Towards ice-core-based synoptic reconstructions of west antarctic climate with artificial neural networks

Reusch, D. B.; Alley, Richard B.

doi:10.1002/joc.1143

Cited by 35 publications

(34 citation statements)

References 54 publications

(78 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Malmgren and Winter (1999) used SOMs to classify climate zones in Puerto Rico. Crane and Hewitson (2003) used SOMs to analyze precipitation data from the mid-Atlantic and northeastern United States, while Reusch et al (2005) applied the SOM methodology to aid in interpreting Antarctic ice core data.…”

Section: Description Of the Self-organizing Map Algorithmmentioning

confidence: 99%

Changes in synoptic weather patterns in the polar regions in the twentieth and twenty-first centuries, part 1: Arctic

2006

View full text Add to dashboard Cite

An analysis of late twentieth and twenty-first century predictions of Arctic circulation patterns in a ten-model ensemble of global climate system models, using the method of self-organizing maps (SOMs), is presented. The model simulations were conducted in support of the fourth assessment report of the intergovernmental panel on climate change (IPCC). The analysis demonstrates the utility of SOMs for climate analysis, both as a tool to evaluate the accuracy of climate model predictions, and to provide a useful alternative view of future climate change.It is found that not all models accurately simulate the frequency of occurrence of Arctic circulation patterns. Some of the models tend to overpredict strong high-pressure patterns while other models overpredict the intensity of cyclonic circulation regimes. In general, the ensemble of models predicts an increase in cyclonically dominated circulation patterns during both the winter and summer seasons, with the largest changes occurring during the first half of the twenty-first century. Analysis of temperature and precipitation anomalies associated with the different circulation patterns reveals coherent patterns that are consistent with the different circulation regimes and highlight the dependence of local changes in these quantities to changes in the synoptic scale circulation patterns.

show abstract

Section: Description Of the Self-organizing Map Algorithmmentioning

confidence: 99%

Changes in synoptic weather patterns in the polar regions in the twentieth and twenty-first centuries, part 1: Arctic

2006

View full text Add to dashboard Cite

show abstract

Section: Description Of the Sommentioning

confidence: 99%

“…Ambroise et al (2000) used SOMs for cloud classification and Malmgren & Winter (1999) used SOMs to classify climate zones in Puerto Rico. Crane & Hewitson (2003) used SOMs to analyze precipitation data from the mid-Atlantic and northeastern USA while Reusch et al (2005) applied the SOM methodology to aid in interpreting Antarctic ice core data.Formally, the SOM may be described as a non-linear mapping of high-dimensional input data onto the elements of a regular low-dimensional array (Kohonen 2001). This array, called a map, is a 2-dimensional matrix of reference vectors, or nodes, that are representative of the probability density function of the input data.…”

mentioning

confidence: 99%

Classification of synoptic patterns in the western Arctic associated with extreme events at Barrow, Alaska, USA

Cassano¹,

Lynch²,

Cassano³

et al. 2006

Clim. Res.

103

View full text Add to dashboard Cite

The coastal geography of Barrow, Alaska, makes the city vulnerable to weather events that cause flooding and erosion. This study uses the self-organizing map (SOM) algorithm, an unsupervised learning process that codifies large, multivariate datasets onto a 2-dimensional array, or map, to study large-scale circulation patterns associated with temperature and high wind extremes at Barrow. The analysis first uses the SOM algorithm to produce an automated 55 yr synoptic climatology of daily sea level pressure patterns for the western Arctic for August to November, when the area is potentially ice free. The results are in agreement with previous Arctic climatologies, showing the Aleutian Low to be dominant in southern Alaska, and high pressure prevalent over the Beaufort and Chukchi Seas. The SOM algorithm is then used to study circulation patterns associated with temperature and high wind extremes at Barrow. These results show that high winds are associated with patterns containing a strong pressure gradient between the Aleutian Low and the Beaufort and Chukchi Seas and also with patterns that contain a low pressure system to the north of Barrow. High (low) air temperature extreme anomalies are associated with patterns that produce strong, southerly (northerly) air flow at Barrow. This study demonstrates the utility of using SOMs to investigate the relationship between local weather conditions and large-scale patterns. This approach can be applied to future global climate model (GCM) simulations to investigate the impact of changes in large-scale circulation patterns to local extreme events.KEY WORDS: Synoptic climatology · Self-organizing maps · SOM · Large-scale circulation · Extreme events Resale or republication not permitted without written consent of the publisherClim Res 30: [83][84][85][86][87][88][89][90][91][92][93][94][95][96][97] 2006 Barrow is located on the west shore of Point Barrow. Atmospheric and sea ice conditions that can lead to storm surge via Ekman transport and wave setup are caused by synoptic weather patterns that produce high, sustained westerly winds coupled with large fetch (open water or low sea ice concentration in the direction of the wind). In general, these weather patterns consist of a synoptic or mesoscale low pressure system to the north of Barrow and/or a high pressure system to the south. However, while several such events that were extreme enough to cause significant damage have occurred (e.g. Lynch et al. 2003), these are not typical patterns in this area. From earlier Arctic climatologies (Keegan 1958, Reed & Kunkel 1960, Moritz 1979, LeDrew 1983 to more current ones (Serreze et al. 1993, Brümmer et al. 2000, McCabe et al. 2001, the Beaufort/Chukchi sector of the Arctic (Fig. 1) does not exhibit much cyclonic activity, and in fact the Beaufort and Chukchi Seas are an area of frequent anticyclones. These anticyclones, coupled with low pressure in southern Alaska, result in prevailing ENE winds of about 5 m s -1 at Barrow (Moritz 1979).The basic aim of synoptic c...

show abstract

“…The asymmetric features can be extracted by (nonlinear) SOM analysis relative to (linear) EOF analysis (Liu and Weisberg 2007). A test using idealized North Atlantic SLP fields also indicated SOM analysis to be more robust than PCA in extracting predefined patterns of variability (Reusch, Hewitson, and Alley 2005).…”

Section: Som Analysismentioning

confidence: 99%

Spatiotemporal characteristics of the sea level anomaly in the Kuroshio Extension using a self-organizing map

Diao

Luo

2016

Atmospheric and Oceanic Science Letters

View full text Add to dashboard Cite

Towards ice-core-based synoptic reconstructions of west antarctic climate with artificial neural networks

Cited by 35 publications

References 54 publications

Changes in synoptic weather patterns in the polar regions in the twentieth and twenty-first centuries, part 1: Arctic

Changes in synoptic weather patterns in the polar regions in the twentieth and twenty-first centuries, part 1: Arctic

Classification of synoptic patterns in the western Arctic associated with extreme events at Barrow, Alaska, USA

Spatiotemporal characteristics of the sea level anomaly in the Kuroshio Extension using a self-organizing map

Contact Info

Product

Resources

About