English

S3RP: Self-Supervised Super-Resolution and Prediction for Advection-Diffusion Process

Machine Learning 2023-06-26 v1 Computer Vision and Pattern Recognition Computational Physics

Abstract

We present a super-resolution model for an advection-diffusion process with limited information. While most of the super-resolution models assume high-resolution (HR) ground-truth data in the training, in many cases such HR dataset is not readily accessible. Here, we show that a Recurrent Convolutional Network trained with physics-based regularizations is able to reconstruct the HR information without having the HR ground-truth data. Moreover, considering the ill-posed nature of a super-resolution problem, we employ the Recurrent Wasserstein Autoencoder to model the uncertainty.

Keywords

Cite

@article{arxiv.2111.04639,
  title  = {S3RP: Self-Supervised Super-Resolution and Prediction for Advection-Diffusion Process},
  author = {Chulin Wang and Kyongmin Yeo and Xiao Jin and Andres Codas and Levente J. Klein and Bruce Elmegreen},
  journal= {arXiv preprint arXiv:2111.04639},
  year   = {2023}
}

Comments

9 pages, 8 figures

R2 v1 2026-06-24T07:30:56.848Z