PDEBench 1D Advection Equation Solutions
- Provider
- Makoto Takamoto et al. (NEC Labs Europe, University of Stuttgart)
- License
- CC-BY-4.0 (source)
- Size
- 10 files
- Format
- HDF5 (in sampled files)
- Stored at
- Hugging Face (https://huggingface.co/datasets/pdebench/Advection)
- Access
- Free and public. No account with the data provider is needed.
- DOI
- 10.18419/darus-2986
- Category
- Physics
- Source
- https://arxiv.org/abs/2210.07182
About PDEBench 1D Advection Equation Solutions
PDEBench (Takamoto, Praditia, Leiteritz, MacKinlay, Alesiani, Pfluger and Niepert; NEC Labs Europe and University of Stuttgart, NeurIPS 2022 Datasets and Benchmarks) is a benchmark of numerically simulated partial differential equations for scientific machine learning, used to compare neural operators such as FNO and U-Net and physics-informed networks. This repository holds the 1D linear advection equation solutions, the simplest transport problem in the suite and a test of whether a model can represent pure translation. Measured 2026-11-14, it contains 8 HDF5 files, 1D_Advection_Sols_beta{0.1 to 7.0}.hdf5, one per advection velocity, each about 8.2 GB, about 66 GB in total. Arrays follow the PDEBench convention [batch, time, x, variables] and open with h5py; the PDEBench GitHub repository provides loaders and baselines. The data are published on the University of Stuttgart DaRUS repository (doi:10.18419/darus-2986) under CC-BY-4.0.
How to load PDEBench 1D Advection Equation Solutions in Python
from huggingface_hub import hf_hub_download
path = hf_hub_download(repo_id="pdebench/Advection", filename="1D_Advection_Sols_beta0.1.hdf5", repo_type="dataset")
print(path)Data structure
File types in sampled files: HDF5
Files
Example file: 1D_Advection_Sols_beta0.1.hdf5
Analyze this dataset without downloading it
On Scigantic, PDEBench 1D Advection Equation Solutions opens in a hosted JupyterLab notebook with the data already mounted, so you can read files where they are stored instead of copying them first. Each notebook includes an AI assistant that can see the mounted files and write and run analysis code. Open the dataset page to launch a notebook, or browse the full catalog.
This page is also available as Markdown and as JSON.
Related Physics datasets
- 2D_ElastoPlastoDynamics: Dynamic Non-Linear Structural Mechanics with Non-Local Constitutive Law (PLAID)
- The Well: Turbulent Radiative Mixing Layer (2D)
- AirfRANS (Original Meshes): 2D Airfoil RANS Simulations in PLAID Format
- PhysicsNeMo Datacenter CFD
- The Well: Post Neutron Star Merger Accretion Disk (GR Neutrino Radiation MHD)
- The Well: Turbulence with Gravity and Radiative Cooling in the Interstellar Medium
- PDEBench 1D Burgers' Equation Solutions
- The Well: Compressible MHD Turbulence (64 Cubed)