arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2412.04833cs.LG
收藏

小波扩散神经算子

Wavelet Diffusion Neural Operator

Department of Artificial Intelligence, School of Engineering, Westlake University(人工智能系,工程学院,西湖大学);Academy of Mathematics and Systems Science, Chinese Academy of Sciences(数学系统科学学院,中国科学院);Fudan University(复旦大学);South China University of Technology(华南理工大学);Microsoft AI4Science(微软AI4Science)

Peiyan Hu, Rui Wang, Xiang Zheng, Tao Zhang, Haodong Feng, Ruiqi Feng, Long Wei, Yue Wang, Zhi-Ming Ma, Tailin Wu

AI总结:

提出Wavelet Diffusion Neural Operator (WDNO)框架,通过在小波域进行扩散建模并引入多分辨率训练,有效解决PDE系统模拟与控制中状态突变及跨分辨率泛化问题,在五个物理系统中表现优于现有方法。

摘要:

模拟和控制由偏微分方程(PDEs)描述的物理系统是科学和工程领域的关键任务。最近,扩散生成模型因能够捕捉长期依赖关系和建模高维状态,已成为处理这些任务的有竞争力的一类方法。然而,扩散模型通常难以处理具有突变状态的系统,并且难以泛化到更高分辨率。在这项工作中,我们提出了Wavelet Diffusion Neural Operator (WDNO),这是一个新颖的PDE模拟和控制框架,旨在增强对这些复杂性的处理能力。WDNO包含两项关键创新。首先,WDNO在整个轨迹的小波域中进行基于扩散的生成建模,以有效处理突变和长期依赖关系。其次,为了解决跨不同分辨率泛化能力差的问题(这是物理系统建模中的基本任务之一),我们引入了多分辨率训练。我们在五个物理系统上验证了WDNO,包括1D平流方程、三个具有突变的挑战性物理系统(1D Burgers方程、1D可压缩Navier-Stokes方程和2D不可压缩流体),以及真实世界数据集ERA5。这表明WDNO在模拟和控制任务上均优于现有最先进方法,在长期和细节预测精度上有显著提升。值得注意的是,在旨在减少漏烟的2D高维和间接控制任务这一具有挑战性的背景下,WDNO与次优基线相比将泄漏减少了78%。代码可在 https://github.com/AI4Science-WestlakeU/wdno.git 找到。

英文摘要:

Simulating and controlling physical systems described by partial differential equations (PDEs) are crucial tasks across science and engineering. Recently, diffusion generative models have emerged as a competitive class of methods for these tasks due to their ability to capture long-term dependencies and model high-dimensional states. However, diffusion models typically struggle with handling system states with abrupt changes and generalizing to higher resolutions. In this work, we propose Wavelet Diffusion Neural Operator (WDNO), a novel PDE simulation and control framework that enhances the handling of these complexities. WDNO comprises two key innovations. Firstly, WDNO performs diffusion-based generative modeling in the wavelet domain for the entire trajectory to handle abrupt changes and long-term dependencies effectively. Secondly, to address the issue of poor generalization across different resolutions, which is one of the fundamental tasks in modeling physical systems, we introduce multi-resolution training. We validate WDNO on five physical systems, including 1D advection equation, three challenging physical systems with abrupt changes (1D Burgers' equation, 1D compressible Navier-Stokes equation and 2D incompressible fluid), and a real-world dataset ERA5, which demonstrates superior performance on both simulation and control tasks over state-of-the-art methods, with significant improvements in long-term and detail prediction accuracy. Remarkably, in the challenging context of the 2D high-dimensional and indirect control task aimed at reducing smoke leakage, WDNO reduces the leakage by 78% compared to the second-best baseline. The code can be found at https://github.com/AI4Science-WestlakeU/wdno.git.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑