Communications in Information and Systems

Volume 22 (2022)

Number 2

Neural-PDE: a RNN based neural network for solving time dependent PDEs

Pages: 223 – 245

DOI: https://dx.doi.org/10.4310/CIS.2022.v22.n2.a3

Authors

Yihao Hu (Department of Applied and Computational Mathematics, and Statistics, University of Notre Dame, Indiana, U.S.A.)

Tong Zhao (Department of Applied and Computer Science and Engineering, University of Notre Dame, Indiana, U.S.A.)

Shixin Xu (Duke Kunshan University, Kunshan, Jiangsu, China)

Lizhen Lin (Department of Applied and Computational Mathematics, and Statistics, University of Notre Dame, Indiana, U.S.A.)

Zhiliang Xu (Department of Applied and Computational Mathematics, and Statistics, University of Notre Dame, Indiana, U.S.A.)

Abstract

Partial differential equations (PDEs) play a crucial role in studying a vast number of problems in science and engineering. Numerically solving nonlinear and/or high-dimensional PDEs is frequently a challenging task. Inspired by the traditional finite difference and finite elements methods and emerging advancements in machine learning, we propose a sequence-to-sequence learning (Seq2Seq) framework called Neural-PDE, which allows one to automatically learn governing rules of any time-dependent PDE system from existing data by using a bidirectional LSTM encoder, and predict the solutions in next $n$ time steps. One critical feature of our proposed framework is that the Neural-PDE is able to simultaneously learn and simulate all variables of interest in a PDE system. We test the Neural-PDE by a range of examples, from one-dimensional PDEs to a multi-dimensional and nonlinear complex fluids model. The results show that the Neural-PDE is capable of learning the initial conditions, boundary conditions and differential operators defining the initial-boundary-value problem of a PDE system without the knowledge of the specific form of the PDE system. In our experiments, the Neural-PDE can efficiently extract the dynamics within 20 epochs training and produce accurate predictions. Furthermore, unlike the traditional machine learning approaches for learning PDEs, such as CNN and MLP, which require great quantity of parameters for model precision, the Neural-PDE shares parameters among all time steps, and thus considerably reduces computational complexity and leads to a fast learning algorithm.

Full Text (PDF format)

Received 26 October 2021

Published 19 May 2022