English
 
Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Predicting the data structure prior to extreme events from passive observables using echo state network

Banerjee, A., Mishra, A., Dana, S. K., Hens, C., Kapitaniak, T., Kurths, J., Marwan, N. (2022): Predicting the data structure prior to extreme events from passive observables using echo state network. - Frontiers in Applied Mathematics and Statistics, 8, 955044.
https://doi.org/10.3389/fams.2022.955044

Item is

Files

show Files
hide Files
:
banerjee_2022_fams-08-955044.pdf (Publisher version), 2MB
Name:
banerjee_2022_fams-08-955044.pdf
Description:
-
Visibility:
Public
MIME-Type / Checksum:
application/pdf / [MD5]
Technical Metadata:
Copyright Date:
-
Copyright Info:
-

Locators

show

Creators

show
hide
 Creators:
Banerjee, Abhirup1, Author              
Mishra, Arindam2, Author
Dana, Syamal K.2, Author
Hens, Chittaranjan2, Author
Kapitaniak, Tomasz2, Author
Kurths, Jürgen1, Author              
Marwan, Norbert1, Author              
Affiliations:
1Potsdam Institute for Climate Impact Research, ou_persistent13              
2External Organizations, ou_persistent22              

Content

show
hide
Free keywords: -
 Abstract: Extreme events are defined as events that largely deviate from the nominal state of the system as observed in a time series. Due to the rarity and uncertainty of their occurrence, predicting extreme events has been challenging. In real life, some variables (passive variables) often encode significant information about the occurrence of extreme events manifested in another variable (active variable). For example, observables such as temperature, pressure, etc., act as passive variables in case of extreme precipitation events. These passive variables do not show any large excursion from the nominal condition yet carry the fingerprint of the extreme events. In this study, we propose a reservoir computation-based framework that can predict the preceding structure or pattern in the time evolution of the active variable that leads to an extreme event using information from the passive variable. An appropriate threshold height of events is a prerequisite for detecting extreme events and improving the skill of their prediction. We demonstrate that the magnitude of extreme events and the appearance of a coherent pattern before the arrival of the extreme event in a time series affect the prediction skill. Quantitatively, we confirm this using a metric describing the mean phase difference between the input time signals, which decreases when the magnitude of the extreme event is relatively higher, thereby increasing the predictability skill.

Details

show
hide
Language(s): eng - English
 Dates: 2022-10-202022-10-20
 Publication Status: Finally published
 Pages: 10
 Publishing info: -
 Table of Contents: -
 Rev. Type: Peer
 Identifiers: DOI: 10.3389/fams.2022.955044
MDB-ID: No data to archive
PIKDOMAIN: RD4 - Complexity Science
Organisational keyword: RD4 - Complexity Science
Research topic keyword: Atmosphere
Research topic keyword: Complex Networks
Research topic keyword: Nonlinear Dynamics
Model / method: Machine Learning
Working Group: Development of advanced time series analysis techniques
OATYPE: Gold Open Access
 Degree: -

Event

show

Legal Case

show

Project information

show

Source 1

show
hide
Title: Frontiers in Applied Mathematics and Statistics
Source Genre: Journal, Scopus, oa
 Creator(s):
Affiliations:
Publ. Info: -
Pages: - Volume / Issue: 8 Sequence Number: 955044 Start / End Page: - Identifier: CoNE: https://publications.pik-potsdam.de/cone/journals/resource/frontiers-applied-mathematics_statistics
Publisher: Frontiers