PDE-Net

PDE-Net: Learning PDEs from Data. In this paper, we present an initial attempt to learn evolution PDEs from data. Inspired by the latest development of neural network designs in deep learning, we propose a new feed-forward deep network, called PDE-Net, to fulfill two objectives at the same time: to accurately predict dynamics of complex systems and to uncover the underlying hidden PDE models. The basic idea of the proposed PDE-Net is to learn differential operators by learning convolution kernels (filters), and apply neural networks or other machine learning methods to approximate the unknown nonlinear responses. Comparing with existing approaches, which either assume the form of the nonlinear response is known or fix certain finite difference approximations of differential operators, our approach has the most flexibility by learning both differential operators and the nonlinear responses. A special feature of the proposed PDE-Net is that all filters are properly constrained, which enables us to easily identify the governing PDE models while still maintaining the expressive and predictive power of the network. These constrains are carefully designed by fully exploiting the relation between the orders of differential operators and the orders of sum rules of filters (an important concept originated from wavelet theory). We also discuss relations of the PDE-Net with some existing networks in computer vision such as Network-In-Network (NIN) and Residual Neural Network (ResNet). Numerical experiments show that the PDE-Net has the potential to uncover the hidden PDE of the observed dynamics, and predict the dynamical behavior for a relatively long time, even in a noisy environment.


References in zbMATH (referenced in 34 articles , 1 standard article )

Showing results 1 to 20 of 34.
Sorted by year (citations)

1 2 next

  1. Forgione, Marco; Piga, Dario: Continuous-time system identification with neural networks: model structures and fitting criteria (2021)
  2. Kang, Sung Ha; Liao, Wenjing; Liu, Yingjie: IDENT: identifying differential equations with numerical time evolution (2021)
  3. Keller, Rachael T.; Du, Qiang: Discovery of dynamics using linear multistep methods (2021)
  4. Lu, Fei; Maggioni, Mauro; Tang, Sui: Learning interaction kernels in heterogeneous systems of agents from multiple trajectories (2021)
  5. Lu, Lu; Meng, Xuhui; Mao, Zhiping; Karniadakis, George Em: DeepXDE: a deep learning library for solving differential equations (2021)
  6. Patel, Ravi G.; Trask, Nathaniel A.; Wood, Mitchell A.; Cyr, Eric C.: A physics-informed operator regression framework for extracting data-driven continuum models (2021)
  7. Qin, Tong; Chen, Zhen; Jakeman, John D.; Xiu, Dongbin: Data-driven learning of nonautonomous systems (2021)
  8. Su, Wei-Hung; Chou, Ching-Shan; Xiu, Dongbin: Deep learning of biological models from data: applications to ODE models (2021)
  9. Arridge, S.; Hauptmann, A.: Networks for nonlinear diffusion problems in imaging (2020)
  10. Beck, Christian; Hornung, Fabian; Hutzenthaler, Martin; Jentzen, Arnulf; Kruse, Thomas: Overcoming the curse of dimensionality in the numerical approximation of Allen-Cahn partial differential equations via truncated full-history recursive multilevel Picard approximations (2020)
  11. Chen, Zhen; Wu, Kailiang; Xiu, Dongbin: Methods to recover unknown processes in partial differential equations using data (2020)
  12. Darbon, Jérôme; Langlois, Gabriel P.; Meng, Tingwei: Overcoming the curse of dimensionality for some Hamilton-Jacobi partial differential equations via neural network architectures (2020)
  13. Fan, Yuwei; Ying, Lexing: Solving electrical impedance tomography with deep learning (2020)
  14. Li, Yingzhou; Lu, Jianfeng; Mao, Anqi: Variational training of neural network approximations of solution maps for physical models (2020)
  15. Magiera, Jim; Ray, Deep; Hesthaven, Jan S.; Rohde, Christian: Constraint-aware neural networks for Riemann problems (2020)
  16. Puligilla, Shivakanth Chary; Jayaraman, Balaji: Assessment of end-to-end and sequential data-driven learning for non-intrusive modeling of fluid flows (2020)
  17. Schaeffer, Hayden; Tran, Giang; Ward, Rachel; Zhang, Linan: Extracting structured dynamical systems using sparse optimization with very few samples (2020)
  18. Uhlmann, Gunther; Wang, Yiran: Convolutional neural networks in phase space and inverse problems (2020)
  19. Wallbridge, James: Jets and differential linear logic (2020)
  20. Wu, Kailiang; Qin, Tong; Xiu, Dongbin: Structure-preserving method for reconstructing unknown Hamiltonian systems from trajectory data (2020)

1 2 next