期刊文献+

基于POI和夜光数据的滇中地区人口空间化模拟研究

Spatial Simulation of Population Distribution Based on Nighttime Light and POI Data in Central Yunnan Province
下载PDF
导出
摘要 夜光数据可以间接反应人类活动的强度和范围,因此被广泛用于人类社会经济总量、城市空间格局、城市扩张等领域的数据挖掘。基于NPP/VIIRS(national polar-orbiting operational environmental satellite system preparatory project/visible infrared imaging radiometer)和LJ1-01两种夜光数据,采用空间滞后模型和空间误差模型两种回归模型进行对比,以选择适合的方法同时融入POI(point of interest)数据,分别基于500 m×500 m、150 m×150 m的格网进行人口值预测,并对预测值进行修正,最后以445个乡镇(街道)的人口统计值计算相对误差进行精度验证。结果表明:1)无论对于哪一种类型的夜光数据,空间滞后模型的精度要稍高于空间误差模型的精度。2)从R 2大小比较,LJ1-01模型人口预测精度要优于NPP/VIIRS,而LJ1-01与POI融合后的模型精度要优于LJ1-01。3)LJ1-01与POI融合后的预测精度分别比LJ1-01、NPP/VIIRS总体误差提升了2.1%、3.8%,反映出夜光数据与POI融合后可以提升模型预测的精度。4)基于LJ1-01与POI融合后的夜光数据人口预测结果,相对误差小于20%的较为准确区间段比之前的NPP/VIIRS、LJ1-01两种数据占比分别增加了19.3%、10.3%,说明LJ1-01与POI融合后数据比LJ1-01数据更具优势。 Nighttime light data can indirectly reflect the intensity and scope of human activities,so it is widely used in data mining of human socio-economic aggregate,urban spatial pattern,urban expansion and other fields.In this study,based on NPP/VIIRS and LJ1-01 nighttime light data,the spatial lag model and spatial error model were used to compare the regression models,and the suitable method was selected to integrate the POI data to predict the population value in the 500 m×500 m and 150 m×150 m grid,and then the values were corrected.Finally,the relative error of 445 towns(streets)was calculated to verify the accuracy.The results show that:1)the accuracy of spatial lag model is higher than that of spatial error model for each light data;2)compared with R 2,the prediction accuracy of LJ1-01 model is better than NPP/VIIRS,and the accuracy of LJ1-01 and POI fusion model is better than LJ1-01;3)when compared with LJ1-01 and NPP/VIIRS,the total error of the fusion of LJ1-01 and POI is increased by 2.1%and 3.8%,which reflects that the accuracy of model prediction can be improved with the fusion of LJ1-01 and POI;4)based on the population prediction results of the fusion of LJ1-01 and POI,the accurate interval with relative error less than 20%is increased by 19.3%and 10.3%respectively compared with the previous NPP/VIIRS and LJ1-01 data,indicating that the data of the fusion of LJ1-01 and POI has more advantages than LJ1-01 data alone.
作者 赵政权 罗虹 ZHAO Zhengquan;LUO Hong(College of Land and Spatial Information,Yunnan Land and Resources Vocational College,Kunming 652501,China)
出处 《贵州大学学报(自然科学版)》 2022年第5期61-67,共7页 Journal of Guizhou University:Natural Sciences
基金 云南省地矿局科技创新基金资助项目(2017JJ04)。
关键词 NPP/VIIRS LJ1-01 POI 滇中地区 人口空间化模拟 NPP/VIIRS LJ1-01 POI central Yunnan Province spatial simulation of population distribution
  • 相关文献

参考文献20

二级参考文献229

共引文献339

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部