TIDE: A Physically Diverse 3D Turbulence Benchmark Dataset for Advancing Scientific Machine Learning
physics.flu-dyn, cs.LG
Submitted: 2026-08-04
Updated: 2026-11-10
Code: https://github.com/Dyloong1/TIDE-dataset-benchmark
Terminology
Sources
- A data free neural operator enabling fast inference of 2D and 3D Navier Stokes equations
- PEST: Physics-Enhanced Swin Transformer for 3D Turbulence Simulation
- Flow Learners for PDEs: Toward a Physics-to-Physics Paradigm for Scientific Computing
- Learning PDE Solvers with Physics and Data: A Unifying View of Physics-Informed Neural Networks and Neural Operators
- FlowRefiner: Flow Matching-Based Iterative Refinement for 3D Turbulent Flow Simulation
- Physics-Preserving Latent Compression for Zero-Shot Resolution Transfer in 3D Turbulence
- Datasheets for Datasets
- DPOT: Auto-Regressive Denoising Operator Transformer for Large-Scale PDE Pre-Training
- An Implicit Adaptive Fourier Neural Operator for Long-term Predictions of Three-dimensional Turbulence
- Integrating Fourier Neural Operator with Diffusion Model for Autoregressive Predictions of Three-dimensional Turbulence
- Multi-Grid Tensorized Fourier Neural Operator for High-Resolution PDEs
- Fourier Neural Operator for Parametric Partial Differential Equations
- CFDBench: A Large-Scale Benchmark for Machine Learning Methods in Fluid Dynamics
- Multiple Physics Pretraining for Physical Surrogate Models
- SuperBench: A Super-Resolution Benchmark Dataset for Scientific Machine Learning
- Learned Coarse Models for Efficient Turbulence Simulation
- Solver-in-the-Loop: Learning from Differentiable Physics to Interact with Iterative PDE-Solvers
- Differential-Integral Neural Operator for Long-Term Turbulence Forecasting
- Transolver: A Fast Transformer Solver for PDEs on General Geometries
Related papers
- Data-driven impeller model for efficient large eddy simulations of metastable von K'arm'an flows
- Numerical study of nitrogen oxides chemistry during plasma assisted combustion in a sequential combustor
- Emergent Transfer of a Physics Foundation Model from Simulation to Laboratory Turbulence
- Early onset of secondary shear instability in Kelvin-Helmholtz braids at high Reynolds number
- Rotational covariance, continuous spectrum and non-modal growth of three-dimensional planar weak viscous shock layers
- Deep Learning-based Algebraic Reynolds Stress Closures for RANS Simulations of Turbulent Flows