分区策略与机器学习的人口分布精细化模拟Fine-scale simulation of population distribution based on zoning strategy and machine learning
成方龙;赵冠伟;
摘要(Abstract):
针对人口普查统计中获取精细尺度的人口分布信息的问题,该文以广州市中心六区为例,利用夜间灯光、兴趣点及土地利用等多源地理信息数据,基于分区建模思想,运用机器学习算法开展了人口分布格网模拟研究。结果表明,基于分区策略和机器学习算法的人口分布模拟结果与实际人口的相关系数为0.834,拟合优度R2为0.695。与基于不分区的人口分布格网模型相比,误差下降明显,模拟精度更高,结果与研究区实际情况更为吻合。
关键词(KeyWords): 人口分布;精细化;机器学习;分区建模
基金项目(Foundation): 国家自然科学基金项目(41671175,41671430);; 广东省自然科学基金项目(2017A030313240);; 广东省高等学校优秀青年教师培养计划资助项目(YQ2015127)
作者(Authors): 成方龙;赵冠伟;
DOI: 10.16251/j.cnki.1009-2307.2020.09.025
参考文献(References):
- [1] 曾文,张小林,向梨丽,等.2000—2010年南京都市区人口空间变动特征研究[J].地理科学,2016,36(1):81-89.(ZENG Wen,ZHANG Xiaolin,XIANG Lili,et al.The features of population redistribution of Nanjing metropolitan area in 2000—2010[J].Scientia Geographical Sinica,2016,36(1):81-89.)
- [2] 胡云锋,王倩倩,刘越,等.国家尺度社会经济数据格网化原理和方法[J].地球信息科学学报,2011,13(5):573-578.(HU Yunfeng,WANG Qianqian,LIU Yue,et al.Index system and transferring methods to build the national society and economic data database[J].Journal of Geo-information Science,2011,13(5):573-578.)
- [3] 李翔,陈振杰,吴洁璇,等.基于夜间灯光数据和空间回归模型的城市常住人口格网化方法研究[J].地球信息科学学报,2017,19(10):1298-1305.(LI Xiang,CHEN Zhenjie,WU Jiexuan,et al.Gridding methods of city permanent population based on night light data and spatial regression models[J].Journal of Geo-information Science,2017,19(10):1298-1305.)
- [4] 刘瑜,肖昱,高松,等.基于位置感知设备的人类移动研究综述[J].地理与地理信息科学,2011,27(4):8-13.(LIU Yu,XIAO Yu,GAO Song,et al.A review of human mobility research based on location aware devices[J].Geography and Geo-Information Science,2011,27(4):8-13.)
- [5] 郭璨,甄峰,朱寿佳.智能手机定位数据应用于城市研究的进展与展望[J].人文地理,2014,29(6):18-23.(GUO Can,ZHEN Feng,ZHU Shoujia.Progress and prospect of the application of smart phone LBS data in urban researches[J].Human Geography,2014,29(6):18-23.)
- [6] 闫庆武,卞正富,张萍,等.基于居民点密度的人口密度空间化[J].地理与地理信息科学,2011,27(5):95-98.(YAN Qingwu,BIAN Zhengfu,ZHANG Ping,et al.Census spatialization based on settlements density[J].Geography and Geo-Information Science,2011,27(5):95-98.)
- [7] 刘建军,李春来.基于遥感和GIS的巢湖流域人口信息提取[J].科学通报,2002,47(23):1835-1837.(LIU Jianjun,LI Chunlai.Population information extraction in Chaohu basin based on remote sensing and GIS[J].Chinese Science Bulletin,2002,47(23):1835-1837.)
- [8] 潘顺.长三角人口数据格网化及其人口空间分布特征分析[D].上海:上海师范大学,2016.(PAN Shun.Population data grid and population spatial distribution analysis in the Yangtze River delta[D].Shanghai:Shanghai Normal University,2016.)
- [9] 毛莹莹.城市人口数据空间化研究:以福州市中心城区为例[D].福州:福建师范大学,2016.(MAO Yingying.Spatialization of urban population data:a case study of Fuzhou central district[D].Fuzhou:Fujian Normal University,2016.)
- [10] 刘焕金.基于多源数据的太湖流域人口空间化研究[D].南京:南京农业大学,2012.(LIU Huanjin.Research on the population specialization basic on multi-source data in Tai lake basin[D].Nanjing:Nanjing Agricultural University,2012.)
- [11] WRIGHT J K.A method of mapping densities of population[J].The Geographical Review,1936,26(1):103-110.
- [12] MARTIN D.Mapping population data from zone centroid locations[J].Transactions of the Institute of British Geographers,1989,14(1):90-97.
- [13] FLOWERDEW R,GREEN M.Developments in areal interpolation methods and GIS[J].The Annals of Regional Science,1992,26(1):67-78.
- [14] GOODCHILD M F,ANSELIN L,DEICHMANN U.A framework for the areal interpolation of socioeconomic data[J].Environment and Planning A,1993,25:383-397.
- [15] 杨眉,王世新,周艺,等.DMSP/OLS夜间灯光数据应用研究综述[J].遥感技术与应用,2011,26(1):45-51.(YANG Mei,WANG Shixin,ZHOU Yi,et al.Review on applications of DMSP/OLS night-time emissions data[J].Remote Sensing Technology and Application,2011,26(1):45-51.)
- [16] 王鹤饶,郑新奇,袁涛.DMSP/OLS数据应用研究综述[J].地理科学进展,2012,10(1):11-18.(WANG Herao,ZHENG Xinqi,YUAN Tao.Overview of researches based on DMSP/OLS nighttime light data[J].Progress in Geography,2012,10(1):11-18.
- [17] ELVIDGE C D,BAUGH K E,KIG E A,et al.Relation between satellite observed visible-near infrared emissions,population,economic activity and electric power consumption[J].International Journal of Remote Sensing,1997,18(6):1373-1379.
- [18] SUTTON K,ROBERTS D,ELVIDGE C.Census from Heaven:an estimate of the global human population using night-time satellite imagery[J].International Journal of Remote Sensing,2001,22(16):3061-3076.
- [19] BRIGGS D J,GULLIVER J,FECHT D,et al.Dasymetric modelling of small-area population distribution using land cover and light emissions data[J].Remote Sensing of Environment,2007,108(4):451-466.
- [20] 卓莉,陈晋,史培军,等.基于夜间灯光数据的中国人口密度模拟[J].地理学报,2005,60(2):266-276.(ZHUO Li,CHEN Jin,SHI Peijun,et al.Modeling population density of China in 1998 based on DMSP/OLS nighttime light image[J].Journal of Geography,2005,60(2):266-276.)
- [21] 曹丽琴,李平湘,张良培.基于DMSP/OLS夜间灯光数据的城市人口估算:以湖北省各县市为例[J].遥感信息,2009(1):83-87.(CAO Liqin,LI Pingxiang,ZHANG Liangpei.Urban population estimation based onthe DMSP/OLS night-time satellite data:a case of Hubei province[J].Remote Sensing Information,2009(1):83-87.)
- [22] 高义,王辉,王培涛,等.基于人口普查与多源夜间灯光数据的海岸带人口空间化分析[J].资源科学,2013,35(12):2517-2523.(GAO Yi,WANG Hui,WANG Peitao,et al.Population spatial processing for Chinese coastal zones based on census and multiple night light data[J].Resources Science,2013,35(12):2517-2523.)
- [23] 李翔,陈振杰,吴洁璇,等.基于夜间灯光数据和空间回归模型的城市常住人口格网化方法研究[J].地球信息科学学报,2017,19(10):1298-1305.(LI Xiang,CHEN Zhenjie,WU Jiexuan,et al.Gridding methods of city permanent population based on night light data and spatial regression models[J].Journal of Geo-information Science,2017,19(10):1298-1305.)
- [24] 高倩,阿里木江.卡斯木.基于DMSP/OLS夜间灯光数据的天山北坡城市群人口分布空间模拟[J].西北人口,2017,38(3):113-120.(GAO Qian,ALIMUJIANG KASIMU.Modeling the population spatial distribution of tianshan north-slope urban agglomeration based on DMSP/OLS night lighting data[J].Northwest Population,2017,38(3):113-120.)
- [25] WU C,MURRAY A T.A cokriging method for estimating population density in urban areas[J].Computers,Environment and Urban Systems,2005,29:558-579.
- [26] GAUGHAN A E,STEVENS F R,LINARD C,et al.High resolution population distribution maps for southeast asia in 2010 and 2015[J].PLOS One,2013,8(2):e55882.
- [27] 颜清梅.基于格网的人口空间分布特征分析[D].成都:四川师范大学,2013.(YAN Qingmei.The analysis of population spatial distribution characteristics based on grid[D].Chengdu:Sichuan Normal University,2013.)
- [28] 吴桂平,曾永年,邹滨,等.基于GIS的区域人口密度空间分布模拟:以张家界市永定区为例[J].测绘科学,2009,34(2):237-240.(WU Guiping,ZENG Yongnian,ZOU Bin,et al.Spatial distribution simulation of regional population density based on GIS:a case study of Yongding District,Zhangjiajie[J].Science of Surveying and Mapping,2009,34(2):237-240.)
- [29] 张建辰,王艳慧.基于土地利用类型的村级人口空间分布模拟:以湖北鹤峰县为例[J].地球信息科学学报,2014,16(3):435-442.(ZHANG Jianchen,WANG Yanhui.Simulation of village-level population distribution based on land use:a case study of Hefeng county in Hubei province[J].Journal of Geo-information Science,2014,16(3):435-442.)
- [30] 林文棋,陈会宴,谢盼,等.基于多源数据的北京市朝阳区人口时空格局评估与预测[J].地球信息科学学报,2018,20(10):1467-1477.(LIN Wenqi,CHEN Huiyan,XIE Pan,et al.Spatial-temporal variation evaluation and prediction of population in Chaoyang district of Beijing based on multisource data[J].Journal of Geo-information Science,2018,20(10):1467-1477.)
- [31] 许玲丽,颜梅春.多源信息多尺度视角的南京市街道级人口模拟研究[J].测绘通报,2019(2):71-75.(XU Lingli,YAN Meichun.Population simulation study of Nanjing streets from multi-source information and multi-scale perspective[J].Bulletin of Surveying and Mapping,2019(2):71-75.)
- [32] 张晓瑞,华茜,程志刚.基于空间句法和LBS大数据的合肥市人口分布空间格局研究[J].地理科学,2018,38(11):1809-1816.(ZHANG Xiaorui,HUA Qian,CHENG Zhigang.Space pattern of urban population distribution based on space syntax and LBS big data[J].Scientia Geographical Sinica,2018,38(11):1809-1816.)
- [33] 黄安,许月卿,孙丕苓,等.基于多源数据人口分布空间化研究:以河北省张家口市为例[J].资源科学,2017,39(11):2186-2196.(HUANG An,XU Yueqing,SUN Piling,et al.Spatial distribution of population specialization based onmulti-source data:a case study of Zhangjiakou city[J].Resources Science,2017,39(11):2186-2196.)
- [34] 谭敏,刘凯,柳林,等.基于随机森林模型的珠江三角洲30 m格网人口空间化[J].地理科学进展,2017,36(10):1304-1312.(TAN Min,LIU Kai,LIU Lin,et al.Spatialization of population in the Pearl River Delta in 30 m grids using random forest model[J].Progress in Geography,2017,36(10):1304-1312.)
- [35] 淳锦,张新长,黄健锋,等.基于POI数据的人口分布格网化方法研究[J].地理与地理信息科学,2018,34(4):83-89.(CHUN Jin,ZHANG Xinchang,HUANG Jianfeng,et al.A gridding method of redistributing population based on POI[J].Geography and Geo-Information Science,2018,34(4):83-89.)
- [36] 符海月,李满春,赵军,等.人口数据格网化模型研究进展综述[J].人文地理,2006,21(3):115-119.(FU Haiyue,LI Manchun,ZHAO Jun,et al.A review of the research progress of population data grid models[J].Human Geography,2006,21(3):115-119.)
- [37] 林丽洁,林广发,颜小霞,等.人口统计数据空间化模型综述[J].亚热带资源与环境学报,2010,5(4):10-16.(LIN Lijie,LIN Guangfa,YAN Xiaoxia,et al.A summary of spatial model of population statistics[J].Journal of Subtropical Resources and Environment,2010,5(4):10-16.)
- [38] BREIMAN L.Random forests[J].Machine Learning,2001,45(1):5-32.
- [39] STEVENS F R,GAUGHAN A E,LINARD C,et al.Disaggregating census data for population mapping using random forests with remotely-sensed and ancillary data[J].Plos One,2015,10(2):e0107042.
- [40] GAUGHAN A E,STEVENS F R,HUANG Z,et al.Spatiotemporal patterns of population in China's mainland,1990 to 2010[J].Scientific Data,2016,3:160005.
- [41] LINARD C,GILBERT M,SNOW R W,et al.Population distribution,settlement patterns and accessibility across africa in 2010[J].Plos One,2012,7(2):e31743.
- [42] 林飞娜,赵文吉,张萍.基于GIS的城市人口空间分布模型与应用:以长春市区为例[J].测绘科学,2008,33(4):163-165.(LIN Feina,ZHAO Wenji,ZHANG Ping.GIS-based spatial distribution model of urban population and its application:a case study of Changchun city[J].Science of Surveying and Mapping,2008,33(4):163-165.)
- [43] 刘睿文,封志明,杨艳昭,等.基于人口集聚度的中国人口集疏格局[J].地理科学进展,2010,29(10):1171-1177.(LIU Ruiwen,FENG Zhiming,YANG Yanzhao,et al.Research on the spatial pattern of population agglomeration and dispersion in China[J].Progress in Geography,2010,29(10):1171-1177.)