No Free Lunch in Flow Surrogates under Time-Varying Boundary Conditions: A Two-Regime Study
math.NA, cs.LG, cs.NA, physics.flu-dyn
Submitted: 2026-07-26
Updated: 2026-09-24
Terminology
Sources
- AROMA: Preserving Spatial Structure for Latent PDE Modeling with Local Neural Fields
- Fourier Neural Operator for Parametric Partial Differential Equations
- Variational Autoencoding Neural Operators
- Choose a Transformer: Fourier or Galerkin
- GNOT: A General Neural Operator Transformer for Operator Learning
- U-NO: U-shaped Neural Operators
- On the Benefits of Memory for Modeling Time-Dependent PDEs
- What You See is Not What You Get: Neural Partial Differential Equations and The Illusion of Learning
- Neural Emulator Superiority: When Machine Learning for PDEs Surpasses its Training Data
- Recurrent Neural Operators: Stable Long-Term PDE Prediction
- Message Passing Neural PDE Solvers
- PDE-Refiner: Achieving Accurate Long Rollouts with Neural PDE Solvers
- Performance of Neural and Polynomial Operator Surrogates
- On instabilities in neural network-based physics simulators
- Solver-in-the-Loop: Learning from Differentiable Physics to Interact with Iterative PDE-Solvers
- Efficiently Modeling Long Sequences with Structured State Spaces
- On the Parameterization and Initialization of Diagonal State Space Models
- Mamba: Linear-Time Sequence Modeling with Selective State Spaces
- Pointwise Metrics Mislead: An Evaluation Protocol for Multimodal Inverse Problems
- Geometry-Informed Neural Operator for Large-Scale 3D PDEs
Related papers
- Do physics-informed neural networks (PINNs) need to be deep? Shallow PINNs using the Levenberg-Marquardt algorithm
- A Neural-preconditioned Poisson Solver for Mixed Dirichlet and Neumann Boundary Conditions
- Second-order consistency for learning chaotic dynamics via randomized Jacobian matching
- Windowed thinning and query complexity for the bouncy particle and Zigzag samplers
- Data-efficient Kernel Methods for Learning Hamiltonian Systems
- Adjoint Method versus Physics-Informed Neural Networks in PDE-Constrained Inverse Problems