NUNet: Deep Learning for Non-Uniform Super-Resolution of Turbulent Flows
Deep Learning (DL) algorithms are becoming increasingly popular for the reconstruction of high-resolution turbulent flows (aka super-resolution). However, current DL approaches perform spatially uniform super-resolution - a key performance limiter for scalability of DL-based surrogates for Computational Fluid Dynamics (CFD). To address the above challenge, we introduce NUNet, a deep learning-based adaptive mesh refinement (AMR) framework for non-uniform super-resolution of turbulent flows. NUNet divides the input low-resolution flow field into patches, scores each patch, and predicts their target resolution. As a result, it outputs a spatially non-uniform flow field, adaptively refining regions of the fluid domain to achieve the target accuracy. We train NUNet with Reynolds-Averaged Navier-Stokes (RANS) solutions from three different canonical flows, namely turbulent channel flow, flat plate, and flow around ellipses. NUNet shows remarkable discerning properties, refining areas with complex flow features, such as near-wall domains and the wake region in flow around solid bodies, while leaving areas with smooth variations (such as the freestream) in the low-precision range. Hence, NUNet demonstrates an excellent qualitative and quantitative alignment with the traditional OpenFOAM AMR solver. Moreover, it reaches the same convergence guarantees as the AMR solver while accelerating it by 3.2-5.5x, including unseen-during-training geometries and boundary conditions, demonstrating its generalization capacities. Due to NUNet's ability to super-resolve only regions of interest, it predicts the same target 1024x1024 spatial resolution 7-28.5x faster than state-of-the-art DL methods and reduces the memory usage by 4.4-7.65x, showcasing improved scalability.
Code (0)
등록된 구현이 없습니다.
Tasks
Super-ResolutionSimilar Papers 제목 키워드 기반
Super Resolution for Turbulent Flows in 2D: Stabilized Physics Informed Neural Networks
We propose a new design of a neural network for solving a zero shot super resolution problem for turbulent flows. We embed Luenberger-type observer into the network's architecture to inform the network of the physics of …
Super-ResolutionSuper-resolution of turbulent reacting flows on complex meshes using graph neural networks
State-of-the-art deep learning models have been extensively utilized to reconstruct small-scale structures from coarse-grained data in turbulent flows. However, their application has predominantly been restricted to stru…
Modeling Continuous Spatial-temporal Dynamics of Turbulent Flow with Test-time Refinement
The precise simulation of turbulent flows holds immense significance across various scientific and engineering domains, including climate science, freshwater science, and energy-efficient manufacturing. Within the realm …
Computational EfficiencySuper-ResolutionSingle-snapshot machine learning for super-resolution of turbulence
Modern machine-learning techniques are generally considered data-hungry. However, this may not be the case for turbulence as each of its snapshots can hold more information than a single data file in general machine-lear…
Super-ResolutionReconstructing Turbulent Flows Using Physics-Aware Spatio-Temporal Dynamics and Test-Time Refinement
Simulating turbulence is critical for many societally important applications in aerospace engineering, environmental science, the energy industry, and biomedicine. Large eddy simulation (LES) has been widely used as an a…
Super-Resolution