基于地理加权回归的茶叶种植专业化空间格局及影响因素——以福建省安溪县为例

Spatial patterns and influence factors of specialization in tea cultivation based on geographically weighted regression model:A case study of Anxi County of Fujian Province,China

以专业化茶叶种植大县安溪县为例,通过评估各乡镇茶叶种植专业化水平,结合Pearson相关分析、普通最小二乘法模型(OLS)和地理加权回归模型(GWR),筛选出平均高程、农民人均纯收入、农业从业人口比重、距交通道路距离4个主要影响安溪县茶叶种植专业化程度的因素,并探讨其对茶叶种植专业化影响程度的空间分异规律.结果表明:安溪县各乡镇茶叶种植专业化程度呈现显著的空间自相关,以县城为中心,茶叶种植专业化程度由近及远呈现出"低-中-高"的形似杜能农业区位模型的圈层结构;GWR的拟合度(0.624)高于OLS(0.595),且前者对空间数据的解释力更高;与杜能农业区位模型的市场距离决定机制相悖,茶叶种植专业化程度受山地自然环境因素的影响明显较社会经济因素更大;茶叶种植专业化程度与平均高程、农民人均纯收入、农业从业人口比重呈正相关,而与距交通道路距离总体呈负相关;茶叶种植专业化程度与平均高程、农民人均纯收入的回归系数主要呈现出"南高北低"的空间分布特征,农业从业人口比重则呈相反的规律,而距交通道路距离则主要呈现"西南低、东北高"的空间特征.

Anxi County, specializing in tea cultivation, was taken as a case in this research. Pearson correlation analysis, ordinary least squares model （OLS） and geographically weighted regression model （GWR） were used to select four primary influence factors of specialization in tea cultivation （i.e., the average elevation, net income per capita, proportion of agricultural population, and the distance from roads） by analyzing the specialization degree of each town of Anxi County. Meanwhile, the spatial patterns of specialization in tea cultivation of Anxi County were evaluated. The resuks indicated that specialization in tea cultivation of Anxi County showed an obvious spatial auto-correlation, and a spatial pattern with ＂low-middle-high＂ circle structure, which was similar to Von Thtinen＇ s circle structure model, appeared from the county town to its surrounding region. Meanwhile, GWR （0.624） had a better fitting degree than OLS （0.595）, and GWR could reasonably expound the spatial data. Contrary to the agricultural location theory of Von Thiinen＇ s model, which indicated that distance from market was a determination factor, the specialization degree of tea cultivation in Anxi was mainly decided by natural conditions of mountain area, instead of the social factors. Specialization degree of tea cultivation was positively correlated with the average elevation, net income per capita and the proportion of agricultural population, while a negative correla- tion was found between the distance from roads and specialization degree of tea cultivation. Coeffi- cients of regression between the specialization degree of tea cultivation and two factors （ i. e., the average elevation and net income per capita） showed a spatial pattern of higher level in the north direction and lower level in the south direction. On the contrary, the regression coefficients for the proportion of agricultural population increased from south to north of Anxi County. Furthermore, re- gression coefficient for the distance from roads showed a spatial pattern of higher level in the north- east direction and lower level in the southwest direction of Anxi County.