矢量GIS中属性数据的不确定性分析

本文从属性区域分类不确定性、边界定位误差和区域内部定量属性数据的抽样误差出发，综合进行属性数据不确定性的度量和传播分析。针对由边界定位误差引起的属性分类不确定性，在顾及区域面积与边界线数等因素下，提出了一种定量度量指标。对于属性区域内部的定量属性抽样值，则建立了抽样值的相关函数表达式。针对ＧＩＳ中常见的两大类操作，即逻辑操作和算术操作，分别根据模糊集合论和概率统计理论建立了相应的属性不确定性传播模

Analysis of Uncertainties of Attributes in Vector GIS

This paper discusses the measurement of uncertainties of attribute data in vector GIS. The uncertainties considered include uncertainties in thematic classificatiion, positional errors of boundaries and sampling errors of quantitative attributes. A quantitative index is proposed for describing the uncertainties related to thematic classification, which includes the effects of complexity of boundaries and areas of polygons. Correlation functions between sample values in attribute data are used to measure data sampling errors quantitatively. The second part of this paper focuses on modeling the propagation of attribute uncertainties in logical and arithmetical operations in GIS analysis using fuzzy set and statistical techniques. Two examples are provided to show how the models can be utilized in specific GIS applications.