mlsanityData to 14 Oct 2026

Data-Efficient Deep Operator Network for Unsteady Flow: A Multi-Fidelity Approach with Physics-Guided Subsampling

arXiv 2503.17941 ↗First posted 23 Mar 2025physics.flu-dyn cs.AIcited by 5

Not on the map. Why?

Abstract (arXiv)

This study presents an enhanced multi-fidelity Deep Operator Network (DeepONet) framework for efficient spatio-temporal flow field prediction when high-fidelity data is scarce. Key innovations include: a merge network replacing traditional dot-product operations, achieving 50.4% reduction in prediction error and 7.57% accuracy improvement while reducing training time by 96%; a transfer learning multi-fidelity approach that freezes pre-trained low-fidelity networks while making only the merge network trainable, outperforming alternatives by up to 76% and achieving 43.7% better accuracy than single-fidelity training; and a physics-guided subsampling method that strategically selects high-fidelity training points based on temporal dynamics, reducing high-fidelity sample requirements by 40% while maintaining comparable accuracy. Comprehensive experiments across multiple resolutions and datasets demonstrate the framework's ability to significantly reduce required high-fidelity dataset size while maintaining predictive accuracy, with consistent superior performance against conventional benchmarks.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 29 of its 57 references that are in the map. First posted on arXiv 23 Mar 2025.

Builds on

29 of 57 references.

References · 29

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,200
  3. 2019DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operatorscited by 2,018
  4. 2020Learning Mesh-Based Simulation with Graph Networkscited by 868
  5. 2022Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distributioncited by 739
  6. 2019DeepXDE: A deep learning library for solving differential equationscited by 619
  7. 2021Advances in Neural Renderingcited by 365
  8. 2024A comprehensive and FAIR comparison between MLP and KAN representations for differential equations and operator networkscited by 104
  9. 2022Multifidelity deep neural operators for efficient learning of partial differential equations with application to fast inverse design of nanoscale heat transportcited by 92
  10. 2021Improved architectures and training algorithms for deep operator networkscited by 86
  11. 2020Transfer learning based multi-fidelity physics informed deep neural networkcited by 68
  12. 2022Multifidelity Deep Operator Networks For Data-Driven and Physics-Informed Problemscited by 58
17 more
  1. 2021Seeing Implicit Neural Representations as Fourier Seriescited by 50
  2. 2020Convolutional-network models to predict wall-bounded turbulence from wall quantitiescited by 47
  3. 2021Towards extraction of orthogonal and parsimonious non-linear modes from turbulent flowscited by 45
  4. 2021Rethinking Positional Encodingcited by 37
  5. 2022Bi-fidelity Modeling of Uncertain and Partially Unknown Systems using DeepONetscited by 27
  6. 2020On transfer learning of neural networks using bi-fidelity data for uncertainty propagationcited by 26
  7. 2024X-MeshGraphNet: Scalable Multi-Scale Graph Neural Networks for Physics Simulationcited by 22
  8. 2021Neural Network Training Using ℓ1-Regularization and Bi-fidelity Datacited by 16
  9. 2022Physics-aware Reduced-order Modeling of Transonic Flow via β-Variational Autoencodercited by 15
  10. 2021Inverse design optimization framework via a two-step deep learning approach: application to a wind turbine airfoilcited by 14
  11. 2023A DeepONet multi-fidelity approach for residual learning in reduced order modelingcited by 14
  12. 2023A multi-fidelity deep operator network (DeepONet) for fusing simulation and monitoring data: Application to real-time settlement prediction during tunnel constructioncited by 12
  13. 2024Data-Driven Physics-Informed Neural Networks: A Digital Twin Perspectivecited by 12
  14. 2022Use of Multifidelity Training Data and Transfer Learning for Efficient Construction of Subsurface Flow Surrogate Modelscited by 11
  15. 2023Predictions of Transient Vector Solution Fields with Sequential Deep Operator Networkcited by 9
  16. 2023Improved Positional Encoding for Implicit Neural Representation based Compact Data Representationcited by 4
  17. 2024Enhancing Graph U-Nets for Mesh-Agnostic Spatio-Temporal Flow Predictioncited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 4.

5 papers.

  1. 2025Rigid-Deformation Decomposition AI Framework for 3D Spatio-Temporal Prediction of Vehicle Collision Dynamicscited by 1
  2. 2026Multifidelity Surrogate Modeling of Depressurized Loss of Forced Cooling in High-temperature Gas Reactorscited by 1
  3. 2026Generative AI-enhanced Probabilistic Multi-Fidelity Surrogate Modeling Via Transfer Learningcited by 0
  4. 2026Multi-Fidelity Learning with Shallow Recurrent Decoders for Multi-Physics Applicationscited by 0
  5. 2026Distance-Aware Attention and Wall-Distance Expert Routing for Transformer-Based 3D Flow Predictioncited by 0