mlsanityData to 14 Oct 2026

An Operator Learning Framework for Spatiotemporal Super-resolution of Scientific Simulations

arXiv 2311.02328 ↗First posted 4 Nov 2023cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

In numerous contexts, high-resolution solutions to partial differential equations are required to capture faithfully essential dynamics which occur at small spatiotemporal scales, but these solutions can be very difficult and slow to obtain using traditional methods due to limited computational resources. A recent direction to circumvent these computational limitations is to use machine learning techniques for super-resolution, to reconstruct high-resolution numerical solutions from low-resolution simulations which can be obtained more efficiently. The proposed approach, the Super Resolution Operator Network (SROpNet), frames super-resolution as an operator learning problem and draws inspiration from existing architectures to learn continuous representations of solutions to parametric differential equations from low-resolution approximations, which can then be evaluated at any desired location. In addition, no restrictions are imposed on the locations of (the fixed number of) spatiotemporal sensors at which the low-resolution approximations are provided, thereby enabling the consideration of a broader spectrum of problems arising in practice, for which many existing super-resolution approaches are not well-suited.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 67 of its 112 references that are in the map. First posted on arXiv 4 Nov 2023.

Builds on

67 of 112 references.

References · 67

  1. 2020Fourier Neural Operator for Parametric Partial Differential Equationscited by 2,908
  2. 2019DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operatorscited by 2,018
  3. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,908
  4. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,552
  5. 2018Image Super-Resolution Using Very Deep Residual Channel Attention Networkscited by 1,264
  6. 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,254
  7. 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,224
  8. 2015Accurate Image Super-Resolution Using Very Deep Convolutional Networkscited by 903
  9. 2017GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networkscited by 834
  10. 2018Residual Dense Network for Image Super-Resolutioncited by 799
  11. 2021Characterizing possible failure modes in physics-informed neural networkscited by 643
  12. 2020When and why PINNs fail to train: A neural tangent kernel perspectivecited by 634
38 more
  1. 2017Video Enhancement with Task-Oriented Flowcited by 619
  2. 2019DeepXDE: A deep learning library for solving differential equationscited by 619
  3. 2021Physics-Informed Neural Operator for Learning Partial Differential Equationscited by 527
  4. 2019EDVR: Video Restoration with Enhanced Deformable Convolutional Networkscited by 494
  5. 2021Physics-informed neural networks (PINNs) for fluid mechanics: A reviewcited by 473
  6. 2017Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolutioncited by 453
  7. 2022Fourier Neural Operator with Learned Deformations for PDEs on General Geometriescited by 427
  8. 2021SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Modelscited by 415
  9. 2021Neural Operator: Learning Maps Between Function Spacescited by 414
  10. 2016Accelerating the Super-Resolution Convolutional Neural Networkcited by 394
  11. 2017Physics Informed Deep Learning (Part I): Data-driven Solutions of Nonlinear Partial Differential Equationscited by 373
  12. 2019Deep Learning for Image Super-resolution: A Surveycited by 369
  13. 2020B-PINNs: Bayesian Physics-Informed Neural Networks for Forward and Inverse PDE Problems with Noisy Datacited by 335
  14. 2023Geometry-Informed Neural Operator for Large-Scale 3D PDEscited by 303
  15. 2021U-FNO -- An enhanced Fourier neural operator-based deep-learning model for multiphase flowcited by 297
  16. 2022Transformer for Partial Differential Equations' Operator Learningcited by 283
  17. 2018Fast, Accurate, and Lightweight Super-Resolution with Cascading Residual Networkcited by 264
  18. 2020Model Reduction and Neural Networks for Parametric PDEscited by 258
  19. 2021Adaptive Fourier Neural Operators: Efficient Token Mixers for Transformerscited by 248
  20. 2020hp-VPINNs: Variational Physics-Informed Neural Networks With Domain Decompositioncited by 236
  21. 2023Spherical Fourier Neural Operators: Learning Stable Dynamics on the Spherecited by 233
  22. 2021Gradient-enhanced physics-informed neural networks for forward and inverse PDE problemscited by 222
  23. 2019Universal Approximation with Deep Narrow Networkscited by 200
  24. 2022FourCastNet: Accelerating Global High-Resolution Weather Forecasting using Adaptive Fourier Neural Operatorscited by 188
  25. 2017Physics Informed Deep Learning (Part II): Data-driven Discovery of Nonlinear Partial Differential Equationscited by 161
  26. 2018Frame-Recurrent Video Super-Resolutioncited by 160
  27. 2016Real-Time Video Super-Resolution with Spatio-Temporal Networks and Motion Compensationcited by 156
  28. 2022A Physics-informed Diffusion Model for High-fidelity Flow Field Reconstructioncited by 152
  29. 2017Detail-revealing Deep Video Super-resolutioncited by 148
  30. 2019Recurrent Back-Projection Network for Video Super-Resolutioncited by 148
  31. 2019PPINN: Parareal Physics-Informed Neural Network for time-dependent PDEscited by 118
  32. 2019Transfer learning enhanced physics informed neural network for phase-field modeling of fracturecited by 116
  33. 2020Estimates on the generalization error of Physics Informed Neural Networks (PINNs) for approximating PDEscited by 116
  34. 2020Video Super-Resolution with Recurrent Structure-Detail Networkcited by 116
  35. 2021Parallel Physics-Informed Neural Networks via Domain Decompositioncited by 112
  36. 2019The phase diagram of approximation rates for deep neural networkscited by 88
  37. 2021Multi-Objective Loss Balancing for Physics-Informed Deep Learningcited by 87
  38. 2019A Deep Journey into Super-resolution: A surveycited by 86

50 most cited of 67 All 67 (JSON)

Built on by

Not cited yet.