Student or educator? Sign up with your school email and get 6 months of Pro free.
Cited by 514

The DOI matches its Crossref record; 45 of the 45 references it cites were found in a registry or an index.

A comprehensive and fair comparison of two neural operators (with practical extensions) based on FAIR data

Open access
Lu, Lu, Meng, Xuhui, Cai, Shengze, Mao, Zhiping, Goswami, Somdatta, Zhang, Zhongqiang, Karniadakis, George Em · 2022 · Computer Methods in Applied Mechanics and Engineering

Abstract

Neural operators can learn nonlinear mappings between function spaces and offer a new simulation paradigm for real-time prediction of complex dynamics for realistic diverse applications as well as for system identification in science and engineering. Herein, we investigate the performance of two neural operators, which have shown promising results so far, and we develop new practical extensions that will make them more accurate and robust and importantly more suitable for industrial-complexity applications. The first neural operator, DeepONet, was published in 2019 (Lu et al., 2019), and its original architecture was based on the universal approximation theorem of Chen & Chen (1995). The second one, named Fourier Neural Operator or FNO, was published in 2020, and it is based on parameterizing the integral kernel in the Fourier space. DeepONet is represented by a summation of products of neural networks (NNs), corresponding to the branch NN for the input function and the trunk NN for the output function; both NNs are general architectures, e.g., the branch NN can be replaced with a CNN or a ResNet. According to Kovachki et al. (2021), FNO in its continuous form can be viewed conceptually as a DeepONet with a specific architecture of the branch NN and a trunk NN represented by a trigonometric basis. In order to compare FNO with DeepONet computationally for realistic setups, we develop several extensions of FNO that can deal with complex geometric domains as well as mappings where the input and output function spaces are of different dimensions. We also develop an extended DeepONet with special features that provide inductive bias and accelerate training, and we present a faster implementation of DeepONet with cost comparable to the computational cost of FNO, which is based on the Fast Fourier Transform. Here we consider 16 different benchmarks to demonstrate the relative performance of the two neural operators, including instability wave analysis in hypersonic boundary layers, prediction of the vorticity field of a flapping airfoil, porous media simulations in complex-geometry domains, etc. We follow the guiding principles of FAIR (Findability, Accessibility, Interoperability, and Reusability) for scientific data management and stewardship. The performance of DeepONet and FNO is comparable for relatively simple settings, but for complex geometries the performance of FNO deteriorates greatly. We also compare theoretically the two neural operators and obtain similar error estimates for DeepONet and FNO under the same regularity assumptions.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1016/j.cma.2022.114778

Cites

45 of 45 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 45 references

Research works printed but not linked: 8

  1. You, 2021, Nonlocal kernel network (NKN): a stable and resolution-independent deep neural network, Preprint
  2. Lin, 2021, Operator learning for predicting multiscale bubble growth dynamics, J. Chem. Phys., 154, 10.1063/5.0041203 · DOI
  3. Lin, 2021, A seamless multiscale operator neural network for inferring bubble dynamics, J. Fluid Mech., 929, 10.1017/jfm.2021.866 · doi:10.1017/jfm.2021.866
  4. Opschoor, 2021, Exponential reLU DNN expression of holomorphic maps in high dimension, Constr. Approx.
  5. Wang, 2009, High-order well-balanced schemes and applications to non-equilibrium flow, J. Comput. Phys., 228, 6682, 10.1016/j.jcp.2009.05.028 · doi:10.1016/j.jcp.2009.05.028
  6. Zhang, 2011, Positivity-preserving high order discontinuous Galerkin schemes for compressible Euler equations with source terms, J. Comput. Phys., 230, 1238, 10.1016/j.jcp.2010.10.036 · doi:10.1016/j.jcp.2010.10.036
  7. Meng, 2015, Multiple-relaxation-time lattice Boltzmann model for incompressible miscible flow with large viscosity ratio and high Péclet number, Phys. Rev. E, 92, 10.1103/PhysRevE.92.043305 · doi:10.1103/physreve.92.043305
  8. Guo, 2002, Non-equilibrium extrapolation method for velocity and pressure boundary conditions in the lattice Boltzmann method, Chin. Phys., 11, 366, 10.1088/1009-1963/11/4/310 · doi:10.1088/1009-1963/11/4/310

Cited by

See all 514

Metadata

Authors
Lu, L., Meng, X., Cai, S., Mao, Z., Goswami, S., Zhang, Z., & Karniadakis, G. E.
Venue
Computer Methods in Applied Mechanics and Engineering
Publisher
Elsevier BV
Published
2022-04
Volume
393
Pages
114778
ISSN
  • 2331-8422 (ISSN-L)
  • 0045-7825
OpenAlex
W4221019179
Cited by
514
References
45
Type
posted content
Language
en
Open access
green
Funders
  • DARPA
  • Office of the Secretary of Defense
  • Air Force Office of Scientific Research (FA9550-20-1-0056, FA9550-20-1-0358)
  • Department of Energy (DE-SC0019453)

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: A comprehensive and fair comparison of two neural operators (with practical extensions) based on FAIR data. https://app.cochat.ai/papers/10.1016/j.cma.2022.114778
The paper
Lu, L., Meng, X., Cai, S., Mao, Z., Goswami, S., Zhang, Z., & Karniadakis, G. E. (2022). A comprehensive and fair comparison of two neural operators (with practical extensions) based on FAIR data. Computer Methods in Applied Mechanics and Engineering. https://doi.org/10.1016/j.cma.2022.114778

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.