Motivated by recent research on Physics-Informed Neural Networks (PINNs), we make the first attempt to introduce the PINNs for numerical simulation of the elliptic Partial Differential Equations (PDEs) on 3D manifolds. PINNs are one of the deep learning-based techniques. Based on the data and physical models, PINNs introduce the standard feedforward neural networks (NNs) to approximate the solutions to the PDE systems. By using automatic differentiation, the PDEs system could be explicitly encoded into NNs and consequently, the sum of mean squared residuals from PDEs could be minimized with respect to the NN parameters. In this study, the residual in the loss function could be constructed validly by using the automatic differentiation because of the relationship between the surface differential operators $\nabla_S/\Delta_S$ and the standard Euclidean differential operators $\nabla/\Delta$. We first consider the unit sphere as surface to investigate the numerical accuracy and convergence of the PINNs with different training example sizes and the depth of the NNs. Another examples are provided with different complex manifolds to verify the robustness of the PINNs.
翻译:根据最近对物理成份神经网络(PINNs)的研究,我们首次尝试采用PINNs, 以对3D 参数进行椭圆部分差异等同(PDEs)的数值模拟。 PINNs是深层次的学习技术之一。根据数据和物理模型,PINNs采用标准进料向神经网络(NNs),以近似PDE系统的解决方案。通过使用自动区分,PDEs系统可以明确地编码成NNWs,因此,PDEs的平均正方形残余的总和可以在NN参数方面最小化。在本研究中,损失函数的剩余部分可以通过使用自动区分法来有效构建,因为表面差分操作商$\nabla_S/\\Delta_S$和标准Euclidean差分解操作商$\nabla/\Delta$。我们首先将单元领域视为调查PINNS的数值准确性和趋同不同培训程度的实例。