基于粗糙集的地学空间关系规则抽取和应用——以珠江三角洲土地利用为例

Extraction of Geo-spatial Relationship Rules Based on Rough Set Theory: Exemplified by Land Use

空间关系反映了地理现象与其环境间的复杂的关联关系,对于地学问题的求解有着重要的作用。因此,有效地抽取地学现象内蕴的主要空间关系规则,将有利于提高地学问题求解的精度和效率。本文探讨了基于粗糙集的地学空间关系表达以及空间关系规则抽取流程。并以珠江三角洲2000年土地利用为例,抽取2000年深圳、香港城镇用地和农村居民点内蕴的空间关系规则。

Geo-spatial relations reflect the complex association between geographical phenomena and environments, so, are very important in dealing with geographical issues. They can be generated according to geometric attributes of spatial phenomena, such as distance, direction, connectivity, similarity etc. Also they can be generated based on combinations of geometric attributes and non-geometric attributes such as statistical correlations, spatial autocorrelations, space interactions, spatial dependencies etc. There are still other geo-spatial relations arising from non-geometric attributes of spatial phenomena. Extracting geo-spatial relation rules effectively helps to improve the accuracy and efficiency of solutions of geographical issues. This paper discusses both the expression of geotrate spatial ample to Kong. relations and the extraction process of geo-spatial relationship rules based on rough set theory. To illustrate the extraction process of the rules, we take the land use vector data of the Pearl River Delta in 2000 as an example to extract the geo-spatial relationship rules of urban areas and rural residential areas in Shenzhen and Hong Kong.