Glyph-maps for visually exploring temporal patterns in climate data and models


  • This article is published in Environmetrics as a special issue on Advances in Statistical Methods for Climate Analysis, edited by Peter Guttorp, University of Washington, Norwegian Computing Center, Stephan R. Sain, National Center for Atmospheric Research, Christopher K. Wikle, University of Missouri.

Dianne Cook, Department of Statistics, Iowa State University, 2415 Snedecor Hall, Ames, IA 50011-1210, U.S.A. E-mail:


The multivariate spatio-temporal nature of climate data makes it difficult to draw all of the aspects simultaneously. This paper describes the conceptualization and construction of a type of display, a glyph-map, that can show these multiple aspects. Glyph-maps are a specialization of multivariate glyph plots. Each spatial location is displayed with one glyph that represents the multiple measurements, often recorded over time, at that location. Glyph-maps allow the discovery of both local and global structure, with a particular focus on temporal relationships, important for studying climate change. They provide alternatives to colored, facetted maps, or statistical summaries such as principal components. Glyph-maps have been used sporadically for spatio-temporal data, and with the ideas and software described in this paper, it will be easier to produce them. The conceptualization described here also will enable developing interactive versions of glyph-maps, and make it simpler to explore the perceptual effects of different scales. The methods are developed for rectangular gridded data, but with some clever processing, which is explained, it is possible to get good glyph-maps of irregularly gridded data. Guides and reference marks, for different types of glyphs used in the glyph-maps, are also discussed. Copyright © 2012 John Wiley & Sons, Ltd.