BLASTNetv3: Multiphysics Simulation Dataset
Zenodo (CERN European Organization for Nuclear Research)
Abstract
Go to https://blastnet.github.io/ to access and download this reacting and non-reacting flow physics simulations. Mission BLASTNet is developed to provide researchers in the reacting and non-reacting flow physics communities with high-fidelity simulation datasets in a convenient format for machine learning (ML) applications. This release substantially expands the scale and diversity of the BLASTNet dataset, containing approximately 25 TB of data, 79,475 full-domain samples, and 337 configurations. By providing a large and diverse collection of high-fidelity flow simulations, BLASTNet aims to facilitate the development, evaluation, and fair comparison of ML methods for scientific and engineering applications. Application The dataset is intended for a wide range of ML applications in fluid dynamics and related fields, including automotive, propulsion, energy, and environmental applications. In particular, the data can support research in areas such as turbulent closure modeling, spatio-temporal modeling, surrogate modeling, super-resolution, reduced-order modeling, and inverse modeling. The scale and diversity of this release also make BLASTNet suitable for investigating data-driven scaling behavior, generalization across flow configurations, and the development of foundation models for fluid physics.
Authors 39
-
Affiliation as printed
Stanford University
-
Sandia National Laboratories California
Affiliation as printed
Sandia National Laboratories California
-
Sandia National Laboratories California
Affiliation as printed
Sandia National Laboratories California
-
Lawrence Livermore National Laboratory
Affiliation as printed
Lawrence Livermore National Laboratory
-
Affiliation as printed
Stanford University
-
Affiliation as printed
The University of Melbourne
-
Affiliation as printed
The University of Melbourne
-
Affiliation as printed
Polytechnique Montréal
-
Affiliation as printed
University of Connecticut
-
Affiliation as printed
Stanford University
-
Affiliation as printed
Stanford University
-
Affiliation as printed
Google (United States)
-
Affiliation as printed
Google (United States)
-
Affiliation as printed
Google (United States)
-
Centre Européen de Recherche et de Formation Avancée en Calcul Scientifique
Affiliation as printed
CERFACS
-
Nvidia (United Kingdom) · Nvidia (United States)
Affiliation as printed
NVIDIA
-
Michael Gauding Aachen
Affiliation as printed
RWTH Aachen University
-
Technische Universität Ilmenau
Affiliation as printed
Technische Universität Ilmenau
-
Affiliation as printed
Forschungszentrum Jülich
-
Technische Universität Ilmenau
Affiliation as printed
Technische Universität Ilmenau
-
Affiliation as printed
Stanford University
-
Affiliation as printed
Stanford University
-
Affiliation as printed
Harvard University
-
Affiliation as printed
Google (United States)
-
Georgia Institute of Technology
Affiliation as printed
Georgia Institute of Technology
-
Georgia Institute of Technology
Affiliation as printed
Georgia Institute of Technology
-
Affiliation as printed
University of Houston
-
Affiliation as printed
Kyoto University
-
Affiliation as printed
Kyoto University
-
Affiliation as printed
Kyoto University
-
University at Buffalo, State University of New York
Affiliation as printed
University at Buffalo, State University of New York
-
Embry-Riddle Aeronautical University Worldwide & Online
Affiliation as printed
Embry-Riddle Aeronautical University Worldwide & Online
-
Universitat Politècnica de Catalunya
Affiliation as printed
Universitat Politècnica de Catalunya
-
Universitat Politècnica de Catalunya
Affiliation as printed
Universitat Politècnica de Catalunya
-
Universitat Politècnica de Catalunya
Affiliation as printed
Universitat Politècnica de Catalunya
-
Universitat Politècnica de Catalunya
Affiliation as printed
Universitat Politècnica de Catalunya
-
Otto-von-Guericke-Universität Magdeburg
Affiliation as printed
Otto-von-Guericke-Universität Magdeburg