Deep-learning of Parametric Partial Differential Equations from Sparse and Noisy Data

Data-driven methods have recently made great progress in the discovery of partial differential equations (PDEs) from spatial-temporal data. However, several challenges remain to be solved, including sparse noisy data, incomplete candidate library, and spatially- or temporally-varying coefficients. In this work, a new framework, which combines neural network, genetic algorithm and adaptive methods, is put forward to address all of these challenges simultaneously. In the framework, a trained neural network is utilized to calculate derivatives and generate a large amount of meta-data, which solves the problem of sparse noisy data. Next, genetic algorithm is utilized to discover the form of PDEs and corresponding coefficients with an incomplete candidate library. Finally, a two-step adaptive method is introduced to discover parametric PDEs with spatially- or temporally-varying coefficients. In this method, the structure of a parametric PDE is first discovered, and then the general form of varying coefficients is identified. The proposed algorithm is tested on the Burgers equation, the convection-diffusion equation, the wave equation, and the KdV equation. The results demonstrate that this method is robust to sparse and noisy data, and is able to discover parametric PDEs with an incomplete candidate library.

[1]  S. Brunton,et al.  Discovering governing equations from data by sparse identification of nonlinear dynamical systems , 2015, Proceedings of the National Academy of Sciences.

[2]  H. Schaeffer,et al.  Learning partial differential equations via data discovery and sparse optimization , 2017, Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[3]  Aaas News,et al.  Book Reviews , 1893, Buffalo Medical and Surgical Journal.

[4]  Roman O. Grigoriev,et al.  Data-driven discovery of partial differential equation models with latent variables , 2019, Physical review. E.

[5]  Guang Lin,et al.  Robust data-driven discovery of governing physical laws with error bars , 2018, Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[6]  Feng Xu,et al.  Data-driven Discovery of Partial Differential Equations for Multiple-Physics Electromagnetic Problem , 2019, 1910.13531.

[7]  Kailiang Wu,et al.  Data-Driven Deep Learning of Partial Differential Equations in Modal Space , 2020, J. Comput. Phys..

[8]  Hao Xu,et al.  DLGA-PDE: Discovery of PDEs with incomplete candidate library via combination of deep learning and genetic algorithm , 2020, J. Comput. Phys..

[9]  Bin Dong,et al.  PDE-Net 2.0: Learning PDEs from Data with A Numeric-Symbolic Hybrid Deep Network , 2018, J. Comput. Phys..

[10]  Anna V. Kaluzhnaya,et al.  Data-driven PDE discovery with evolutionary approach , 2019, ICCS.

[11]  Steven L. Brunton,et al.  Data-Driven Identification of Parametric Partial Differential Equations , 2018, SIAM J. Appl. Dyn. Syst..

[12]  Roman O Grigoriev,et al.  Robust and optimal sparse regression for nonlinear PDE models. , 2019, Chaos.

[13]  Haibin Chang,et al.  Machine learning subsurface flow equations from data , 2019, Computational Geosciences.

[14]  Hao Xu,et al.  DL-PDE: Deep-learning based data-driven discovery of partial differential equations from discrete and noisy data , 2019, Communications in Computational Physics.

[15]  Liping Wang,et al.  Data-driven discovery of free-form governing differential equations , 2019, ArXiv.

[16]  Maziar Raissi,et al.  Deep Hidden Physics Models: Deep Learning of Nonlinear Partial Differential Equations , 2018, J. Mach. Learn. Res..

[17]  Steven L. Brunton,et al.  Data-driven discovery of partial differential equations , 2016, Science Advances.

[18]  Hayden Schaeffer,et al.  Sparse model selection via integral terms. , 2017, Physical review. E.

[19]  Yan Chen,et al.  Data assimilation for transient flow in geologic formations via ensemble Kalman filter , 2006 .

[20]  Kailiang Wu,et al.  Data Driven Governing Equations Approximation Using Deep Neural Networks , 2018, J. Comput. Phys..

[21]  Haibin Chang,et al.  Identification of physical processes via combined data-driven and data-assimilation methods , 2018, J. Comput. Phys..