Solving continuum and rarefied flows using differentiable programming
文献类型：期刊论文
| 作者 | Xiao TB(肖天白)1,2,3 |
| 刊名 | JOURNAL OF COMPUTATIONAL PHYSICS
 |
| 出版日期 | 2025-10-15 |
| 卷号 | 539页码:31 |
| 关键词 | Computational fluid dynamics Boltzmann equation Kinetic theory Scientific machine learning Differentiable programming |
| ISSN号 | 0021-9991 |
| DOI | 10.1016/j.jcp.2025.114224 |
| 通讯作者 | Xiao, Tianbai(txiao@imech.ac.cn) |
| 英文摘要 | Accurate and efficient prediction of multi-scale flows remains a formidable challenge. Constructing theoretical models and numerical methods often involves the design and optimization of parameters. While gradient descent methods have been mainly manifested to shine in the wave of deep learning, composable automatic differentiation can advance scientific computing where the application of classical adjoint methods alone is infeasible or cumbersome. Differentiable programming provides a novel paradigm that unifies data structures and control flows and facilitates gradient-based optimization of parameters in a computer program. This paper addresses the notion and implementation of the first solution algorithm for multi-scale flow physics across continuum and rarefied regimes based on differentiable programming. The fully differentiable simulator provides a unified framework for the convergence of computational fluid dynamics and machine learning, i.e., scientific machine learning. Specifically, parameterized flow models and numerical methods can be constructed for forward physical processes, while the parameters can be trained on the fly with the help of the gradients that are taken through the backward passes of the whole simulation program, a.k.a., end-to-end optimization. As a result, versatile data-augmented modeling and simulation can be achieved for physics discovery, surrogate modeling, and simulation acceleration. The fundamentals and implementation of the solution algorithm are demonstrated in detail. Numerical experiments, including forward and inverse problems for hydrodynamic and kinetic equations, are presented to demonstrate the performance of the numerical method. The open-source codes to reproduce the numerical results are available under the MIT license. |
| 分类号 | 一类/力学重要期刊 |
| WOS关键词 | BOLTZMANN-EQUATION ; NEURAL-NETWORKS ; SCHEMES ; DISSIPATION ; CLOSURE |
| 资助项目 | National Science Foundation of China[12302381] ; Chinese Academy of Sciences Project for Young Scientists in Basic Research[YSBR-107] |
| WOS研究方向 | Computer Science ; Physics |
| 语种 | 英语 |
| WOS记录号 | WOS:001539150800001 |
| 资助机构 | National Science Foundation of China ; Chinese Academy of Sciences Project for Young Scientists in Basic Research |
| 其他责任者 | 肖天白 |
| 源URL | [http://dspace.imech.ac.cn/handle/311007/102331]  |
| 专题 | 力学研究所_高温气体动力学国家重点实验室 |
| 作者单位 | 1.Chinese Acad Sci, Ctr Interdisciplinary Res Fluids, Beijing, Peoples R China; 2.Univ Chinese Acad Sci, Sch Engn Sci, Beijing, Peoples R China 3.Chinese Acad Sci, Inst Mech, State Key Lab High Temp Gas Dynam, Beijing, Peoples R China; |
| 推荐引用方式 GB/T 7714 | Xiao TB. Solving continuum and rarefied flows using differentiable programming[J]. JOURNAL OF COMPUTATIONAL PHYSICS,2025,539:31. |
| APA | 肖天白.(2025).Solving continuum and rarefied flows using differentiable programming.JOURNAL OF COMPUTATIONAL PHYSICS,539,31. |
| MLA | 肖天白."Solving continuum and rarefied flows using differentiable programming".JOURNAL OF COMPUTATIONAL PHYSICS 539(2025):31. |
入库方式： OAI收割
来源：力学研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。