Extrapolating tipping points and simulating non-stationary dynamics of complex systems using efficient machine learning
Abstract Model-free and data-driven prediction of tipping point transitions in nonlinear dynamical systems is a challenging and outstanding task in complex systems science. We propose a novel, fully data-driven machine learning algorithm based on next-generation reservoir computing to extrapolate th...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Portfolio
2024-01-01
|
Series: | Scientific Reports |
Online Access: | https://doi.org/10.1038/s41598-023-50726-9 |
_version_ | 1797363420077490176 |
---|---|
author | Daniel Köglmayr Christoph Räth |
author_facet | Daniel Köglmayr Christoph Räth |
author_sort | Daniel Köglmayr |
collection | DOAJ |
description | Abstract Model-free and data-driven prediction of tipping point transitions in nonlinear dynamical systems is a challenging and outstanding task in complex systems science. We propose a novel, fully data-driven machine learning algorithm based on next-generation reservoir computing to extrapolate the bifurcation behavior of nonlinear dynamical systems using stationary training data samples. We show that this method can extrapolate tipping point transitions. Furthermore, it is demonstrated that the trained next-generation reservoir computing architecture can be used to predict non-stationary dynamics with time-varying bifurcation parameters. In doing so, post-tipping point dynamics of unseen parameter regions can be simulated. |
first_indexed | 2024-03-08T16:20:07Z |
format | Article |
id | doaj.art-1781a643ff1f4af78d5198d530b066c1 |
institution | Directory Open Access Journal |
issn | 2045-2322 |
language | English |
last_indexed | 2024-03-08T16:20:07Z |
publishDate | 2024-01-01 |
publisher | Nature Portfolio |
record_format | Article |
series | Scientific Reports |
spelling | doaj.art-1781a643ff1f4af78d5198d530b066c12024-01-07T12:22:20ZengNature PortfolioScientific Reports2045-23222024-01-0114111210.1038/s41598-023-50726-9Extrapolating tipping points and simulating non-stationary dynamics of complex systems using efficient machine learningDaniel Köglmayr0Christoph Räth1German Aerospace Center (DLR), Institute for AI Safety and SecurityGerman Aerospace Center (DLR), Institute for AI Safety and SecurityAbstract Model-free and data-driven prediction of tipping point transitions in nonlinear dynamical systems is a challenging and outstanding task in complex systems science. We propose a novel, fully data-driven machine learning algorithm based on next-generation reservoir computing to extrapolate the bifurcation behavior of nonlinear dynamical systems using stationary training data samples. We show that this method can extrapolate tipping point transitions. Furthermore, it is demonstrated that the trained next-generation reservoir computing architecture can be used to predict non-stationary dynamics with time-varying bifurcation parameters. In doing so, post-tipping point dynamics of unseen parameter regions can be simulated.https://doi.org/10.1038/s41598-023-50726-9 |
spellingShingle | Daniel Köglmayr Christoph Räth Extrapolating tipping points and simulating non-stationary dynamics of complex systems using efficient machine learning Scientific Reports |
title | Extrapolating tipping points and simulating non-stationary dynamics of complex systems using efficient machine learning |
title_full | Extrapolating tipping points and simulating non-stationary dynamics of complex systems using efficient machine learning |
title_fullStr | Extrapolating tipping points and simulating non-stationary dynamics of complex systems using efficient machine learning |
title_full_unstemmed | Extrapolating tipping points and simulating non-stationary dynamics of complex systems using efficient machine learning |
title_short | Extrapolating tipping points and simulating non-stationary dynamics of complex systems using efficient machine learning |
title_sort | extrapolating tipping points and simulating non stationary dynamics of complex systems using efficient machine learning |
url | https://doi.org/10.1038/s41598-023-50726-9 |
work_keys_str_mv | AT danielkoglmayr extrapolatingtippingpointsandsimulatingnonstationarydynamicsofcomplexsystemsusingefficientmachinelearning AT christophrath extrapolatingtippingpointsandsimulatingnonstationarydynamicsofcomplexsystemsusingefficientmachinelearning |