Vol. 28, no. 3

Exploratory Analysis of Spatial Data Using Interactive Maps and Data Mining

1. Andrienko, G. Andrienko, A. Savinov, H. Voss, and D. Wettschereck

We present new methods for analyzing geo-referenced statistical data. These methods combine visualization and direct manipulation techniques of exploratory data analysis and algorithms for data mining. The methods have been implemented by integrating two hitherto separate software tools: Descartes for interactive thematic mapping, and the data mining toolbox Kepler. In using these tools, data analysis may proceed as a steady interaction between visual inspiration and insights gained from mathematical-statistical calculations. After introducing the various components of the methods and tools, the paper guides the reader through in-depth examples of using the tools in the context of analysis of urban demographic data. In particular, it is shown how geography-based classifications of urban districts can be related to available thematic characteristics by applying the data mining algorithms classification tree derivation, attribute weighting, and subgroup discovery.

Keywords: Exploratory data analysis, interactive maps, spatial data mining

Symbolization of Map Projection Distortion: A Review

Karen A. Mulcahy and Keith C. Clarke

One of the most fundamental steps in map creation is the transformation of information from the surface of a globe onto a flat map. Mapmakers have developed and used hundreds of different map projections over the past 2,000 years, yet there is no perfect choice because every map projection uniquely alters some aspect of space during the transformation process. Detailed information about the type, amount, and distribution of distortion is essential for choosing the best projection for a particular map or data set. The distortion inherent in projections can be measured and symbolized much like any other map variable. Methods for symbolizing map projection distortion are reviewed, with each method described and illustrated in graphical form. The symbolization methods are collected under ten separate headings organized from simple to more complex in terms of interpretation. Most of these methods are highly effective at communicating distortion, yet they are rarely used beyond textbooks and technical documentation. Map projections and the distortions they carry need to be better understood by spatial data developers, distributors, and users. Map distortion should be carried along with map data as confidence layers, and the easily accessible distortion displays should be available to help in the selection of map projections. There is a suitably wide array of symbolization methods to match any need from basic education to research.

Keywords: Map projection distortion, cartographic symbolization, visualization

All Equal-Area Map Projections Are Created Equal, But Some Are More Equal Than Others* With apologies to George Orwell

1. Lynn Usery and Jeong Chang Seong

High-resolution regional and global raster databases are currently being generated for a variety of environmental and scientific modeling applications. The projection of these data from geographic coordinates to a plane coordinate system is subject to significant areal error. Sources of error include users selecting an inappropriate projection or incorrect parameters for a given projection, algorithmic errors in commercial geographic information system (GIS) software, and errors resulting from the projection of data in the raster format. To assess the latter type of errors, the accuracy of raster projection was analyzed by two methods. First, a set of 12 one-degree by one-degree quadrilaterals placed at various latitudes was projected at several raster resolutions and compared to the projection of a vector representation of the same quadrilaterals. Second, several different raster resolutions of land cover data for Asia were projected and the total areas of 21 land cover categories were tabulated and compared. While equal-area projections are designed to specifically preserve area, the comparison of the results of the one-degree by one-degree quadrilaterals with the common equal area projections (e.g., the Mollweide) indicates a considerable variance in the one-degree area after projection. Similarly, the empirical comparison of land cover areas for Asia among various projections shows that total areas of land cover vary with projection type, raster resolution, and latitude. No single projection is best for all resolutions and all latitudes. While any of the equal-area projections tested are reasonably accurate for most applications with resolutions of eight-kilometer pixels or smaller, significant variances in accuracies appear at larger pixel sizes.

Role of Local Contextual Factors in Building Public Participation GIS: The Milwaukee Experience

Rina Ghose and William E. Huxhold

By virtue of its cost and technological complexity, GIS has been critiqued as an elitist anti-democratic technology. In response there has been an ongoing proliferation of public participation GIS (PPGIS) initiatives in order to facilitate citizen participation in planning. It is critical to conduct case study research of these initiatives, in order to identify factors and conditions fostering sustainable PPGIS initiatives at the local level. Through the case of Milwaukee, this paper explores the local contextual factors and the network of actors and institutions that foster the PPGIS process in that city. Particular attention is paid to the role of the University of Wisconsin-Milwaukee and its efforts to provide equitable public access to GIS through university/community partnerships. The paper critically explores the PPGIS initiatives undertaken in Milwaukee and concludes that the initiatives contain contradictory impulses of creating simultaneous empowerment of community organizations and their dependence on the network of stakeholder institutions.

Keywords: Public participation GIS, community empowerment, community organizations, neighborhood planning, contextual factors