SURFNet: Super-resolution of Turbulent Flows with Transfer Learning using Small Datasets

• URL: http://arxiv.org/abs/2108.07667v1
• Date: Tue, 17 Aug 2021 14:53:04 GMT
• Title: SURFNet: Super-resolution of Turbulent Flows with Transfer Learning using Small Datasets
• Authors: Octavi Obiols-Sales, Abhinav Vishnu, Nicholas Malaya, and Aparna Chandramowlishwaran
• Abstract summary: This paper introduces SURFNet, a transfer learning-based super-resolution flow network. SURFNet primarily trains the DL model on low-resolution datasets and transfer learns the model on a handful of high-resolution flow problems. We empirically evaluate SURFNet's performance by solving the Navier-Stokes equations in the turbulent regime on input resolutions up to 256x larger than the coarse model.
• Score: 0.9297355862757838
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep Learning (DL) algorithms are emerging as a key alternative to computationally expensive CFD simulations. However, state-of-the-art DL approaches require large and high-resolution training data to learn accurate models. The size and availability of such datasets are a major limitation for the development of next-generation data-driven surrogate models for turbulent flows. This paper introduces SURFNet, a transfer learning-based super-resolution flow network. SURFNet primarily trains the DL model on low-resolution datasets and transfer learns the model on a handful of high-resolution flow problems - accelerating the traditional numerical solver independent of the input size. We propose two approaches to transfer learning for the task of super-resolution, namely one-shot and incremental learning. Both approaches entail transfer learning on only one geometry to account for fine-grid flow fields requiring 15x less training data on high-resolution inputs compared to the tiny resolution (64x256) of the coarse model, significantly reducing the time for both data collection and training. We empirically evaluate SURFNet's performance by solving the Navier-Stokes equations in the turbulent regime on input resolutions up to 256x larger than the coarse model. On four test geometries and eight flow configurations unseen during training, we observe a consistent 2-2.1x speedup over the OpenFOAM physics solver independent of the test geometry and the resolution size (up to 2048x2048), demonstrating both resolution-invariance and generalization capabilities. Our approach addresses the challenge of reconstructing high-resolution solutions from coarse grid models trained using low-resolution inputs (super-resolution) without loss of accuracy and requiring limited computational resources.

Related papers

• SoFlow: Solution Flow Models for One-Step Generative Modeling [10.054000663262618]
  Flow Models (SoFlow) is a framework for one-step generation from scratch.<n>Flow Matching loss allows our models to provide estimated velocity fields during training.<n>Our models achieve better FID-50K scores than MeanFlow models on the ImageNet 256x256 dataset.
  arXiv  Detail & Related papers  (2025-12-17T18:10:17Z)
• PMRT: A Training Recipe for Fast, 3D High-Resolution Aerodynamic Prediction [0.0]
  Surrogate models have been shown to accurately predict aerodynamics within the design space for which they were trained.<n>We propose Progressive Multi-Resolution Training (PMRT), a probabilistic multi-resolution training schedule.<n>PMRT samples batches from three resolutions based on probabilities that change during training.<n>We show that a single model can be trained across five datasets from different solvers, including a real-world dataset, by conditioning on the simulation parameters.
  arXiv  Detail & Related papers  (2025-09-21T18:05:50Z)
• Fusing CFD and measurement data using transfer learning [49.1574468325115]
  We introduce a non-linear method based on neural networks combining simulation and measurement data via transfer learning.<n>In a first step, the neural network is trained on simulation data to learn spatial features of the distributed quantities.<n>The second step involves transfer learning on the measurement data to correct for systematic errors between simulation and measurement by only re-training a small subset of the entire neural network model.
  arXiv  Detail & Related papers  (2025-07-28T07:21:46Z)
• Greedy Growing Enables High-Resolution Pixel-Based Diffusion Models [41.67994377132345]
  We propose a greedy algorithm that grows the architecture into high-resolution end-to-end models. This enables a single stage model capable of generating high-resolution images without the need of a super-resolution cascade. Our results rely on public datasets and show that we are able to train non-cascaded models up to 8B parameters with no further regularization schemes.
  arXiv  Detail & Related papers  (2024-05-27T02:12:39Z)
• Diffusion-Based Neural Network Weights Generation [80.89706112736353]
  D2NWG is a diffusion-based neural network weights generation technique that efficiently produces high-performing weights for transfer learning. Our method extends generative hyper-representation learning to recast the latent diffusion paradigm for neural network weights generation. Our approach is scalable to large architectures such as large language models (LLMs), overcoming the limitations of current parameter generation techniques.
  arXiv  Detail & Related papers  (2024-02-28T08:34:23Z)
• Towards a Better Theoretical Understanding of Independent Subnetwork Training [56.24689348875711]
  We take a closer theoretical look at Independent Subnetwork Training (IST) IST is a recently proposed and highly effective technique for solving the aforementioned problems. We identify fundamental differences between IST and alternative approaches, such as distributed methods with compressed communication.
  arXiv  Detail & Related papers  (2023-06-28T18:14:22Z)
• Learning Controllable Adaptive Simulation for Multi-resolution Physics [86.8993558124143]
  We introduce Learning controllable Adaptive simulation for Multi-resolution Physics (LAMP) as the first full deep learning-based surrogate model. LAMP consists of a Graph Neural Network (GNN) for learning the forward evolution, and a GNN-based actor-critic for learning the policy of spatial refinement and coarsening. We demonstrate that our LAMP outperforms state-of-the-art deep learning surrogate models, and can adaptively trade-off computation to improve long-term prediction error.
  arXiv  Detail & Related papers  (2023-05-01T23:20:27Z)
• Learning to Optimize Permutation Flow Shop Scheduling via Graph-based Imitation Learning [70.65666982566655]
  Permutation flow shop scheduling (PFSS) is widely used in manufacturing systems. We propose to train the model via expert-driven imitation learning, which accelerates convergence more stably and accurately. Our model's network parameters are reduced to only 37% of theirs, and the solution gap of our model towards the expert solutions decreases from 6.8% to 1.3% on average.
  arXiv  Detail & Related papers  (2022-10-31T09:46:26Z)
• Machine Learning-Accelerated Computational Solid Mechanics: Application to Linear Elasticity [0.0]
  We leverage the governing equations and boundary conditions of the physical system to train the model without using any high-resolution labeled data. We demonstrate that the super-resolved fields match the accuracy of an advanced numerical solver running at 400 times the coarse mesh resolution.
  arXiv  Detail & Related papers  (2021-12-16T07:39:50Z)
• Stacked Generative Machine Learning Models for Fast Approximations of Steady-State Navier-Stokes Equations [1.4150517264592128]
  We develop a weakly-supervised approach to solve the steady-state Navier-Stokes equations under various boundary conditions. We achieve state-of-the-art results without any labeled simulation data. We train stacked models of increasing complexity generating the numerical solutions for N-S equations.
  arXiv  Detail & Related papers  (2021-12-13T05:08:55Z)
• Multi-Scale Aligned Distillation for Low-Resolution Detection [68.96325141432078]
  This paper focuses on boosting the performance of low-resolution models by distilling knowledge from a high- or multi-resolution model. On several instance-level detection tasks and datasets, the low-resolution models trained via our approach perform competitively with high-resolution models trained via conventional multi-scale training.
  arXiv  Detail & Related papers  (2021-09-14T12:53:35Z)
• A comparative study of various Deep Learning techniques for spatio-temporal Super-Resolution reconstruction of Forced Isotropic Turbulent flows [0.45935798913942893]
  This study performs super-resolution analysis on turbulent flow fields spatially and temporally using various state-of-the-art machine learning techniques. The dataset used for this study is extracted from the 'isotropic 1024 coarse' dataset which is a part of Johns Hopkins Turbulence databases.
  arXiv  Detail & Related papers  (2021-07-07T17:16:55Z)
• Deep Learning for Efficient Reconstruction of High-Resolution Turbulent DNS Data [0.0]
  Large Eddy Simulation (LES) presents a more computationally efficient approach for solving fluid flows on lower-resolution (LR) grids. We introduce a novel deep learning framework SR-DNS Net, which aims to mitigate this inherent trade-off between solution fidelity and computational complexity. Our model efficiently reconstructs the high-fidelity DNS data from the LES like low-resolution solutions while yielding good reconstruction metrics.
  arXiv  Detail & Related papers  (2020-10-21T23:37:58Z)
• An Online Method for A Class of Distributionally Robust Optimization with Non-Convex Objectives [54.29001037565384]
  We propose a practical online method for solving a class of online distributionally robust optimization (DRO) problems. Our studies demonstrate important applications in machine learning for improving the robustness of networks.
  arXiv  Detail & Related papers  (2020-06-17T20:19:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.