Pith. sign in

REVIEW 2 cited by

Learning to correct spectral methods for simulating turbulent flows

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2207.00556 v2 pith:DRA3ATQZ submitted 2022-07-01 cs.LG physics.flu-dyn

classification cs.LGphysics.flu-dyn
keywords numericalpdeslearningspectralmachinemethodsworkclassical
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Despite their ubiquity throughout science and engineering, only a handful of partial differential equations (PDEs) have analytical, or closed-form solutions. This motivates a vast amount of classical work on numerical simulation of PDEs and more recently, a whirlwind of research into data-driven techniques leveraging machine learning (ML). A recent line of work indicates that a hybrid of classical numerical techniques and machine learning can offer significant improvements over either approach alone. In this work, we show that the choice of the numerical scheme is crucial when incorporating physics-based priors. We build upon Fourier-based spectral methods, which are known to be more efficient than other numerical schemes for simulating PDEs with smooth and periodic solutions. Specifically, we develop ML-augmented spectral solvers for three common PDEs of fluid dynamics. Our models are more accurate (2-4x) than standard spectral solvers at the same resolution but have longer overall runtimes (~2x), due to the additional runtime cost of the neural network component. We also demonstrate a handful of key design principles for combining machine learning and numerical methods for solving PDEs.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 15 citations worldwide. Full citation record

  1. General-domain FC-based shock-dynamics solver II: Non-smooth domains, accuracy and parallel performance

    math.NA 2025-06 conditional novelty 7.0 of 10

    New C1 and C2 corner patches let the FC-SDNN spectral solver treat 2D Euler flows in non-smooth domains, with near-perfect weak scaling to 1620 cores.

  2. Mondrian: Transformer Operators via Domain Decomposition

    cs.LG 2025-06 conditional novelty 5.0 of 10

    Mondrian applies transformer attention to subdomain-restricted functions, decoupling the model from the grid resolution.

Pith tools