Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Rectified Flows for Fast Multiscale Fluid Flow Modeling

About

Statistical surrogate modeling of fluid flows is hard because dynamics are multiscale and highly sensitive to initial conditions. Conditional diffusion surrogates can be accurate, but usually need hundreds of stochastic sampling steps. We propose a rectified-flow surrogate that learns a time-dependent conditional velocity field transporting input-to-output laws along near-straight trajectories. Inference is then a deterministic ODE solve, making each function evaluation more informative: on multiscale 2D benchmarks, we match diffusion-class posterior statistics with only (8) ODE steps versus (\ge 128) for score-based diffusion. Theoretically, we give a law-level analysis for conditional PDE forecasting. We (i) connect one-point Wasserstein field metrics to the (k=1) correlation-marginal perspective in statistical solutions, (ii) derive a one-step error split into a **coverage** term (high-frequency tail, controlled by structure functions/spectral decay) and a **fit** term (controlled by the training objective), and (iii) show that rectification-time **straightness** controls ODE local truncation error, yielding practical step-size/step-count guidance. Motivated by this, we introduce a curvature-aware sampler that uses an EMA straightness proxy to adapt blending and step sizes at inference. Across incompressible and compressible multiscale 2D flows, it matches diffusion baselines in Wasserstein statistics and spectra, preserves fine-scale structure beyond MSE surrogates, and significantly reduces inference cost.

Victor Armegioiu, Yannick Ramic, Siddhartha Mishra• 2025

Related benchmarks

TaskDatasetResultRank
Solving PDEBurgers
Relative Error2.76
24
Forward PDE solvingNavier-Stokes
Relative L2 Error1.4
15
Forward PDE solvingPoisson
Relative L2 Error1.58
15
Forward PDE solving1D Burgers' equation standard synthetic (test)
Relative L2 Error0.0276
10
Forward PDE solvingHYCOM
Relative L2 Error31.8
10
Inverse PDE solvingDarcy
Relative L2 Error36.95
10
Forward PDE solvingDarcy
Relative L2 Error0.71
9
Showing 7 of 7 rows

Other info

Follow for update