Guardado en:
Detalles Bibliográficos
Autores principales: Fleddermann, Luk, Parlitz, Ulrich, Wellecke, Gerrit
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2504.05512
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908646248546304
author Fleddermann, Luk
Parlitz, Ulrich
Wellecke, Gerrit
author_facet Fleddermann, Luk
Parlitz, Ulrich
Wellecke, Gerrit
contents Reservoir computers can be used to predict time series generated by spatio-temporal chaotic systems. Using multiple reservoirs in parallel has shown improved performances for these predictions, by effectively reducing the input dimensionality of each reservoir. Similarly, one may further reduce the dimensionality of the input data by transforming to a lower-dimensional latent space. Combining both approaches, we show that using dimensionality-reduced latent space predictions for parallel reservoir computing not only reduces computational costs, but also leads to better prediction results for small to medium reservoir sizes. In the combined approach we further demonstrate that dimensionality reduction improves small-reservoir predictions regardless of noise contaminating the training data. The benefit of dimensionality-reduced parallel reservoir computing is illustrated and evaluated on the basis of the prediction of the one-dimensional Kuramoto-Sivashinsky equation.
format Preprint
id arxiv_https___arxiv_org_abs_2504_05512
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Improving the prediction of spatio-temporal chaos by combining parallel reservoir computing with dimensionality reduction
Fleddermann, Luk
Parlitz, Ulrich
Wellecke, Gerrit
Chaotic Dynamics
Computational Physics
Reservoir computers can be used to predict time series generated by spatio-temporal chaotic systems. Using multiple reservoirs in parallel has shown improved performances for these predictions, by effectively reducing the input dimensionality of each reservoir. Similarly, one may further reduce the dimensionality of the input data by transforming to a lower-dimensional latent space. Combining both approaches, we show that using dimensionality-reduced latent space predictions for parallel reservoir computing not only reduces computational costs, but also leads to better prediction results for small to medium reservoir sizes. In the combined approach we further demonstrate that dimensionality reduction improves small-reservoir predictions regardless of noise contaminating the training data. The benefit of dimensionality-reduced parallel reservoir computing is illustrated and evaluated on the basis of the prediction of the one-dimensional Kuramoto-Sivashinsky equation.
title Improving the prediction of spatio-temporal chaos by combining parallel reservoir computing with dimensionality reduction
topic Chaotic Dynamics
Computational Physics
url https://arxiv.org/abs/2504.05512