Convolutional autoencoder and conditional random fields hybrid for predicting 
spatial-temporal chaos

Herzog, S.; Wörgötter, F.; Parlitz, Ulrich

doi:10.1063/1.5124926

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

Convolutional autoencoder and conditional random fields hybrid for predicting spatial-temporal chaos

MPS-Authors

/persons/resource/persons173613

Parlitz, Ulrich
Research Group Biomedical Physics, Max Planck Institute for Dynamics and Self-Organization, Max Planck Society;

External Resource

There are no locators available

Fulltext (restricted access)

There are currently no full texts shared for your IP range.

フルテキスト (公開)

公開されているフルテキストはありません

付随資料 (公開)

There is no public supplementary material available

引用

Herzog, S., Wörgötter, F., & Parlitz, U. (2019). Convolutional autoencoder and conditional random fields hybrid for predicting spatial-temporal chaos. Chaos, 29(12):. doi:10.1063/1.5124926.

引用: https://hdl.handle.net/21.11116/0000-0005-8106-2

要旨

We present an approach for data-driven prediction of high-dimensional chaotic time series generated by spatially-extended systems. The algorithm employs a convolutional autoencoder for dimension reduction and feature extraction combined with a probabilistic prediction scheme operating in the feature space, which consists of a conditional random field. The future evolution of the spatially-extended system is predicted using a feedback loop and iterated predictions. The excellent performance of this method is illustrated and evaluated using Lorenz-96 systems and Kuramoto-Sivashinsky equations of different size generating time series of different dimensionality and complexity.