English

Physics-Informed CNNs for Super-Resolution of Sparse Observations on Dynamical Systems

Fluid Dynamics 2022-11-08 v2 Machine Learning

Abstract

In the absence of high-resolution samples, super-resolution of sparse observations on dynamical systems is a challenging problem with wide-reaching applications in experimental settings. We showcase the application of physics-informed convolutional neural networks for super-resolution of sparse observations on grids. Results are shown for the chaotic-turbulent Kolmogorov flow, demonstrating the potential of this method for resolving finer scales of turbulence when compared with classic interpolation methods, and thus effectively reconstructing missing physics.

Keywords

Cite

@article{arxiv.2210.17319,
  title  = {Physics-Informed CNNs for Super-Resolution of Sparse Observations on Dynamical Systems},
  author = {Daniel Kelshaw and Georgios Rigas and Luca Magri},
  journal= {arXiv preprint arXiv:2210.17319},
  year   = {2022}
}

Comments

Published in NeurIPS 2022: Machine Learning and the Physical Sciences Workshop. Code at https://github.com/magrilab/pisr. arXiv admin note: text overlap with arXiv:2210.16215

R2 v1 2026-06-28T04:50:56.052Z