Interpretable learning of effective dynamics for multiscale systems
OPEN ACCESS
Loading...
Author / Producer
Date
2025-01
Publication Type
Journal Article
ETH Bibliography
yes
Citations
Altmetric
OPEN ACCESS
Data
Rights / License
Abstract
The modelling and simulation of high-dimensional multiscale systems is a critical challenge across all areas of science and engineering. It is broadly believed that even with today's computer advances resolving all spatio-temporal scales described by the governing equations remains a remote target. This realization has prompted intense efforts to develop model-order reduction techniques. In recent years, techniques based on deep recurrent neural networks (RNNs) have produced promising results for the modelling and simulation of complex spatiotemporal systems and offer large flexibility in model development as they can incorporate experimental and computational data. However, neural networks lack interpretability, which limits their utility and generalizability across complex systems. Here, we propose a novel framework of interpretable learning effective dynamics (iLED) that offers comparable accuracy to state-of-the-art RNN-based approaches while providing the added benefit of interpretability. The iLED framework is motivated by Mori-Zwanzig and Koopman operator (KO) theory, which justifies the choice of the specific architecture. We demonstrate the effectiveness of the proposed framework in simulations of three benchmark multiscale systems. Our results show that the iLED framework can generate accurate predictions and obtain interpretable dynamics, making it a promising approach for solving high-dimensional multiscale systems.
Permanent link
Publication status
published
External links
Editor
Book title
Journal / series
Volume
481 (2305)
Pages / Article No.
20240167
Publisher
Royal Society
Event
Edition / version
Methods
Software
Geographic location
Date collected
Date created
Subject
model-order reduction; interpretability; neural networks; Koopman operator; multiscale systems
Organisational unit
Notes
Funding
956201 - Data Driven Computational Mechanics at EXascale (EC)