English

Multiscale Neural Operator: Learning Fast and Grid-independent PDE Solvers

Machine Learning 2022-07-26 v1 Artificial Intelligence Computational Engineering, Finance, and Science Distributed, Parallel, and Cluster Computing

Abstract

Numerical simulations in climate, chemistry, or astrophysics are computationally too expensive for uncertainty quantification or parameter-exploration at high-resolution. Reduced-order or surrogate models are multiple orders of magnitude faster, but traditional surrogates are inflexible or inaccurate and pure machine learning (ML)-based surrogates too data-hungry. We propose a hybrid, flexible surrogate model that exploits known physics for simulating large-scale dynamics and limits learning to the hard-to-model term, which is called parametrization or closure and captures the effect of fine- onto large-scale dynamics. Leveraging neural operators, we are the first to learn grid-independent, non-local, and flexible parametrizations. Our \textit{multiscale neural operator} is motivated by a rich literature in multiscale modeling, has quasilinear runtime complexity, is more accurate or flexible than state-of-the-art parametrizations and demonstrated on the chaotic equation multiscale Lorenz96.

Keywords

Cite

@article{arxiv.2207.11417,
  title  = {Multiscale Neural Operator: Learning Fast and Grid-independent PDE Solvers},
  author = {Björn Lütjens and Catherine H. Crawford and Campbell D Watson and Christopher Hill and Dava Newman},
  journal= {arXiv preprint arXiv:2207.11417},
  year   = {2022}
}

Comments

Presented at International Conference on Machine Learning Workshop AI for Science, 2022

R2 v1 2026-06-25T01:09:53.720Z