Super-resolution analysis via machine learning: a survey for fluid flows

This paper surveys machine-learning-based super-resolution reconstruction for vortical flows. Super resolution aims to find the high-resolution flowfields from low-resolution data and is generally an approach used in image reconstruction. In addition to surveying a variety of recent super-resolution applications, we provide case studies of super-resolution analysis for an example of two-dimensional decaying isotropic turbulence. We demonstrate that physics-inspired model designs enable successful reconstruction of vortical flows from spatially limitedmeasurements. We also discuss the challenges and outlooks of machine-learning-based superresolution analysis for fluid flow applications. The insights gained from this study can be leveraged for superresolution analysis of numerical and experimental flow data.

Automated summary

This paper surveys machine-learning-based super-resolution reconstruction for vortical flows. Super resolution aims to find the high-resolution flowfields from low-resolution data and is generally an approach used in image reconstruction. In addition to surveying a variety of recent super-resolution applications, we provide case studies of super-resolution analysis for an example of two-dimensional decaying isotropic turbulence. We demonstrate that physics-inspired model designs enable successful reconstruction of vortical flows from spatially limited measurements. We also discuss the challenges and outlooks of machine-learning-based superresolution analysis for fluid flow applications. The insights gained from this study can be leveraged for superresolution analysis of numerical and experimental flow data.