代表性人口空间分布数据集的精度评价——以2010年广东省为例  

Accuracy Comparison of Four Gridded Population Datasets in Guangdong Province,China

作　　者：林丹淳 谭敏 刘凯[1] 柳林 朱远辉[1] Lin Danchun;Tan Min;Liu Kai;Liu Lin;Zhu Yuanhui(School of Geography and Planning,Sun Yat-sen University,Guangdong Provincial Engineering Research Center for Public Security and Disaster,Guangdong Key Laboratory for Urbanization and Geo-Simulation,Guangzhou 510275,China;Guangzhou Urban Planning&Design Studio,Guangzhou 510030;Center of Geographic Information Analysis for Public Security,School of Geographic Sciences,Guangzhou University,Guangzhou 510006,China)

机构地区：[1]中山大学地理科学与规划学院广东省公共安全与灾害工程技术研究中心广东省城市化与地理环境空间模拟重点实验室,广州510275 [2]广州市城市规划设计所,广州510030 [3]广州大学地理科学学院公共安全地理信息分析中心,广州510006

出　　处：《热带地理》2020年第2期346-356,共11页Tropical Geography

基　　金：国家自然科学基金重点项目(41531178);广东省自然科学基金研究团队项目(2014A030312010)。

摘　　要：以人口密度差异显著的广东省为研究区,比较Worldpop、GPW v4和2种中国公里网格人口分布数据集的空间分布一致性,并以第六次全国人口普查数据为真值,按人口密度分为高、中、低3组,从误差的数值分布和空间分布两方面定量评价4种数据集的精度,最后讨论估算误差的可能来源及数据适用性。结果表明,4种网格人口数据集中Worldpop整体精度最高,且在人口密集区的精度也是最高;GPW v4在低人口密度和中人口密度区域精度略高于Worldpop,但对镇街内人口分布细节刻画不够详细;2种中国公里网格人口分布数据集精度较前两者低,主要受空间化方法和模型变量的选择所限制。Worldpop适合用于人口密度中等及人口密度高区域的精细化研究,GPW v4适合用于长时序、最小研究单元大于镇街的研究,第一种中国公里网格人口分布数据集适合用于需要考虑镇街内人口分布和空间异质性的研究,第二种中国公里网格人口分布数据集适用于需要考虑人口分布细节和空间格局变化的长时序研究。The spatial distribution of population is foundational information for policy making,disaster prevention,economic development,environmental protection,and natural sciences or socioeconomic research.Analyzing different gridded population products is essential for learning their characteristics and proper application.Considering timeliness of data and convenience of access,this study compared the spatial consistency of WorldPop,GPW v4(Gridded Population of World,version 4)and two types of Gridded Population of China datasets in Guangdong Province,China,a province with significant population density differences.The sixth census data in 2010 were divided into high,middle,and low density groups and used as reference data to validate these four datasets on numerical and spatial distribution of error.Moreover,the study used average absolute error,average relative error,root mean square error,correlation coefficient,four indicators,ratio error statistics,and the Taylor diagram for quantitative evaluation.Then,the spatial distribution of the ratio error and the accuracy of the four datasets in different population density regions were analyzed.Finally,an evaluation of error sources and applications from two aspects,including methods for spatializing census data and variables selection of spatial model,was performed.The findings of the study are as follows:1)These four population datasets have similar spatial distribution trends,and the population is concentrated in the Pearl River Delta regions such as Guangzhou,Shenzhen,Dongguan,Foshan,Zhongshan and Chaoshan regions such as Shantou and Jieyang.The WorldPop dataset had the highest relative accuracy in the whole Guangdong Province,as well as in the high population density area,whereas the GPW v4 dataset performed better than WorldPop in the middle and low population density areas;however,GPW v4 had a shortcoming in depicting population distribution beneath the township level because of the areal-weighting method used.The two types of Gridded Population of China datasets ha

关 键 词：Worldpop GPW V4 中国公里网格人口分布数据集 精度对比 广东省 

分 类 号：C924.2[社会学—人口学]