Guo Diansheng, Gahegan Mark, Maceachren Alan M, Zhou Biliang
Department of Geography, University of South Carolina, 709 Bull Street, Columbia, SC 29208. E-mail: <
Cartogr Geogr Inf Sci. 2005 Apr 1;32(2):113-132. doi: 10.1559/1523040053722150.
The discovery, interpretation, and presentation of multivariate spatial patterns are important for scientific understanding of complex geographic problems. This research integrates computational, visual, and cartographic methods together to detect and visualize multivariate spatial patterns. The integrated approach is able to: (1) perform multivariate analysis, dimensional reduction, and data reduction (summarizing a large number of input data items in a moderate number of clusters) with the Self-Organizing Map (SOM); (2) encode the SOM result with a systematically designed color scheme; (3) visualize the multivariate patterns with a modified Parallel Coordinate Plot (PCP) display and a geographic map (GeoMap); and (4) support human interactions to explore and examine patterns. The research shows that such "mixed initiative" methods (computational and visual) can mitigate each other's weakness and collaboratively discover complex patterns in large geographic datasets, in an effective and efficient way.
多元空间模式的发现、解释和呈现对于科学理解复杂的地理问题至关重要。本研究将计算、视觉和制图方法整合在一起,以检测和可视化多元空间模式。这种综合方法能够:(1)使用自组织映射(SOM)进行多元分析、降维和数据约简(在适度数量的聚类中总结大量输入数据项);(2)用系统设计的配色方案对SOM结果进行编码;(3)用改进的平行坐标图(PCP)显示和地理地图(GeoMap)可视化多元模式;(4)支持人机交互以探索和检查模式。研究表明,这种“混合主动”方法(计算和视觉)可以相互弥补不足,以有效且高效的方式在大型地理数据集中协同发现复杂模式。