摘要
综合运用最邻近指数、核密度分析、标准差椭圆、Getis-Ord G*i指数和XGBoost机器学习等方法,探讨了中国露营地的空间分布格局特征、影响因素以及不同城市露营地建设适宜性.结果表明:①中国露营地分布呈现集聚特征,整体分布上表现为"东聚西散、南多北少",呈"多核心—多轴线"的空间格局,区域及省际分布差异性显著,在京津冀、长三角、珠三角和川渝四大区域形成集聚区;②中国露营地空间分布特征受自然条件、旅游资源禀赋和社会经济环境的综合影响,基于XGBoost算法输出的影响因素权重值由高到低依次为:NDVI、DEM、AQI水平、GDP、A级景点数量、国内旅游收入、道路密度、国内旅游人数、工资水平;③中国露营地建设高适宜性区域主要集中于经济发达的东部地区,露营地数量占总数的48.90％;中适宜性区域主要分布于西北、中部与东北部分地区,露营地较为分散;低适宜性区域主要集中于青海和云南两省.
Abstract
The study comprehensively employed methods including nearest neighbor index,kernel density analysis,standard devia-tion ellipse,Getis-Ord G*i statistic,and XGBoost machine learning to investigate the spatial distribution patterns,influencing factors,and suitability for camping site construction in different cities of China.The results showed that:The distribution of camping sites in Chi-na exhibited an aggregation characteristic,with an overall pattern of"concentration in the east and dispersion in the west,more in the south and fewer in the north",presenting a spatial structure of"multiple cores-multiple axes".Significant regional and inter-provin-cial distribution differences existed,forming concentration areas in Beijing-Tianjin-Hebei,the Yangtze River Delta,the Pearl River Delta,and the Chengdu-Chongqing regions.The spatial distribution features of camping sites in China were comprehensively influenced by natural conditions,tourism resource endowments,and socio-economic environment.Based on the XGBoost algorithm,the influencing factors,ranked from high to low weights,were:NDVI,DEM,AQI level,GDP,number of Grade A scenic spots,domestic tourism income,road density,domestic tourism population,and wage level.Areas with high suitability for camping site construction in China were mainly concentrated in economically developed eastern regions,accounting for 48.90％of the total number;areas with moderate suitability were primarily distributed in the northwest,central,and northeast parts,with camping sites more dispersed;areas with low suitability were mainly concentrated in Qinghai and Yunnan provinces.
国家科技期刊平台
NSTL
万方数据