:\n-------\n\n### Native boundary polygon areas\n\nFor each published `run_N`, `run_N/boundary_cell_area_N.npy` is a one-dimensional little-endian float32 (`<f4`) array with one area in `m^2` per native polygon (and matching `CellData` tuple) of `run_N/boundary_N.vtp`, in its original cell order. It is not valid for an STL, PhysicsNeMo PDMsh, retriangulated mesh, or reordered cells. The method and per-case metadata are in [`surface_cell_areas/`](surface_cell_areas/).\n\n\nEach folder (e.g run1,run2...run\"i\" etc) corresponds to a different geometry that contains the following files where \"i\" is the run number: \n* geometry stl (~135mb): drivaer_i.stl \n* CAD geometry (STEP, millimetres): drivaer_i.step\n* reference values for each geometry: geo_ref_i.csv \n* reference geometry for each geometry: geo_parameters_i.csv \n* Boundary VTU (~500mb): boundary_i.vtp \n* Native boundary polygon cell areas (`m^2`, matching `boundary_i.vtp` `CellData` order): `boundary_cell_area_i.npy`\n* Volume field VTU (~50GB): volume_i.vtu ( please note on HuggingFace this is split into part 1 and part2 - please cat them together to create the volume_i.vtu)\n* forces/moments time-averaged (using varying frontal area/wheelbase): force_mom_i.csv \n* forces/moments time-averaged (using constant frontal area/wheelbase): force_mom_constref_i.csv \n* slices: folder containing .vtp slices in x,y,z that contain flow-field variables \n* Images: This folder contains images of various flow variables (e.g. Cp, CpT, UMagNorm) for slices of the domain at X, Y, and Z locations (M signifies minus, P signifies positive), as well as on the surface. It also includes evaluation plots of the time-averaging of the force coefficients (via the tool MeanCalc) and a residual plot illustrating the convergence.\n\nIn addition to the files per run folder, there are also: \n* openfoam_meshes : this folder contains the OpenFOAM meshes (in OpenFOAM format) used for these simulations. The 0 and system folders are just the default output from ANSA and were not those used in this study. Please refer to the arxiv paper for full details of the CFD setup. We hope that by providin","encoding":"utf8","key":"README.md","name":"README.md","size":10645,"truncated":true}],"sourceObjectKey":"force_mom_all.csv","starterCell":"import pandas as pd\ndf = pd.read_csv(\"hf://datasets/neashton/drivaerml/force_mom_all.csv\")\ndf.head()","starterSamplePath":"force_mom_all.csv","totalObjects":100000},"summary":"DrivAerML is a high-fidelity computational fluid dynamics dataset for machine learning in automotive aerodynamics, published by Neil Ashton and colleagues, with the CFD workflow…","title":"DrivAerML: High-Fidelity CFD Dataset for Road-Car External Aerodynamics","updatedAt":"2026-11-14T17:38:26.791Z","visibility":"public","websiteUrl":"https://caemldatasets.org/drivaerml/"}}