arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2510.23936cs.LGphysics.flu-dyn
收藏

一种实现2D和3D Navier Stokes方程快速推理的无数据神经算子

A data free neural operator enabling fast inference of 2D and 3D Navier Stokes equations

Junho Choi, Teng-Yuan Chang, Namjung Kim, Youngjoon Hong

AI总结:

提出一种用于Navier Stokes方程的无数据算子网络,结合物理架构与机器学习,在2D和3D流中实现高精度、高效率的实时集合预测。

摘要:

高维流模型(例如Navier Stokes型PDEs)的集合模拟对于实时应用而言计算成本过高。神经算子能够实现快速推理,但受到昂贵数据需求和向3D流泛化能力差的限制。我们提出了一种用于Navier Stokes方程的无数据算子网络,它消除了对配对解数据的需求,并能够对大型集合预测进行稳健的实时推理。该基于物理的架构以初始和边界条件以及强迫函数作为输入,产生对高变异性和扰动具有稳健性的解。在2D基准和3D测试案例中,该方法在精度上超越了先前的神经算子,并且在集合计算上实现了比传统数值求解器更高的效率。值得注意的是,它提供了三维Navier Stokes方程的精确解,这是无数据神经算子此前未曾证明的领域。通过将基于数值的架构与机器学习的可扩展性相结合,该方法为端到端的科学模拟与预测建立了一条通向无数据、高保真PDE替代模型的实用途径。

英文摘要:

Ensemble simulations of high-dimensional flow models (e.g., Navier Stokes type PDEs) are computationally prohibitive for real time applications. Neural operators enable fast inference but are limited by costly data requirements and poor generalization to 3D flows. We present a data-free operator network for the Navier Stokes equations that eliminates the need for paired solution data and enables robust, real time inference for large ensemble forecasting. The physics-grounded architecture takes initial and boundary conditions as well as forcing functions, yielding solutions robust to high variability and perturbations. Across 2D benchmarks and 3D test cases, the method surpasses prior neural operators in accuracy and, for ensembles, achieves greater efficiency than conventional numerical solvers. Notably, it delivers accurate solutions of the three dimensional Navier Stokes equations, a regime not previously demonstrated for data free neural operators. By uniting a numerically grounded architecture with the scalability of machine learning, this approach establishes a practical pathway toward data free, high fidelity PDE surrogates for end to end scientific simulation and prediction.

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。

↑