Khovanov, I. A. (2021) Data for Stochastic approach for assessing the predictability of chaotic time-series using reservoir computing. [Dataset]

	Archive (ZIP) (Dataset file) WRAP_dataset_153069.zip - Published Version Available under License Creative Commons Attribution 4.0. Download (16Mb)
	Plain Text (Readme file) readme.txt - Published Version Available under License Creative Commons Attribution 4.0. Download (1660b)

Request Changes to record.

Abstract

The applicability of machine learning for predicting chaotic dynamics relies heavily upon the data used in the training stage. Chaotic time series obtained by numerically solving ordinary differential equations embed a complicated noise of the applied numerical scheme. Such a dependence of the solution on the numeric scheme leads to an inadequate representation of the real chaotic system. A stochastic approach for generating training time series and characterizing their predictability is suggested to address this problem. The approach is applied for analyzing two chaotic systems with known properties, the Lorenz system and the Anishchenko–Astakhov generator. Additionally, the approach is extended to critically assess a reservoir computing model used for chaotic time series prediction. Limitations of reservoir computing for surrogate modeling of chaotic systems are highlighted.

Item Type:	Dataset
Subjects:	Q Science > Q Science (General) T Technology > T Technology (General)
Divisions:	Faculty of Science, Engineering and Medicine > Engineering > Engineering
Type of Data:	Simulation Data
Library of Congress Subject Headings (LCSH):	Chaotic behavior in systems, Machine learning, Neural networks (Computer science), Industry 4.0
Publisher:	University of Warwick, School of Engineering
Official Date:	20 July 2021
Dates:	Date Event 20 July 2021 Published 20 July 2021 Available 25 May 2021 Created
Status:	Not Peer Reviewed
Publication Status:	Published
Media of Output (format):	ASCII format
Access rights to Published version:	Open Access (Creative Commons)
Copyright Holders:	University of Warwick
Description:	Dataset consists of a set of folders for figures shown in the paper. Data are included in ASCII format. Each folder contains file "comment.txt" with relevant to each figure information. File 'comment_on_numerical_methods.pdf' is a brief description of the used numerical methods.
Date of first compliant deposit:	20 July 2021
Date of first compliant Open Access:	20 July 2021
Related URLs:	Other Related item in WRAP
Contributors:	Contribution Name Contributor ID Depositor Khovanov, I. A. 29260

Request changes or add full text files to a record

Repository staff actions (login required)

View Item

Downloads