Moving sampling physics-informed neural networks induced by moving mesh PDE.

Journal: Neural networks : the official journal of the International Neural Network Society
Published Date:

Abstract

In this work, we propose an end-to-end adaptive sampling framework based on deep neural networks and the moving mesh method (MMPDE-Net), which can adaptively generate new sampling points by solving the moving mesh PDE. This model focuses on improving the quality of sampling points generation. Moreover, we develop an iterative algorithm based on MMPDE-Net, which makes sampling points distribute more precisely and controllably. Since MMPDE-Net is independent of the deep learning solver, we combine it with physics-informed neural networks (PINN) to propose moving sampling PINN (MS-PINN) and show the error estimate of our method under some assumptions. Finally, we demonstrate the performance improvement of MS-PINN compared to PINN through numerical experiments of four typical examples, which numerically verify the effectiveness of our method.

Authors

  • Yu Yang
    Department of Obstetrics & Gynecology, the First Affiliated Hospital of Xi'an Jiaotong University, Xian, Shaanxi, China.
  • Qihong Yang
    School of Mathematics, Sichuan University, 610065, Chengdu, China. Electronic address: yangqh@stu.scu.edu.cn.
  • Yangtao Deng
    School of Mathematics, Sichuan University, 610065, Chengdu, China. Electronic address: ytdeng1998@foxmail.com.
  • Qiaolin He
    School of Mathematics, Sichuan University, 610065, Chengdu, China. Electronic address: qlhejenny@scu.edu.cn.