论文标题
使用物理知识的卷积神经网络无需高分辨率标签的超级分辨率和降解流体流动
Super-resolution and denoising of fluid flow using physics-informed convolutional neural networks without high-resolution labels
论文作者
论文摘要
流体流的高分辨率（HR）信息虽然可取，但由于计算或实验资源有限，通常较少访问。在许多情况下，流体数据通常是稀疏，不完整且可能嘈杂的。如何增强空间分辨率并降低流量数据的噪声水平至关重要且实际上有用。深度学习（DL）技术已被证明对超分辨率（SR）任务有效，但是，这主要依靠足够的人力资源标签进行培训。在这项工作中，我们使用卷积神经网络（CNN）提出了一种新型的基于DL的SR解决方案，该解决方案能够在高维参数空间中从低分辨率（LR）输入中产生HR流场。通过利用流体流的保护定律和边界条件，对CNN-SR模型进行了训练，而无需任何HR标签。此外，提出的CNN-SR解决方案统一了向前的SR和逆数据同化，即物理学是部分已知的情况，例如未知的边界条件。已经研究了与心血管应用相关的几个流量SR问题，以证明该方法的有效性和优点。研究了高斯和非高斯MRI噪声，以说明脱氧能力。
High-resolution (HR) information of fluid flows, although preferable, is usually less accessible due to limited computational or experimental resources. In many cases, fluid data are generally sparse, incomplete, and possibly noisy. How to enhance spatial resolution and decrease the noise level of flow data is essential and practically useful. Deep learning (DL) techniques have been demonstrated to be effective for super-resolution (SR) tasks, which, however, primarily rely on sufficient HR labels for training. In this work, we present a novel physics-informed DL-based SR solution using convolutional neural networks (CNN), which is able to produce HR flow fields from low-resolution (LR) inputs in high-dimensional parameter space. By leveraging the conservation laws and boundary conditions of fluid flows, the CNN-SR model is trained without any HR labels. Moreover, the proposed CNN-SR solution unifies the forward SR and inverse data assimilation for the scenarios where the physics is partially known, e.g., unknown boundary conditions. Several flow SR problems relevant to cardiovascular applications have been studied to demonstrate the proposed method's effectiveness and merit. Both Gaussian and non-Gaussian MRI noises are investigated to illustrate the denoising capability.
