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 2006.13305physics.geo-phcs.LGeess.IVstat.ML
收藏

基于理论引导的生成对抗网络的动态地下水流深度学习

Deep Learning of Dynamic Subsurface Flow via Theory-guided Generative Adversarial Network

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

Tianhao He, Dongxiao Zhang

摘要:

生成式对抗网络(GAN)由于其强大的学习复杂数据分布的能力,在图像识别、文本处理和科学计算等领域有着广泛的应用。在这项研究中,提出了一种理论指导的生成对抗网络(TgGAN)来求解动态偏微分方程(PDE)。与标准GANs不同,训练项不再是真实数据和生成的数据,而是它们的残差。此外,控制方程、其他物理约束和工程控制等理论被编码到生成器的损失函数中,以确保预测不仅遵守训练数据,而且遵守这些理论。TgGAN被提出用于具有非均匀模型参数的动态地下流,并且每个时间步的数据被处理为二维图像。在这项研究中,几个数值的情况下,介绍了测试的TgGAN的性能。TgGAN模型可以很容易地实现对未来响应的预测、无标签学习和噪声数据学习。文中还讨论了训练数据的个数和配点的影响。为了提高TgGAN的效率,还采用了迁移学习算法。数值结果表明,TgGAN模型对于动态偏微分方程的深度学习是鲁棒和可靠的。

英文摘要:

Generative adversarial network (GAN) has been shown to be useful in various applications, such as image recognition, text processing and scientific computing, due its strong ability to learn complex data distributions. In this study, a theory-guided generative adversarial network (TgGAN) is proposed to solve dynamic partial differential equations (PDEs). Different from standard GANs, the training term is no longer the true data and the generated data, but rather their residuals. In addition, such theories as governing equations, other physical constraints and engineering controls, are encoded into the loss function of the generator to ensure that the prediction does not only honor the training data, but also obey these theories. TgGAN is proposed for dynamic subsurface flow with heterogeneous model parameters, and the data at each time step are treated as a two-dimensional image. In this study, several numerical cases are introduced to test the performance of the TgGAN. Predicting the future response, label-free learning and learning from noisy data can be realized easily by the TgGAN model. The effects of the number of training data and the collocation points are also discussed. In order to improve the efficiency of TgGAN, the transfer learning algorithm is also employed. Numerical results demonstrate that the TgGAN model is robust and reliable for deep learning of dynamic PDEs.

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。

↑