Finite Difference Neural Networks: Fast Prediction of Partial Differential Equations
@article{Shi2020FiniteDN,
title={Finite Difference Neural Networks: Fast Prediction of Partial Differential Equations},
author={Zheng Shi and Nur Sila Gulgec and Albert S. Berahas and Shamim N. Pakzad and Martin Tak{\'a}c},
journal={2020 19th IEEE International Conference on Machine Learning and Applications (ICMLA)},
year={2020},
pages={130-135}
}Discovering the underlying behavior of complex systems is an important topic in many science and engineering disciplines. In this paper, we propose a novel neural network framework, finite difference neural networks (FD-Net), to learn partial differential equations from data. Specifically, our proposed finite difference inspired network is designed to learn the underlying governing partial differential equations from trajectory data, and to iteratively estimate the future dynamical behavior…
Figures and Tables from this paper
figure 1 
table 1 
figure 2 
table 2 
figure 3 
figure 4 
figure 5 
figure 6 
figure 7 
figure 8 
figure 9 
figure 10 
figure 11 
figure 12 
figure 13 
figure 14 
figure 15 
figure 16 
figure 17 
figure 18 
figure 19 
figure 20 
figure 21 
figure 22 
figure 23 
figure 24 
figure 25 
figure 26 
figure 27 
figure 28 
figure 29 
figure 30 
figure 31 
figure 32 
figure 33 
figure 34 
figure 35 
figure 36 
figure 37 
figure 38 
figure 39 
figure 40 
figure 41 
figure 42 
figure 43 
figure 44 
figure 45 
figure 46 
figure 47 
figure 48
2 Citations
Learning time-dependent PDE solver using Message Passing Graph Neural Networks
- Computer ScienceArXiv
- 2022
A discretization and domain invariant neural network time-dependent PDE solver based on message passing graph neural nets (MPGNN) which is trained on a sample domain with different discretizations, although the underlying physics remains to be the same.
Accelerated Training of Physics Informed Neural Networks (PINNs) using Meshless Discretizations
- Computer Science
- 2022
This work presents a new technique for the accelerated training of PINNs that combines modern scientific computing techniques with machine learning: discretely-trained PINNs (DT-PINNs), and shows that fp64 DT- PINNs offer a superior cost-accuracy profloating-point to fp32 vanilla-pinNs, opening the door to a new paradigm of leveraging scienti fiC computing techniques to support machine learning.
References
SHOWING 1-10 OF 27 REFERENCES
Learning partial differential equations via data discovery and sparse optimization
- Computer ScienceProceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences
- 2017
This work develops a learning algorithm to identify the terms in the underlying partial differential equations and to approximate the coefficients of the terms only using data, which uses sparse optimization in order to perform feature selection and parameter estimation.
Physics Informed Deep Learning (Part II): Data-driven Discovery of Nonlinear Partial Differential Equations
- Computer ScienceArXiv
- 2017
We introduce physics informed neural networks -- neural networks that are trained to solve supervised learning tasks while respecting any given law of physics described by general nonlinear partial…
Neural Ordinary Differential Equations
- Computer ScienceNeurIPS
- 2018
This work shows how to scalably backpropagate through any ODE solver, without access to its internal operations, which allows end-to-end training of ODEs within larger models.
Hidden physics models: Machine learning of nonlinear partial differential equations
- Computer ScienceJ. Comput. Phys.
- 2018
Data-driven discovery of partial differential equations
- MathematicsScience Advances
- 2017
The sparse regression method is computationally efficient, robust, and demonstrated to work on a variety of canonical problems spanning a number of scientific domains including Navier-Stokes, the quantum harmonic oscillator, and the diffusion equation.
PDE-Net: Learning PDEs from Data
- Computer ScienceICML
- 2018
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.
Deep Learning the Physics of Transport Phenomena
- Computer ScienceArXiv
- 2017
We have developed a new data-driven paradigm for the rapid inference, modeling and simulation of the physics of transport phenomena by deep learning. Using conditional generative adversarial networks…
PDE-Net 2.0: Learning PDEs from Data with A Numeric-Symbolic Hybrid Deep Network
- Computer ScienceJ. Comput. Phys.
- 2019
Automated reverse engineering of nonlinear dynamical systems
- Computer ScienceProceedings of the National Academy of Sciences
- 2007
This work introduces for the first time a method that can automatically generate symbolic equations for a nonlinear coupled dynamical system directly from time series data, applicable to any system that can be described using sets of ordinary nonlinear differential equations.
Numerical solution of partial differential equations
- Mathematics
- 2013
Numerical solution of PDEs is rich and active field of modern applied mathematics. The steady growth of the subject is stimulated by everincreasing demands from the natural sciences, engineering and…