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

Gelbrecht, Maximilian; Lucarini, Valerio; Boers, Niklas; Kurths, Jürgen

doi:10.1140/epjs/s11734-021-00175-0

アイテム詳細

登録内容を編集ファイル形式で保存

一時保存へ追加

タグ情報を表示リリース履歴を表示詳細要約

公開

学術論文

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

Authors

/persons/resource/gelbrecht

Gelbrecht, Maximilian
Potsdam Institute for Climate Impact Research;

Lucarini, Valerio
External Organizations;

/persons/resource/Niklas.Boers

Boers, Niklas
Potsdam Institute for Climate Impact Research;

/persons/resource/Juergen.Kurths

Kurths, Jürgen
Potsdam Institute for Climate Impact Research;

URL

There are no locators available

フルテキスト (公開)

25715oa.pdf
(出版社版), 981KB

付随資料 (公開)

There is no public supplementary material available

引用

Gelbrecht, M., Lucarini, V., Boers, N., & Kurths, J. (2021). Analysis of a bistable climate toy model with physics-based machine learning methods. European Physical Journal - Special Topics, 230(13-15), 3121-3131. doi:10.1140/epjs/s11734-021-00175-0.

引用: https://publications.pik-potsdam.de/pubman/item/item_25715

要旨

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.