RefreshNet: learning multiscale dynamics through hierarchical refreshing

Forecasting complex system dynamics, particularly for long-term predictions, is persistently hindered by error accumulation and computational burdens. This study presents RefreshNet, a multiscale framework developed to overcome these challenges, delivering an unprecedented balance between computatio...

Full description

Saved in:
Bibliographic Details
Published in:Nonlinear dynamics 2024-08, Vol.112 (16), p.14479-14496
Main Authors: Farooq, Junaid, Rafiq, Danish, Vlachas, Pantelis R., Bazaz, Mohammad Abid
Format: Article
Language:English
Subjects:
Accumulation
Accuracy
Automotive Engineering
Classical Mechanics
Complex systems
Computational efficiency
Control
Dynamical Systems
Engineering
Error analysis
Forecasting
Mechanical Engineering
Reaction-diffusion equations
Recurrent neural networks
System dynamics
Vibration
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Forecasting complex system dynamics, particularly for long-term predictions, is persistently hindered by error accumulation and computational burdens. This study presents RefreshNet, a multiscale framework developed to overcome these challenges, delivering an unprecedented balance between computational efficiency and predictive accuracy. RefreshNet incorporates convolutional autoencoders to identify a reduced order latent space capturing essential features of the dynamics, and strategically employs multiple recurrent neural network blocks operating at varying temporal resolutions within the latent space, thus allowing the capture of latent dynamics at multiple temporal scales. The unique “refreshing” mechanism in RefreshNet allows coarser blocks to reset inputs of finer blocks, effectively controlling and alleviating error accumulation. This design demonstrates superiority over existing techniques regarding computational efficiency and predictive accuracy, especially in long-term forecasting. The framework is validated using three benchmark applications: the FitzHugh–Nagumo system, the Reaction–Diffusion equation, and Kuramoto–Sivashinsky dynamics. RefreshNet significantly outperforms state-of-the-art methods in long-term forecasting accuracy and speed, marking a significant advancement in modeling complex systems and opening new avenues in understanding and predicting their behavior.
ISSN:0924-090X
1573-269X
DOI:10.1007/s11071-024-09813-3