Using Linked Micromap Plots to Characterize Omernik Ecoregions

  • Authors:
  • Daniel B. Carr;Anthony R. Olsen;Suzanne M. Pierson;Jean-Yves P. Courbois

  • Affiliations:
  • Center for Computational Statistics, George Mason University, Fairfax, VA 22030, USA. dcarr@galaxy.gmu.edu;US Environmental Protection Agency, NHEERL Western Ecology Division, 200 S.W. 35th Street, Corvallis, OR 97333, USA. tolsen@heart.cor.epa.gov;OAO, c/o US EPA, 200 S.W. 35th Street, Corvallis, OR 97333, USA. spierson@mercury.cor.epa.gov;Department of Statistics, Oregon State University, Corvallis, OR 97331, USA. courbois@stat.orst.edu

  • Venue:
  • Data Mining and Knowledge Discovery
  • Year:
  • 2000

Quantified Score

Hi-index 0.00

Visualization

Abstract

The paper introduces linked micromap (LM) plots forpresenting environmental summaries. The LM template includes parallelsequences of micromap, label, and statistical summary graphics panelswith attention paid to perceptual grouping, sorting and linking ofthe summary components. The applications show LM plots for OmernikLevel II Ecoregions. The summarized United States continental dataincludes USGS digital elevation, 30-year normal precipitation andtemperature, and 8 million AVHRR pixels classified into 159 types ofland cover. One LM plot uses a line-height glyph to represent all 159land cover percentages per ecoregion. LM plots represent newvisualization methodology that is useful in the data and knowledgebased pattern representation and knowledge discovery process. The LMplots focus on providing an orienting overview. The overview providesa starting place for subsequent drilling down to what could otherwisebe viewed as an overwhelming mass of data. The overview also providesa starting place to learn about the intellectual structure that liesbehind the notion of ecoregions and begins to connect this abstractstructure to quantitative methods.