Predicting dynamical system evolution with residual neural networks

10/11/2019
by   Artem Chashchin, et al.
0

Forecasting time series and time-dependent data is a common problem in many applications. One typical example is solving ordinary differential equation (ODE) systems ẋ=F(x). Oftentimes the right hand side function F(x) is not known explicitly and the ODE system is described by solution samples taken at some time points. Hence, ODE solvers cannot be used. In this paper, a data-driven approach to learning the evolution of dynamical systems is considered. We show how by training neural networks with ResNet-like architecture on the solution samples, models can be developed to predict the ODE system solution further in time. By evaluating the proposed approaches on three test ODE systems, we demonstrate that the neural network models are able to reproduce the main dynamics of the systems qualitatively well. Moreover, the predicted solution remains stable for much longer times than for other currently known models.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/16/2019

Matrix Lie Maps and Neural Networks for Solving Differential Equations

The coincidence between polynomial neural networks and matrix Lie maps i...
research
08/19/2020

Augmenting Neural Differential Equations to Model Unknown Dynamical Systems with Incomplete State Information

Neural Ordinary Differential Equations replace the right-hand side of a ...
research
08/12/2021

Prediction of dynamical systems using geometric constraints imposed by observations

Solution of Ordinary Differential Equation (ODE) model of dynamical syst...
research
12/19/2017

Bilinear residual Neural Network for the identification and forecasting of dynamical systems

Due to the increasing availability of large-scale observation and simula...
research
05/09/2022

Auto-SDE: Learning effective reduced dynamics from data-driven stochastic dynamical systems

Multiscale stochastic dynamical systems have been widely adopted to scie...
research
02/12/2023

SpReME: Sparse Regression for Multi-Environment Dynamic Systems

Learning dynamical systems is a promising avenue for scientific discover...
research
06/26/2023

TaylorPDENet: Learning PDEs from non-grid Data

Modeling data obtained from dynamical systems has gained attention in re...

Please sign up or login with your details

Forgot password? Click here to reset