# 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

- Computer ScienceJ. Mach. Learn. Res.
- 2018

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

- Computer ScienceCommunications in Computational Physics
- 2022

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.

### Deep learning of dynamics and signal-noise decomposition with time-stepping constraints

- Computer ScienceJ. Comput. Phys.
- 2019

### Machine Learning of Space-Fractional Differential Equations

- Computer Science, MathematicsSIAM J. Sci. Comput.
- 2019

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

- Computer Science, MathematicsArXiv
- 2021

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.

- Computer ScienceChaos
- 2020

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

- Computer ScienceJournal of Computational Physics
- 2018

### Physics-informed machine learning for reduced-order modeling of nonlinear problems

- Computer ScienceJ. Comput. Phys.
- 2021

### Discovery of Dynamics Using Linear Multistep Methods

- MathematicsSIAM J. Numer. Anal.
- 2021

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

- Computer ScienceArXiv
- 2019

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.