Spatial Clustering for the Regionalization of Maize Cultivation in China and its Outlier Analysis

Regionalization of crop cultivation is the foundation of large-scale planting and a reasonable layout scheme, but current approaches mainly rely on qualitative analysis and heuristic methods, which cannot meet the progressively challenging demands. In this study, we propose a spatial clustering approach that consists of two steps. First, attributive clustering is applied on the indicators. Second, post-processing step of spatial contiguity adjustment is applied according to specific rules. This two-step algorithm results in clustered regions which are both contiguous in spatial relation and similar in attributes. In this paper, we demonstrate the use of a spatial clustering method on the regionalization of crop cultivation, with the maize growing in China as an example. The result shows that the result is highly consistent with the conventional regionalization of maize cultivation in China, which proves the feasibility of our approach, and suggests its possible application on other crops. Furthermore, we carry out outlier analysis for each of the regions to identify the counties that show abnormal behaviors in maize cultivation, and further analyze the possible causes. Key-Words: Spatial clustering, regionalization, maize-growing region, outlier analysis