Extending a Physics-Informed Machine Learning Network for Superresolution Studies of Rayleigh-B\'enard Convection

TL;DR

This paper develops a physics-informed CNN model called MeshFreeFlowNet for superresolution of turbulent Rayleigh-Bénard convection, successfully capturing large-scale features and inertial range scaling across a wide range of turbulence intensities.

Contribution

The paper introduces a physics-constrained CNN architecture that incorporates PDEs and boundary conditions for superresolution in turbulent fluid systems, extending previous ML approaches.

Findings

Model accurately recovers large-scale flow features.

Superresolution predictions match inertial range slopes.

More turbulent regimes yield better small-scale recovery.

Abstract

Advancing our understanding of astrophysical turbulence is bottlenecked by the limited resolution of numerical simulations that may not fully sample scales in the inertial range. Machine learning (ML) techniques have demonstrated promise in up-scaling resolution in both image analysis and numerical simulations (i.e., superresolution). Here we employ and further develop a physics-constrained convolutional neural network (CNN) ML model called "MeshFreeFlowNet'' (MFFN) for superresolution studies of turbulent systems. The model is trained both on the simulation images as well as the evaluated PDEs, making it sensitive to the underlying physics of a particular fluid system. We develop a framework for 2D turbulent Rayleigh-B\'enard convection (RBC) generated with the \textsc{Dedalus} code by modifying the MFFN architecture to include the full set of simulation PDEs and the boundary conditions. Our training set includes fully developed turbulence sampling Rayleigh numbers ($Ra$) of $Ra=10^6-10^{10}$. We evaluate the success of the learned simulations by comparing the power spectra of the direct \textsc{Dedalus} simulation to the predicted model output, and compare both ground truth and predicted power spectral inertial range scalings to theoretical predictions. We find that the updated network performs well at all $Ra$ studied here in recovering large-scale information, including the inertial range slopes. The superresolution prediction is overly dissipative at smaller scales than that of the inertial range in all cases, but the smaller-scales are better recovered in more turbulent, than laminar, regimes. This is likely because more turbulent systems have a rich variety of structures at many length scales compared to laminar flows.