arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.08670cs.CVcs.CEcs.PFphysics.comp-ph
收藏

基于机器学习的地质流体求解器

A Machine Learning accelerated geophysical fluid solver

Technical University of Berlin(柏林技术大学);ETHz, Switzerland(瑞士ETH Zurich);Institute of Mathematics, Technical University of Berlin, Germany(柏林技术大学数学系);Institute of High Performance Computing Systems(高性能计算系统研究所)

Yang Bai

AI总结:

本文提出了一种基于深度学习的地质流体求解器,通过数据驱动离散化方法提升求解精度和稳定性,并在实验中验证了其有效性。

摘要:

机器学习方法在许多领域取得了成功,例如图像分类和自然语言处理。然而,仍需确定如何将ML应用于具有数学约束的领域,如求解偏微分方程(PDEs)。在将ML技术应用于求解PDEs的各种方法中,数据驱动的离散化方法提供了一种加速和改进现有结构网格上PDE求解器的有希望的方法。它通过预测准线性差分算子的系数来计算函数在给定位置的值或导数。与使用传统有限差分或有限体积方案相比,它能够提高低分辨率模拟的精度和稳定性。同时,它也可以从传统数值方案中受益,例如通过适应有限体积型公式来实现守恒定律。在本论文中,我们采用不同的框架实现了浅水方程和欧拉方程的经典求解器。实验表明,我们的经典求解器在Pyclaw求解器上表现要好得多。然后我们提出了四种不同的深度神经网络用于ML求解器。结果表明,其中两种方法能够输出令人满意的解。

英文摘要:

Machine learning methods have been successful in many areas, like image classification and natural language processing. However, it still needs to be determined how to apply ML to areas with mathematical constraints, like solving PDEs. Among various approaches to applying ML techniques to solving PDEs, the data-driven discretization method presents a promising way of accelerating and improving existing PDE solver on structured grids where it predicts the coefficients of quasi-linear stencils for computing values or derivatives of a function at given positions. It can improve the accuracy and stability of low-resolution simulation compared with using traditional finite difference or finite volume schemes. Meanwhile, it can also benefit from traditional numerical schemes like achieving conservation law by adapting finite volume type formulations. In this thesis, we have implemented the shallow water equation and Euler equation classic solver under a different framework. Experiments show that our classic solver performs much better than the Pyclaw solver. Then we propose four different deep neural networks for the ML-based solver. The results indicate that two of these approaches could output satisfactory solutions.

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。

↑