Reservoir time series analysis: Using the response of complex dynamical systems as a universal indicator of change

Journal Article

Braden Thorne

Authors: Thorne, Braden Jüngling, Thomas Small, Michael Corrêa, Débora Zaitouny, Ayham

2022-02-10

Publication

Chaos, 32(3), [033109]

32

This paper was selected as an editor pick
Published under an exclusive license by AIP Publishing

Quality Indicators

Peer Reviewed

Q1 Journal as rated in SJR

This paper was selected as an editor's pick

Relevance to the Centre

Reservoir time series analysis (RTSA), is a method by which the state space representation generated by a reservoir computing (RC) model can be used for time series analysis. Compared to several benchmark approaches, Braden can show significant, generalised accuracy across the proposed RTSA features that surpass the benchmark methods. Braden uses this method for bearing fault distinction to motivate using RTSA in application.

DOI: 10.1063/5.0082122