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

Gelbrecht, M., Lucarini, V. ORCID: https://orcid.org/0000-0001-9392-1471, Boers, N. and Kurths, J. (2021) Analysis of a bistable climate toy model with physics-based machine learning methods. The European Physical Journal Special Topics, 230. pp. 3121-3131. ISSN 1951-6355 doi: 10.1140/epjs/s11734-021-00175-0

Abstract/Summary

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.

Item Type	Article
URI	https://reading-clone.eprints-hosting.org/id/eprint/98670
Identification Number/DOI	10.1140/epjs/s11734-021-00175-0
Refereed	Yes
Divisions	Interdisciplinary Research Centres (IDRCs) > Centre for the Mathematics of Planet Earth (CMPE) Science > School of Mathematical, Physical and Computational Sciences > Department of Mathematics and Statistics
Publisher	Springer
Download/View statistics	View download statistics for this item