Detecting decadal changes in ENSO using neural networks

Julie A. Leloup, Zouhair Lachkhar, Jean Philippe Boulanger, Sylvie Thiria

Research output: Contribution to journalArticle

Abstract

The present manuscript analyzes monthly equatorial Pacific indices by using a specific neural algorithm, the so-called "Self-Organizing Maps" (SOMs). The main result is a change found in the nature of the transitions between cold to warm and warm to cold extreme events from 1950 to present, around the late 1970s. SOM is an unsupervised clustering technique which allows one to reduce high-dimensional data space (in this case, three indices over 636 months) in terms of a smaller set of three-dimensional reference vectors (100) characterizing pertinent situations. These reference vectors, which are displayed on a two-dimension map, are closely related by a topological relationship leading us to discriminate La Niña conditions from the opposite El Niño conditions. In a second step, a Hierarchical Agglomerative Clustering (HAC) method is used to further group the reference vectors into a small number of clusters (12) whose spatial and temporal characteristics can be analyzed and interpreted in terms of physical parameters. Schematically, these 12 clusters can be divided into two "warm" clusters, six "neutral" or "transition" clusters and four "cold" clusters. In each particular group (warm, neutral, cold), the clusters mainly differ from each other by the amplitude of the anomalies, their spatial patterns and their temporal variability. Some clusters are found to be strongly linked to the boreal spring period, while others have barely any records during that season. Other clusters are associated with records mainly observed either prior to or after 1980. This suggests that the method is able to identify changes in the variability of the tropical Pacific basin observed on decadal time scales (1976 climate shift in our case). Each monthly record can be summarized by the cluster to which it belongs. The temporal evolution of this value during extreme ENSO events shows similar patterns (persistence in specific clusters and transition between groups of clusters) associated with comparable El Niño or La Niña events. The methodology described in the present study (SOM plus HAC) is suggested to be useful both for seasonal ENSO predictability and for the detection of decadal changes in ENSO behavior.

Original languageEnglish (US)
Pages (from-to)147-162
Number of pages16
JournalClimate Dynamics
Volume28
Issue number2-3
DOIs
StatePublished - Feb 1 2007

Fingerprint

El Nino-Southern Oscillation
extreme event
temporal evolution
persistence
timescale
anomaly
methodology
cold
climate
basin
method
index

ASJC Scopus subject areas

  • Atmospheric Science

Cite this

Detecting decadal changes in ENSO using neural networks. / Leloup, Julie A.; Lachkhar, Zouhair; Boulanger, Jean Philippe; Thiria, Sylvie.

In: Climate Dynamics, Vol. 28, No. 2-3, 01.02.2007, p. 147-162.

Research output: Contribution to journalArticle

Leloup, Julie A. ; Lachkhar, Zouhair ; Boulanger, Jean Philippe ; Thiria, Sylvie. / Detecting decadal changes in ENSO using neural networks. In: Climate Dynamics. 2007 ; Vol. 28, No. 2-3. pp. 147-162.
@article{eba8d0d14ed649718b8f1c1ccf58a71f,
title = "Detecting decadal changes in ENSO using neural networks",
abstract = "The present manuscript analyzes monthly equatorial Pacific indices by using a specific neural algorithm, the so-called {"}Self-Organizing Maps{"} (SOMs). The main result is a change found in the nature of the transitions between cold to warm and warm to cold extreme events from 1950 to present, around the late 1970s. SOM is an unsupervised clustering technique which allows one to reduce high-dimensional data space (in this case, three indices over 636 months) in terms of a smaller set of three-dimensional reference vectors (100) characterizing pertinent situations. These reference vectors, which are displayed on a two-dimension map, are closely related by a topological relationship leading us to discriminate La Ni{\~n}a conditions from the opposite El Ni{\~n}o conditions. In a second step, a Hierarchical Agglomerative Clustering (HAC) method is used to further group the reference vectors into a small number of clusters (12) whose spatial and temporal characteristics can be analyzed and interpreted in terms of physical parameters. Schematically, these 12 clusters can be divided into two {"}warm{"} clusters, six {"}neutral{"} or {"}transition{"} clusters and four {"}cold{"} clusters. In each particular group (warm, neutral, cold), the clusters mainly differ from each other by the amplitude of the anomalies, their spatial patterns and their temporal variability. Some clusters are found to be strongly linked to the boreal spring period, while others have barely any records during that season. Other clusters are associated with records mainly observed either prior to or after 1980. This suggests that the method is able to identify changes in the variability of the tropical Pacific basin observed on decadal time scales (1976 climate shift in our case). Each monthly record can be summarized by the cluster to which it belongs. The temporal evolution of this value during extreme ENSO events shows similar patterns (persistence in specific clusters and transition between groups of clusters) associated with comparable El Ni{\~n}o or La Ni{\~n}a events. The methodology described in the present study (SOM plus HAC) is suggested to be useful both for seasonal ENSO predictability and for the detection of decadal changes in ENSO behavior.",
author = "Leloup, {Julie A.} and Zouhair Lachkhar and Boulanger, {Jean Philippe} and Sylvie Thiria",
year = "2007",
month = "2",
day = "1",
doi = "10.1007/s00382-006-0173-1",
language = "English (US)",
volume = "28",
pages = "147--162",
journal = "Climate Dynamics",
issn = "0930-7575",
publisher = "Springer Verlag",
number = "2-3",

}

TY - JOUR

T1 - Detecting decadal changes in ENSO using neural networks

AU - Leloup, Julie A.

AU - Lachkhar, Zouhair

AU - Boulanger, Jean Philippe

AU - Thiria, Sylvie

PY - 2007/2/1

Y1 - 2007/2/1

N2 - The present manuscript analyzes monthly equatorial Pacific indices by using a specific neural algorithm, the so-called "Self-Organizing Maps" (SOMs). The main result is a change found in the nature of the transitions between cold to warm and warm to cold extreme events from 1950 to present, around the late 1970s. SOM is an unsupervised clustering technique which allows one to reduce high-dimensional data space (in this case, three indices over 636 months) in terms of a smaller set of three-dimensional reference vectors (100) characterizing pertinent situations. These reference vectors, which are displayed on a two-dimension map, are closely related by a topological relationship leading us to discriminate La Niña conditions from the opposite El Niño conditions. In a second step, a Hierarchical Agglomerative Clustering (HAC) method is used to further group the reference vectors into a small number of clusters (12) whose spatial and temporal characteristics can be analyzed and interpreted in terms of physical parameters. Schematically, these 12 clusters can be divided into two "warm" clusters, six "neutral" or "transition" clusters and four "cold" clusters. In each particular group (warm, neutral, cold), the clusters mainly differ from each other by the amplitude of the anomalies, their spatial patterns and their temporal variability. Some clusters are found to be strongly linked to the boreal spring period, while others have barely any records during that season. Other clusters are associated with records mainly observed either prior to or after 1980. This suggests that the method is able to identify changes in the variability of the tropical Pacific basin observed on decadal time scales (1976 climate shift in our case). Each monthly record can be summarized by the cluster to which it belongs. The temporal evolution of this value during extreme ENSO events shows similar patterns (persistence in specific clusters and transition between groups of clusters) associated with comparable El Niño or La Niña events. The methodology described in the present study (SOM plus HAC) is suggested to be useful both for seasonal ENSO predictability and for the detection of decadal changes in ENSO behavior.

AB - The present manuscript analyzes monthly equatorial Pacific indices by using a specific neural algorithm, the so-called "Self-Organizing Maps" (SOMs). The main result is a change found in the nature of the transitions between cold to warm and warm to cold extreme events from 1950 to present, around the late 1970s. SOM is an unsupervised clustering technique which allows one to reduce high-dimensional data space (in this case, three indices over 636 months) in terms of a smaller set of three-dimensional reference vectors (100) characterizing pertinent situations. These reference vectors, which are displayed on a two-dimension map, are closely related by a topological relationship leading us to discriminate La Niña conditions from the opposite El Niño conditions. In a second step, a Hierarchical Agglomerative Clustering (HAC) method is used to further group the reference vectors into a small number of clusters (12) whose spatial and temporal characteristics can be analyzed and interpreted in terms of physical parameters. Schematically, these 12 clusters can be divided into two "warm" clusters, six "neutral" or "transition" clusters and four "cold" clusters. In each particular group (warm, neutral, cold), the clusters mainly differ from each other by the amplitude of the anomalies, their spatial patterns and their temporal variability. Some clusters are found to be strongly linked to the boreal spring period, while others have barely any records during that season. Other clusters are associated with records mainly observed either prior to or after 1980. This suggests that the method is able to identify changes in the variability of the tropical Pacific basin observed on decadal time scales (1976 climate shift in our case). Each monthly record can be summarized by the cluster to which it belongs. The temporal evolution of this value during extreme ENSO events shows similar patterns (persistence in specific clusters and transition between groups of clusters) associated with comparable El Niño or La Niña events. The methodology described in the present study (SOM plus HAC) is suggested to be useful both for seasonal ENSO predictability and for the detection of decadal changes in ENSO behavior.

UR - http://www.scopus.com/inward/record.url?scp=33845430376&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33845430376&partnerID=8YFLogxK

U2 - 10.1007/s00382-006-0173-1

DO - 10.1007/s00382-006-0173-1

M3 - Article

AN - SCOPUS:33845430376

VL - 28

SP - 147

EP - 162

JO - Climate Dynamics

JF - Climate Dynamics

SN - 0930-7575

IS - 2-3

ER -