arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2009.04543cs.LGphysics.comp-phphysics.data-an
收藏

弱形式理论指导的神经网络(TgNN-wf)用于地下单相和两相流的深度学习

Weak Form Theory-guided Neural Network (TgNN-wf) for Deep Learning of Subsurface Single and Two-phase Flow

Peng Cheng Laboratory(鹏城实验室);Southern University of Science and Technology(南方科技大学);Peking University(北京大学)

Rui Xu, Dongxiao Zhang, Miao Rong, Nanzhe Wang

摘要:

深度神经网络(DNN)被广泛用作地球物理应用中的代理模型;将理论指导纳入DNN提高了可推广性。然而,大多数这样的方法定义的损失函数的基础上的强形式的守恒定律(通过偏微分方程,PDE),这是受到恶化的精度时,PDE具有高阶导数或解决方案具有强的不连续性。本文提出了一种弱形式理论指导的神经网络(TgNN-wf),它将PDE的弱形式公式化与损失函数相结合,并结合数据约束和初始边界条件正则化来解决上述困难。在弱形式下,偏微分方程中的高阶导数可以通过分部积分转移到测试函数上,从而减少了计算误差。我们使用区域分解与局部定义的测试函数,它捕捉局部不连续性有效。两个数值算例表明了所提出的TgNN-wf的优越性强形式TgNN,包括非稳态二维单相流问题的水头预测和一维两相流问题的饱和度剖面预测。结果表明,TgNN-wf始终具有更高的精度比TgNN,特别是当强间断的解决方案。当积分子域的数量不太大(<10,000)时,TgNN-wf也比TgNN训练得更快。此外,TgNN-wf对噪声更具鲁棒性。因此,所提出的TgNN-wf为更准确有效地解决小数据范围内的各种深度学习问题铺平了道路。

英文摘要:

Deep neural networks (DNNs) are widely used as surrogate models in geophysical applications; incorporating theoretical guidance into DNNs has improved the generalizability. However, most of such approaches define the loss function based on the strong form of conservation laws (via partial differential equations, PDEs), which is subject to deteriorated accuracy when the PDE has high order derivatives or the solution has strong discontinuities. Herein, we propose a weak form theory-guided neural network (TgNN-wf), which incorporates the weak form formulation of the PDE into the loss function combined with data constraint and initial and boundary conditions regularizations to tackle the aforementioned difficulties. In the weak form, high order derivatives in the PDE can be transferred to the test functions by performing integration-by-parts, which reduces computational error. We use domain decomposition with locally defined test functions, which captures local discontinuity effectively. Two numerical cases demonstrate the superiority of the proposed TgNN-wf over the strong form TgNN, including the hydraulic head prediction for unsteady-state 2D single-phase flow problems and the saturation profile prediction for 1D two-phase flow problems. Results show that TgNN-wf consistently has higher accuracy than TgNN, especially when strong discontinuity in the solution is present. TgNN-wf also trains faster than TgNN when the number of integration subdomains is not too large (<10,000). Moreover, TgNN-wf is more robust to noises. Thus, the proposed TgNN-wf paves the way for which a variety of deep learning problems in the small data regime can be solved more accurately and efficiently.

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。

↑