Analysis of a bistable climate toy model with physics-based machine learning methods

Maximilian Gelbrecht, Valerio Lucarini, Niklas Boers, Jürgen Kurths

Research output: Contribution to journalArticlepeer-review

6 Scopus citations

Abstract

We propose a comprehensive framework able to address both the predictability of the first and of the second kind for high-dimensional chaotic models. For this purpose, we analyse the properties of a newly introduced multistable climate toy model constructed by coupling the Lorenz ’96 model with a zero-dimensional energy balance model. First, the attractors of the system are identified with Monte Carlo Basin Bifurcation Analysis. Additionally, we are able to detect the Melancholia state separating the two attractors. Then, Neural Ordinary Differential Equations are applied to predict the future state of the system in both of the identified attractors.

Original languageEnglish
Pages (from-to)3121-3131
Number of pages11
JournalEuropean Physical Journal: Special Topics
Volume230
Issue number14-15
DOIs
StatePublished - Oct 2021
Externally publishedYes

Fingerprint

Dive into the research topics of 'Analysis of a bistable climate toy model with physics-based machine learning methods'. Together they form a unique fingerprint.

Cite this