Discovery of subdiffusion problem with noisy data via deep learning

@article{Xu2022DiscoveryOS,
  title={Discovery of subdiffusion problem with noisy data via deep learning},
  author={Xingjian Xu and Minghua Chen},
  journal={J. Sci. Comput.},
  year={2022},
  volume={92},
  pages={23}
}
Data-driven discovery of partial differential equations (PDEs) from observed data in machine learning has been developed by embedding the discovery problem. Recently, the discovery of traditional ODEs dynamics using linear multistep methods in deep learning have been discussed in [Racheal and Du, SIAM J. Numer. Anal. 59 (2021) 429-455; Du et al. arXiv:2103.11488]. We extend this framework to the data-driven discovery of the timefractional PDEs, which can effectively characterize the ubiquitous… 

References

SHOWING 1-10 OF 31 REFERENCES

Deep Hidden Physics Models: Deep Learning of Nonlinear Partial Differential Equations

  • M. Raissi
  • Computer Science
    J. Mach. Learn. Res.
  • 2018
TLDR
This work puts forth a deep learning approach for discovering nonlinear partial differential equations from scattered and potentially noisy observations in space and time by approximate the unknown solution as well as the nonlinear dynamics by two deep neural networks.

Convergence Rate Analysis for Deep Ritz Method

TLDR
A rigorous numerical analysis on deep Ritz method (DRM) for second order elliptic equations with Neumann boundary conditions is provided and the first nonasymptotic convergence rate in H norm for DRM is established using deep networks with ReLU activation functions.

Machine Learning of Space-Fractional Differential Equations

TLDR
This work provides a user-friendly and feasible way to perform fractional derivatives of kernels, via a unified set of d-dimensional Fourier integral formulas amenable to generalized Gauss-Laguerre quadrature.

A Deep Learning Based Discontinuous Galerkin Method for Hyperbolic Equations with Discontinuous Solutions and Random Uncertainties

TLDR
The D2GM is found numerically to be first-order and second-order accurate for (stochastic) linear conservation law with smooth solutions using piecewise constant and piecewise linear basis functions, respectively.

Solving Fokker-Planck equation using deep learning.

TLDR
Penalty factors are introduced to overcome the local optimization for the deep learning approach to solve the general FP equations based on deep neural networks, and the corresponding setting rules are given.

DGM: A deep learning algorithm for solving partial differential equations

Discovery of Dynamics Using Linear Multistep Methods

TLDR
This work establishes for the first time a rigorous framework based on refined notions of consistency and stability to yield convergence using LMMs for discovery for discovery of inverse dynamics.

A comparative study of physics-informed neural network models for learning unknown dynamics and constitutive relations

TLDR
The results indicate that the accuracy of the trained neural network models is much higher for the cases where the authors only have to learn a constitutive relation instead of the whole dynamics, corroborates the well-known fact from scientific computing that building as much structural information is available into an algorithm can enhance its efficiency and/or accuracy.