Towards ice-core-based synoptic reconstructions of West Antarctic climate with artificial neural networks

David B. Reusch, Bruce C. Hewitson, Richard B. Alley

Research output: Contribution to journalArticle

28 Citations (Scopus)

Abstract

Ice cores have, in recent decades, produced a wealth of palaeoclimatic insights over widely ranging temporal and spatial scales. Nonetheless, interpretation of ice-core-based climate proxies is still problematic due to a variety of issues unrelated to the quality of the ice-core data. Instead, many of these problems are related to our poor understanding of key transfer functions that link the atmosphere to the ice. This study uses two tools from the field of artificial neural networks (ANNs) to investigate the relationship between the atmosphere and surface records of climate in West Antarctica. The first, self-organizing maps (SOMs), provides an unsupervised classification of variables from the mid-troposphere (700 hPa temperature, geopotential height and specific humidity) into groups of similar synoptic patterns. An SOM-based climatology at annual resolution (to match ice-core data) has been developed for the period 1979-93 based on the European Centre for Medium-Range Weather Forecasts (ECMWF) 15-year reanalysis (ERA-15) dataset. This analysis produced a robust mapping of years to annual-average synoptic conditions as generalized atmospheric patterns or states. Feed-forward ANNs, our second ANN-based tool, were then used to upscale from surface data to the SOM-based classifications, thereby relating the surface sampling of the atmosphere to the large-scale circulation of the mid-troposphere. Two recorders of surface climate were used in this step: automatic weather stations (AWSs) and ice cores. Six AWS sites provided 15 years of near-surface temperature and pressure data. Four ice-core sites provided 40 years of annual accumulation and major ion chemistry. Although the ANN training methodology was properly designed and followed standard principles, limited training data and noise in the ice-core data reduced the effectiveness of the upscaling predictions. Despite these shortcomings, which might be expected to preclude successful analyses, we find that the combined techniques do allow ice-core reconstruction of annual-average synoptic conditions with some skill. We thus consider the ANN-based approach to upscaling to be a useful tool, but one that would benefit from additional training data.

Original languageEnglish (US)
Pages (from-to)581-610
Number of pages30
JournalInternational Journal of Climatology
Volume25
Issue number5
DOIs
StatePublished - Apr 1 2005

Fingerprint

ice core
artificial neural network
climate
upscaling
weather station
atmosphere
troposphere
unsupervised classification
surface pressure
geopotential
transfer function
climatology
humidity
surface temperature
weather
ice
methodology
ion
sampling
prediction

All Science Journal Classification (ASJC) codes

  • Atmospheric Science

Cite this

@article{ce23b55862104678ad9f9ecb0b4e3685,
title = "Towards ice-core-based synoptic reconstructions of West Antarctic climate with artificial neural networks",
abstract = "Ice cores have, in recent decades, produced a wealth of palaeoclimatic insights over widely ranging temporal and spatial scales. Nonetheless, interpretation of ice-core-based climate proxies is still problematic due to a variety of issues unrelated to the quality of the ice-core data. Instead, many of these problems are related to our poor understanding of key transfer functions that link the atmosphere to the ice. This study uses two tools from the field of artificial neural networks (ANNs) to investigate the relationship between the atmosphere and surface records of climate in West Antarctica. The first, self-organizing maps (SOMs), provides an unsupervised classification of variables from the mid-troposphere (700 hPa temperature, geopotential height and specific humidity) into groups of similar synoptic patterns. An SOM-based climatology at annual resolution (to match ice-core data) has been developed for the period 1979-93 based on the European Centre for Medium-Range Weather Forecasts (ECMWF) 15-year reanalysis (ERA-15) dataset. This analysis produced a robust mapping of years to annual-average synoptic conditions as generalized atmospheric patterns or states. Feed-forward ANNs, our second ANN-based tool, were then used to upscale from surface data to the SOM-based classifications, thereby relating the surface sampling of the atmosphere to the large-scale circulation of the mid-troposphere. Two recorders of surface climate were used in this step: automatic weather stations (AWSs) and ice cores. Six AWS sites provided 15 years of near-surface temperature and pressure data. Four ice-core sites provided 40 years of annual accumulation and major ion chemistry. Although the ANN training methodology was properly designed and followed standard principles, limited training data and noise in the ice-core data reduced the effectiveness of the upscaling predictions. Despite these shortcomings, which might be expected to preclude successful analyses, we find that the combined techniques do allow ice-core reconstruction of annual-average synoptic conditions with some skill. We thus consider the ANN-based approach to upscaling to be a useful tool, but one that would benefit from additional training data.",
author = "Reusch, {David B.} and Hewitson, {Bruce C.} and Alley, {Richard B.}",
year = "2005",
month = "4",
day = "1",
doi = "10.1002/joc.1143",
language = "English (US)",
volume = "25",
pages = "581--610",
journal = "International Journal of Climatology",
issn = "0899-8418",
publisher = "John Wiley and Sons Ltd",
number = "5",

}

Towards ice-core-based synoptic reconstructions of West Antarctic climate with artificial neural networks. / Reusch, David B.; Hewitson, Bruce C.; Alley, Richard B.

In: International Journal of Climatology, Vol. 25, No. 5, 01.04.2005, p. 581-610.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Towards ice-core-based synoptic reconstructions of West Antarctic climate with artificial neural networks

AU - Reusch, David B.

AU - Hewitson, Bruce C.

AU - Alley, Richard B.

PY - 2005/4/1

Y1 - 2005/4/1

N2 - Ice cores have, in recent decades, produced a wealth of palaeoclimatic insights over widely ranging temporal and spatial scales. Nonetheless, interpretation of ice-core-based climate proxies is still problematic due to a variety of issues unrelated to the quality of the ice-core data. Instead, many of these problems are related to our poor understanding of key transfer functions that link the atmosphere to the ice. This study uses two tools from the field of artificial neural networks (ANNs) to investigate the relationship between the atmosphere and surface records of climate in West Antarctica. The first, self-organizing maps (SOMs), provides an unsupervised classification of variables from the mid-troposphere (700 hPa temperature, geopotential height and specific humidity) into groups of similar synoptic patterns. An SOM-based climatology at annual resolution (to match ice-core data) has been developed for the period 1979-93 based on the European Centre for Medium-Range Weather Forecasts (ECMWF) 15-year reanalysis (ERA-15) dataset. This analysis produced a robust mapping of years to annual-average synoptic conditions as generalized atmospheric patterns or states. Feed-forward ANNs, our second ANN-based tool, were then used to upscale from surface data to the SOM-based classifications, thereby relating the surface sampling of the atmosphere to the large-scale circulation of the mid-troposphere. Two recorders of surface climate were used in this step: automatic weather stations (AWSs) and ice cores. Six AWS sites provided 15 years of near-surface temperature and pressure data. Four ice-core sites provided 40 years of annual accumulation and major ion chemistry. Although the ANN training methodology was properly designed and followed standard principles, limited training data and noise in the ice-core data reduced the effectiveness of the upscaling predictions. Despite these shortcomings, which might be expected to preclude successful analyses, we find that the combined techniques do allow ice-core reconstruction of annual-average synoptic conditions with some skill. We thus consider the ANN-based approach to upscaling to be a useful tool, but one that would benefit from additional training data.

AB - Ice cores have, in recent decades, produced a wealth of palaeoclimatic insights over widely ranging temporal and spatial scales. Nonetheless, interpretation of ice-core-based climate proxies is still problematic due to a variety of issues unrelated to the quality of the ice-core data. Instead, many of these problems are related to our poor understanding of key transfer functions that link the atmosphere to the ice. This study uses two tools from the field of artificial neural networks (ANNs) to investigate the relationship between the atmosphere and surface records of climate in West Antarctica. The first, self-organizing maps (SOMs), provides an unsupervised classification of variables from the mid-troposphere (700 hPa temperature, geopotential height and specific humidity) into groups of similar synoptic patterns. An SOM-based climatology at annual resolution (to match ice-core data) has been developed for the period 1979-93 based on the European Centre for Medium-Range Weather Forecasts (ECMWF) 15-year reanalysis (ERA-15) dataset. This analysis produced a robust mapping of years to annual-average synoptic conditions as generalized atmospheric patterns or states. Feed-forward ANNs, our second ANN-based tool, were then used to upscale from surface data to the SOM-based classifications, thereby relating the surface sampling of the atmosphere to the large-scale circulation of the mid-troposphere. Two recorders of surface climate were used in this step: automatic weather stations (AWSs) and ice cores. Six AWS sites provided 15 years of near-surface temperature and pressure data. Four ice-core sites provided 40 years of annual accumulation and major ion chemistry. Although the ANN training methodology was properly designed and followed standard principles, limited training data and noise in the ice-core data reduced the effectiveness of the upscaling predictions. Despite these shortcomings, which might be expected to preclude successful analyses, we find that the combined techniques do allow ice-core reconstruction of annual-average synoptic conditions with some skill. We thus consider the ANN-based approach to upscaling to be a useful tool, but one that would benefit from additional training data.

UR - http://www.scopus.com/inward/record.url?scp=17844404018&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=17844404018&partnerID=8YFLogxK

U2 - 10.1002/joc.1143

DO - 10.1002/joc.1143

M3 - Article

AN - SCOPUS:17844404018

VL - 25

SP - 581

EP - 610

JO - International Journal of Climatology

JF - International Journal of Climatology

SN - 0899-8418

IS - 5

ER -