English
 
Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
 
 
DownloadE-Mail
  Long-term ENSO prediction with echo-state networks

Hassanibesheli, F., Kurths, J., Boers, N. (2022): Long-term ENSO prediction with echo-state networks. - Environmental Research: Climate, 1, 1, 011002.
https://doi.org/10.1088/2752-5295/ac7f4c

Item is

Files

show Files
hide Files
:
27911oa.pdf (Publisher version), 5MB
Name:
27911oa.pdf
Description:
-
Visibility:
Public
MIME-Type / Checksum:
application/pdf / [MD5]
Technical Metadata:
Copyright Date:
-
Copyright Info:
-

Locators

show

Creators

show
hide
 Creators:
Hassanibesheli, Forough1, Author              
Kurths, Jürgen1, Author              
Boers, Niklas1, Author              
Affiliations:
1Potsdam Institute for Climate Impact Research, ou_persistent13              

Content

show
hide
Free keywords: -
 Abstract: The El Niño-Southern Oscillation (ENSO) is a climate phenomenon that profoundly impacts weather patterns and extreme events worldwide. Here we develop a method based on a recurrent neural network, called echo state network (ESN), which can be trained efficiently to predict different ENSO indices despite their relatively high noise levels. To achieve this, we train the ESN model on the low-frequency variability of ENSO indices and estimate the potential future high-frequency variability from specific samples of its past history. Our method reveals the importance of cross-scale interactions in the mechanisms underlying ENSO and skilfully predicts its variability and especially El Niño events at lead times up to 21 months. This study considers forecasts skillful if the correlation coefficients are above 0.5. Our results show that the low-frequency component of ENSO carries substantial predictive power, which can be exploited by training our model on single scalar time series. The proposed machine learning method for data-driven modeling can be readily applied to other time series, e.g. finance and physiology. However, it should be noted that our approach cannot straightforwardly be turned into a real-time operational forecast because of the decomposition of the original time series into the slow and fast components using low-pass filter techniques.

Details

show
hide
Language(s): eng - English
 Dates: 2022-07-212022-09
 Publication Status: Finally published
 Pages: 18
 Publishing info: -
 Table of Contents: -
 Rev. Type: Peer
 Identifiers: DOI: 10.1088/2752-5295/ac7f4c
MDB-ID: No data to archive
PIKDOMAIN: RD4 - Complexity Science
Organisational keyword: FutureLab - Artificial Intelligence in the Anthropocene
OATYPE: Gold Open Access
 Degree: -

Event

show

Legal Case

show

Project information

show

Source 1

show
hide
Title: Environmental Research: Climate
Source Genre: Journal, other, oa
 Creator(s):
Affiliations:
Publ. Info: -
Pages: - Volume / Issue: 1 (1) Sequence Number: 011002 Start / End Page: - Identifier: CoNE: https://publications.pik-potsdam.de/cone/journals/resource/2752-5295
Publisher: IOP Publishing