Enhancing the accuracy of under-resolved numerical simulations of atmospheric flows with super resolution

TL;DR

This paper explores deep learning super-resolution techniques to improve the accuracy of coarse-grid atmospheric flow simulations, demonstrating that multi-scale CNNs outperform other models in capturing complex flow features.

Contribution

The study compares various super-resolution architectures, introducing a multi-scale CNN that enhances the accuracy and efficiency of atmospheric flow simulations.

Findings

Multi-scale CNNs outperform other models in complex flow reconstruction.

Super-resolution improves the accuracy of coarse-grid atmospheric simulations.

Model performance depends on training dataset size and flow complexity.

Abstract

Super-resolution (SR) techniques based on deep learning have recently emerged as a promising approach to enhance the spatial resolution of computational fluid dynamics simulations while containing computational cost. In this paper, we investigate several SR architectures to improve coarse-grid simulations of mesoscale atmospheric flows, with training data generated from simulations of the weakly compressible Euler equations. We compare a baseline convolutional neural network (CNN), an attention-enhanced CNN, a multi-scale CNN designed to capture flow structures across different spatial scales, and a diffusion-based SR model. The methods are evaluated on two standard atmospheric benchmarks: the rising thermal bubble and the density current. Results show that the baseline CNN can accurately reconstruct simpler flow features, while more complex flows require multi-scale architectures. Overall, SR based on the multi-scale CNN provides the best balance of accuracy, robustness, and computational efficiency, outperforming even a state-of-the-art diffusion-based approach. We also analyze the sensitivity of the models to the size of the training dataset, highlighting limitations and trade-offs of the proposed SR strategies.