Tropical Cyclone Trend Analysis using Enhanced Parallel Coordinates and Statistical Analysis
Chad A Steed, Patrick J. Fitzpatrick, J. Edward Swan II, and T.J. Jankun-Kelly. Tropical Cyclone Trend Analysis using Enhanced Parallel Coordinates and Statistical Analysis. Cartography and Geographic Information Science, 36(3):251–265, July 2009.
Download
Abstract
This work presents, via an in-depth case study, how parallel coordinates coupled with statistical analysis can be used for more effective knowledge discovery and confirmation in complex, environmental data sets. Advanced visual interaction techniques such as dynamic axis scaling, conjunctive parallel coordinates, statistical indicators, and aerial perspective shading are combined into an interactive geovisual analytics system. Moreover, the system facilitates statistical processes such as stepwise regression and correlation analysis to assist in the identification and quantification of the most significant predictors for a particular dependent variable. Using a systematic workflow, this approach is demonstrated via a North Atlantic hurricane climate study in close collaboration with a domain expert. By revealing several important physical associations, the case study reveals that the visual analytics approach facilitates a deeper understanding of multidimensional climate data sets when compared to traditional techniques.
BibTeX
@Article{CAGIS09-tcta,
author = {Chad A Steed and Patrick J. Fitzpatrick and J. Edward {Swan~II} and
T.J. Jankun-Kelly},
title = {Tropical Cyclone Trend Analysis using Enhanced Parallel Coordinates
and Statistical Analysis},
journal = {Cartography and Geographic Information Science},
month = {July},
year = 2009,
volume = 36,
number = 3,
pages = {251--265},
abstract = {
This work presents, via an in-depth case study, how parallel
coordinates coupled with statistical analysis can be used for more
effective knowledge discovery and confirmation in complex, environmental
data sets. Advanced visual interaction techniques
such as dynamic axis scaling, conjunctive parallel coordinates,
statistical indicators, and aerial perspective shading are
combined into an interactive geovisual analytics system.
Moreover, the system facilitates statistical processes such
as stepwise regression and correlation analysis to assist in the
identification and quantification of the most significant predictors
for a particular dependent variable. Using a systematic workflow,
this approach is demonstrated via a North Atlantic hurricane climate
study in close collaboration with a domain expert. By revealing
several important physical associations, the case study reveals
that the visual analytics approach facilitates a deeper
understanding of multidimensional climate data sets when compared to
traditional techniques.
},
}