Self-organizing maps: applications to synoptic climatology

Abstract

Self organizing maps (SOMs) are used to locate archetypal points that describe the multi-dimensional distribution function of a gridded sea level pressure data set for the northeast United States. These points -nodes on the SOM -identify the primary features of the synoptic-scale circulation over the region. In effect, the nodes represent a non-linear distribution of overlapping, non-discreet, circulation types. The circulation patterns are readily visualized in a 2-dimensional array (the SOM) that places similar types adjacent to one another and very different types far apart in the SOM space. The SOM is used to describe synoptic circulation changes over time, and to relate the circulation to January station precipitation data (for State College, Pennsylvania) in the center of the domain. The paper focuses on the methodology; however, the analysis suggests that circulation systems that promote precipitation have decreased over the last 40 yr -although January precipitation at State College has actually increased. Further analysis with the SOM indicates that this is due to a change in precipitation characteristics of the synoptic-scale circulation features, rather than to their frequency of occurrence.KEY WORDS: Self-organizing maps · Synoptic climatology · Downscaling · Climate change · Synoptic classification Resale or republication not permitted without written consent of the publisherClim Res 22: [13][14][15][16][17][18][19][20][21][22][23][24][25][26] 2002 some form of correlation, cluster, and/or eigenfunction analysis. In all cases, the approach of generalizing the circulation into characteristic modes or synoptic types required a fine balance between producing a small enough number of types to easily visualize and conceptualize the circulation, while avoiding so much generalization that the strength of any relationship to a local climate variable was lost. The major problems with this approach are due to the degree of within group variability produced. It is also common that days in the same synoptic type can often be associated with a very different local response, or that the same response can be obtained from different synoptic types. The fundamental characteristics of synoptic classification techniques are effectively summarized in Yarnal (1993).Underlying this traditional approach to synoptic classification is the premise that the continuum of weather states may be effectively divided into a small number of categories with clear discernable boundaries. This premise clearly has limitations: while typing weather systems gives a good first-order insight into the basic characteristics of the climate system, much of the information is inherently subsumed by the degree of generalization imposed.In response to this, Hewitson & Crane (1992a,b) proposed that the system can be treated as a continuum with a continuous function, and that quantitative relationships between the atmosphere and local surface variables can be developed in the form of a downscaling transfer function. This procedure is d...

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

“…For the application of the SOM algorithm in this paper, the input data are daily arrays of gridded SLP from an ensemble of global climate models and the reference vectors contain spatial SLP data. The reference vectors are of the same dimension as the input data vectors (Hewitson and Crane, 2002); and for our application, the position of a data value in the reference vector corresponds to a fixed spatial location in the two-dimensional EASE grid. The resulting map is a two-dimensional array of gridded SLP fields that are representative of the range of SLP patterns contained in the input data set, and can be used to depict the probability density function of those patterns as a function of time.…”

“…This is an important attribute of the approach, since it allows analysis not only on a node-by-node basis but also on a map area by map area basis, as appropriate. A thorough theoretical description of the SOM algorithm is found in Kohonen (2001) and further details on the application of the SOM algorithm to climate data can be found in Hewitson and Crane (2002).…”

“…In this analysis, the high-dimensional input data consists of a time series of three decades of daily gridded SLP fields from an ensemble of global climate system models, and thus represents both spatial and temporal dimensions. The use of self-organizing neural networks to analyze and organize circulation data represents a new way to create comprehensive and useful synoptic climatologies (Barry and Perry, 2001;Hewitson and Crane, 2002). SOMs have been used across a wide range of disciplines (Oja et al, 2003;Kaski et al, 1998), but are newer to climate research.…”

“…SOMs have been used across a wide range of disciplines (Oja et al, 2003;Kaski et al, 1998), but are newer to climate research. Hewitson and Crane (2002) used the SOM technique to classify synoptic patterns over the east coast of the United States, and to relate these patterns to daily precipitation at State College, Pennsylvania. Cavazos (1999Cavazos ( , 2000 used SOMs to identify and classify patterns representative of extreme wintertime precipitation in Central America and the Balkans respectively, identifying large-scale circulation anomalies associated with local extreme precipitation events.…”

Downscaling of GCM scenarios to assess precipitation changes in the little rainy season (March-June) in Cameroon

“…SOFMs have been used in climatology for classification purposes (Malmgren & Winter 1999, Cavazos 2000 and can achieve the same results as obtained by other methods. Hewitson & Crane (2002) recently used SOFMs to describe changes of synoptic circulation over time, and they discussed in detail their performance and utility in climatological studies. …”