基于随机森林模型的环渤海地区人口空间化模拟

doi:10.12082/dqxxkx.2022.210524

摘要/Abstract

摘要：

人口空间化数据能够将人口分布更精细地反映在地理空间中,可以为科学研究和政策制定提供更加精细的数据源。本文选取多源遥感数据和兴趣点作为影响环渤海地区人口分布的自变量因子,利用随机森林模型对环渤海地区进行分区密度制图,生成该地区2010年和2020年30 m人口空间化数据,并将结果与WorldPop数据集以及其他地区30 m研究成果进行对比。结果表明：① 本文模拟结果精度整体高于WorldPop数据集10%以上;② 相较于WorldPop数据集,本文人口数据能细致地描述环渤海人口分布的空间异质性;③ 与其他地区30 m研究成果相比,模拟精度也有所提升;④ 遥感建成区数据和兴趣点是环渤海地区人口分布的最重要指示性指标;⑤ 在环渤海地区人口估计方面,社会因素与人口分布有更高的相关性,映射人口分布的主要因素因地区而异。

关键词: 环渤海地区, 随机森林, 影响因素, 人口空间化, 多源数据, 兴趣点数据

Abstract:

The spatialization of population at a fine resolution can reflect the explicit size and detailed distribution of the population. It can provide fine-scale data sources for scientific research and policy making. As a national key area of urbanization development in China's main functional zoning and the intensive area of optimizing the development strategy layout, the Bohai Rim Region is one of the areas with relatively high population density and developed economy in China. In this study, the random forest model was applied to multi-source data and points of interest to estimate the population distribution in impervious areas with a spatial resolution of 30 m in the Bohai region. The estimated results were compared with those of the World Pop dataset and other regional studies with the same spatial resolution. Based on the results, the importance of input variables was analyzed. The results showed that the overall accuracy of the simulation predicted in this study was 10% higher than that of the World Pop dataset. Compared with the World Pop population data, the 30-m resolution of our result provided detailed information of population distributions in the Bohai Rim Region. ?Compared with research results in other regions at the same resolution, the accuracy was partially improved. Built-up areas and points-of-interest were the most important indicators of population distribution in the Bohai Rim. Social factors had a higher correlation with population distribution. The main factors affecting the population distribution varied from region to region.

Key words: Bohai Rim region, random forest, influencing factors, population spatialization, multi-source data, point of interest

高雪梅, 杨续超, 陈柏儒, 林琳. 基于随机森林模型的环渤海地区人口空间化模拟[J]. 地球信息科学学报, 2022, 24(6): 1150-1162.DOI:10.12082/dqxxkx.2022.210524

GAO Xuemei, YANG Xuchao, CHEN Bairu, LIN Lin. Spatialization of Population in the Bohai Rim Region Using Random Forest Model[J]. Journal of Geo-information Science, 2022, 24(6): 1150-1162.DOI:10.12082/dqxxkx.2022.210524

图/表 11

图1

表1

表2

图2

表3

表4

图3

图4

表5

表6

图5

参考文献 50

[1]	Aubrecht C, özceylan D, Steinnocher K, et al. Multi-level geospatial modeling of human exposure patterns and vulnerability indicators[J]. Natural Hazards, 2013, 68(1):147-163. DOI: 10.1007/s11069-012-0389-9 doi: 10.1007/s11069-012-0389-9
[2]	Zeng J, Zhu Z Y, Zhang J L, et al. Social vulnerability assessment of natural hazards on county-scale using high spatial resolution satellite imagery: A case study in the Luogang district of Guangzhou, South China[J]. Environmental Earth Sciences, 2012, 65(1):173-182. DOI: 10.1007/s12665-011-1079-8 doi: 10.1007/s12665-011-1079-8
[3]	Ahola T, Virrantaus K, Krisp J M, et al. A spatio-temporal population model to support risk assessment and damage analysis for decision-making[J]. International Journal of Geographical Information Science: Geovisual Analytics for Spatial Decision Support, 2007, 21(8):935-953. DOI: 10.1080/13658810701349078 doi: 10.1080/13658810701349078
[4]	Yao Y, Liu X, Li X, et al. Mapping fine-scale population distributions at the building level by integrating multisource geospatial big data[J]. International Journal of Geographical Information Science, 2017, 31(6):1220-1244. DOI: 10.1080/13658816.2017.1290252 doi: 10.1080/13658816.2017.1290252
[5]	Jia P, Sankoh O, Tatem A J. Mapping the environmental and socioeconomic coverage of the INDEPTH international health and demographic surveillance system network[J]. Health & Place, 2015, 36:88-96. DOI: 10.1016/j.healthplace.2015.09.009 doi: 10.1016/j.healthplace.2015.09.009
[6]	贾建民, 袁韵, 贾轼. 基于人口流动的新冠肺炎疫情风险分析[J]. 中国科学基金, 2020, 34(6):667-674.
	[ Jia J M, Yuan Y, Jia S. Risk Analysis of COVID-19 Based on Population Flow[J]. China Science Foundation, 2020, 34(6):667-674. ] DOI: 10.16262/j.cnki.1000-8217.2020.06.003 doi: 10.16262/j.cnki.1000-8217.2020.06.003
[7]	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. DOI: 10.1371/journal.pone.0055882 doi: 10.1371/journal.pone.0055882
[8]	Su H, Wei H, Zhao J. Density effect and optimum density of the urban population in China[J]. Urban Studies, 2016, 54(7):1760-1777. DOI: 10.1177/0042098015624839 doi: 10.1177/0042098015624839
[9]	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. doi: 10.3724/SP.J.1047.2011.00573
	[ Hu Y F, Wang Q Q, Liu Y, et al. Index system and transferring methods to build the national society and economy grid database[J]. Journal of Geo-information Science, 2011, 13(5):573-578. ] doi: 10.3724/SP.J.1047.2011.00573
[10]	柏中强, 王卷乐, 杨飞. 人口数据空间化研究综述[J]. 地理科学进展, 2013, 32(11):1692-1702. doi: 10.11820/dlkxjz.2013.11.012
	[ Bo Z Q, Wang J L, Yang F. Research progress in spatialization of population data[J]. Progress in Geography, 2013, 32(11):1692-1702. ] DOI: 10.11820/dlkxiz.2013.11.012 doi: 10.11820/dlkxiz.2013.11.012
[11]	李军, 胡云峰. 我国经济社会统计数据空间均匀程度分析[J]. 地域研究与开发, 2009, 28(3):130-134.
	[ Li J Hu Y F. Study on the spatial unifomity of economic and social index based on geographic infomation system[J]. Areal Research and Dvelopment, 2009, 28(3):130-134. ] DOI: 10. 3969/j.issn.1003-2363.2009.03.029 doi: 10. 3969/j.issn.1003-2363.2009.03.029
[12]	Bakillah M, Liang S, Mobasheri A, et al. Fine-resolution population mapping using OpenStreetMap points-of-interest[J]. International Journal of Geographical Information Science, 2014, 28(9):1940-1963. DOI: 10.1080/13658816.2014.909045 doi: 10.1080/13658816.2014.909045
[13]	Wang L, Wang S, Zhou Y, et al. Mapping population density in China between 1990 and 2010 using remote sensing[J]. Remote Sensing of Environment, 2018, 210:269-281. DOI: 10.1016/j.rse.2018.03.007 doi: 10.1016/j.rse.2018.03.007
[14]	袁锦标, 曹永旺, 倪方舟,等. 中国县域人口集聚空间格局及影响因素的空间异质性研究[J]. 地理与地理信息科学, 2020, 36(3):25-33.
	[ Yuan J B, Cao Y W, Ni F Z, et al. A study on the spatial pattern of county population agglomeration and the spatial heterogeneity of Its influencing factors in China[J]. Geography and Geo-Information Science, 2020, 36(3):25-33. ] DOI: 10.3969/issn.1672-0504.2020.03.004 doi: 10.3969/issn.1672-0504.2020.03.004
[15]	Lin J, Cromley R G. Evaluating geo-located Twitter data as a control layer for areal interpolation of population[J]. Applied Geography, 2015, 58:41-47. DOI: 10.1016/j.apgeog.2015.01.006 doi: 10.1016/j.apgeog.2015.01.006
[16]	Qiu F, Cromley R. Areal interpolation and dasymetric modeling[J]. Geographical Analysis, 2013, 45(3):213-215. DOI: 10.1111/gean.12016 doi: 10.1111/gean.12016
[17]	Balk D L, Deichmann U, Yetman G, et al. Determining global population distribution: methods, applications and data[J]. Adv Parasitol, 2006, 62:119-156. DOI: 10.1016/S0065-308X(05)62004-0 doi: 10.1016/S0065-308X(05)62004-0
[18]	Bhaduri B, Bright E, Coleman P, et al. LandScan USA: A high-resolution geospatial and temporal modeling approach for population distribution and dynamics[J]. GeoJournal, 2007, 69(1-2):103-117. DOI: 10.1007/s10708-007-9105-9 doi: 10.1007/s10708-007-9105-9
[19]	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):e107042. DOI: 10.1371/journal.pone.0107042 doi: 10.1371/journal.pone.0107042
[20]	付晶莹, 江东, 黄耀欢. 中国公里网格人口分布数据集[J]. 地理学报, 2014, 69(s1):41-44. doi: 10.11821/dlxb2014S006
	[ Fu J Y, Dong J, Huan H Y. PopularionGrid_ China[J]. Acta Geographica Sinica, 2014, 69(s1):41-44. ] DOI: 10.11821/dlxb2014S006 doi: 10.11821/dlxb2014S006
[21]	邱歌. 基于随机森林模型的高精度人口数据空间化[D]. 呼和浩特: 内蒙古师范大学, 2019.
	[ Qiu G. High-resolution population mapping using a random forest model: A case study in Zhengzhou, China[D]. Hohhot: Inner Mongolia Teaching University, 2019. ]
[22]	董南, 杨小唤, 蔡红艳. 人口数据空间化研究进展[J]. 地球信息科学学报, 2016, 18(10):1295-1304. doi: 10.3724/SP.J.1047.2016.01295
	[ Dong N, Yang X H, Cai H Y. Research progress and perspective on the spatialization of population data[J]. Journal of Geo-information Science, 2016, 18(10):1295-1304. ] DOI: 10.3724/SPJ.1047.2016.01295 doi: 10.3724/SPJ.1047.2016.01295
[23]	Zhou Y, Ma M, Shi K, et al. Estimating and interpreting fine-scale gridded population using random forest regression and multisource data[J]. ISPRS International Journal of Geo-Information, 2020, 9(6):369. DOI: 10.3390/ijgi9060369 doi: 10.3390/ijgi9060369
[24]	王超, 阚瑷珂, 曾业隆,等. 基于随机森林模型的西藏人口分布格局及影响因素[J]. 地理学报, 2019, 74(4):664-680. doi: 10.11821/dlxb201904004
	[ Wang C, Kan A K, Zeng Y L, et al. Population distribution pattern and influencing factors in Tibet based on random forest model[J]. Acta Geographica Sinica, 2019, 74(4):664-680. ] DOI: 10.11821/dlxb201904004 doi: 10.11821/dlxb201904004
[25]	刘艺, 杨歆佳, 刘劲松. 基于随机森林的人口密度模型优化试验研究[J]. 全球变化数据学报(中英文), 2020, 4(4):402-416.
	[ Liu Y, Yang X J, Liu J S. Experimental study on optimization of population density models based on random forest[J]. Global Change Research Data Publishing & Repository, 2020, 4(4):402-416. ] DOI: 0.3974/geodp.2020.04.15 doi: 0.3974/geodp.2020.04.15
[26]	Gaughan A E, Stevens F R, Huang Z, et al. Spatiotemporal patterns of population in mainland China, 1990 to 2010[J]. Scientific Data, 2016, 3(1):160005. DOI: 10.1038/sdata.2016.5 doi: 10.1038/sdata.2016.5
[27]	Sorichetta A, Hornby G M, Stevens F R, et al. High-resolution gridded population datasets for Latin America and the Caribbean in 2010, 2015, and 2020[J]. Scientific Data, 2015, 2(1):150045. DOI: 10.1038/sdata.2015.45 doi: 10.1038/sdata.2015.45
[28]	谭敏, 刘凯, 柳林,等. 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. doi: 10.18306/dlkxjz.2017.10.012
	[ Tan M, Liu K, Liu L, et al. Spatialization of population in the Pearl River Delta in 30m grids using random forest model[J]. Progress in Geography, 2017, 36(10):1304-1312. ] DOI: 10.18306/dlkxiz2017.10.012 doi: 10.18306/dlkxiz2017.10.012
[29]	廖顺宝, 孙九林. 基于GIS的青藏高原人口统计数据空间化[J]. 地理学报, 2003, 58(1):25-33.
	[ Liao S B, Sun J L. GIS based spatialization of population census data in Qinghai-Tibet Plateau[J]. Acta Geographica Sinica, 2003, 58(1):25-33. ] DOI: 10.11821/xb200301004. doi: 10.11821/xb200301004.
[30]	马钰琪, 朱秀芳, 刘宪锋,等. 基于夜间灯光数据和多地理因子数据的人口空间化方法--以辽宁省为例[J]. 北京师范大学学报(自然科学版), 2015, 51(S1):57-61.
	[ Ma Y Q, Zhu X F, Liu X F, et al. A population spatialization method based on DMSP/OLS night time light data and weighted multi-geographic factors: The example of Liaoning Province[J]. Journal of Beijing Normal University (Natural Science), 2015,51( S1):57-61. ] DOI: 10.16360/j.cnki.bruns.2015.s1.009 doi: 10.16360/j.cnki.bruns.2015.s1.009
[31]	胡云锋, 赵冠华, 张千力. 基于夜间灯光与LUC数据的川渝地区人口空间化研究[J]. 地球信息科学学报, 2018, 20(1):68-78. doi: 10.12082/dqxxkx.2018.170224
	[ Hu Y F, Zhao G H, Zhang Q L. Spatial distribution of population data based on nighttime light and LUC data in the Sichuan-Chongqing Region[J]. Journal of Geo-information Science, 2018, 20(1):68-78. ] DOI: 10.12082/dqxxkx.2018.170224 doi: 10.12082/dqxxkx.2018.170224
[32]	邹雅婧, 闫庆武, 黄杰,等. 基于LJ1-01夜间灯光影像的苏锡常地区人口空间化研究[J]. 长江流域资源与环境, 2020, 29(5):1086-1094.
	[ Zou Y J, Yan Q W, Huang J, et al. Modeling the population density of Su-Xi-Chang Region based on Luojia-1A nighttime light image[J]. Resources and Environment in the Yangtze Basin, 2020, 29(5):1086-1094. ] DOI: 10.11870/cjlyzyyhj202005004 doi: 10.11870/cjlyzyyhj202005004
[33]	王璇璇, 赵明松, 谢毅,等. 基于NPP-VIIRS夜光遥感的江苏省人口数据空间化研究[J]. 黑龙江工程学院学报, 2020, 34(3):31-35.
	[ Wang X X, Zhao M S, Xie Y, et al. Research on the population data spatialization based on NPP-VIIRS nighttime light data in Jiangsu Province[J]. Journal of Heilongjiang Institute of Technology, 2020, 34(3):31-35. ] DOI: 10.19352/j.cnki,issnI671-4679.2020.03,007 doi: 10.19352/j.cnki,issnI671-4679.2020.03,007
[34]	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 Y, Wang H, Wang P T, 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. ] DOI: CNKI:SUN:ZRZY.0.2013-12-024 doi: CNKI:SUN:ZRZY.0.2013-12-024
[35]	Ye T, Zhao N, Yang X, et al. Improved population mapping for China using remotely sensed and points-of-interest data within a random forests model[J]. Science of The Total Environment, 2019, 658:936-946. DOI: 10.1016/j.scitotenv.2018.12.276 doi: 10.1016/j.scitotenv.2018.12.276
[36]	朱守杰, 杜世宏, 李军,等. 融合多源空间数据的城镇人口分布估算[J]. 地球信息科学学报, 2020, 22(8):1607-1616.
	[ Zhu S J, Du S H, Li J, et al. Estimating population distribution in cities and towns though fusing multi-source spatial data[J]. Journal of Geo-information Science, 2020, 22(8):1607-1616. ] DOI: 10.12082/dqxxkx.2020.190783 doi: 10.12082/dqxxkx.2020.190783
[37]	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 J, Zhang X C, Huang J F, et al. A gridding method of redistributing population based on POIs[J]. Geography and Geo-information Science, 2018, 34(4):83-89. ] DOI: 10.3969/j.issn.1672-0504.2018.04.013 doi: 10.3969/j.issn.1672-0504.2018.04.013
[38]	Yang X, Yao C, Chen Q, et al. Improved estimates of population exposure in low-elevation coastal zones of China[J]. International Journal of Environmental Research and Public Health, 2019, 16(20):4012. DOI: 10.3390/ijerph16204012 doi: 10.3390/ijerph16204012
[39]	Chen Z, Yu B, Yang C, et al. An extended time series (2000-2018) of global NPP-VIIRS-like nighttime light data from a cross-sensor calibration[J]. Earth System Science Data, 2021, 13(3):889-906. DOI: 10.5194/essd-13-889-2021 doi: 10.5194/essd-13-889-2021
[40]	Esch T, Heldens W, Hirner A, et al. Breaking new ground in mapping human settlements from space-The Global Urban Footprint[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2017, 134:30-42. DOI: 10.1016/j.isprsjp rs.2017.10.012 doi: 10.1016/j.isprsjp rs.2017.10.012
[41]	Kuang W, Zhang S, Li X, et al. A 30 m resolution dataset of China's urban impervious surface area and green space, 2000-2018[J]. Earth System Science Data, 2021, 13(1): 63-82. DOI: 10.5194/essd-13-63-2021 doi: 10.5194/essd-13-63-2021
[42]	曾永明. 中国人口空间分布形态模拟与预测--基于“五普”和“六普”的分县尺度人口密度研究[J]. 人口与经济, 2016(6):48-61.
	[ Zeng Y M Simulation and projection on the pattern of Chinese population spatial distribution: research with population density of county level based on the 5th and 6th population census of China[J]. Population & Economics, 2016(6):48-61. ] DOI: 10.3969/j.issn.1000-4149.2016.06.005 doi: 10.3969/j.issn.1000-4149.2016.06.005
[43]	Shi X, Li M, Hunter O, et al. Estimation of environmental exposure: interpolation, kernel density estimation or snapshotting[J]. Annals of GIS, 2018, 25(1):1-8. DOI: 10.1080/19475683.2018.1555188 doi: 10.1080/19475683.2018.1555188
[44]	Breiman L. Random Forest[J]. Machine Learning, 2001, 45(1):5-32. DOI: 10.1023/A:1010933404324 doi: 10.1023/A:1010933404324
[45]	Breiman L. Statistical Modeling: The Two Cultures[J]. Statistical Science, 2001, 16(3):199-231. DOI: 10.1214/ss/1009213726 doi: 10.1214/ss/1009213726
[46]	人民网-北京频道. 北京:争取明年或到后年陆续将第二批行政事业单位搬到副中心[EB/OL]. http://bj.people.com.cn/n2/2021/12 01/c233088-35031445.html, 2021-12-01 .
	[ Beijing: Strive to move the second batch of administrative institutions to the sub-center next year or the following year[EB/OL]. http://bj.people.com.cn/n2/2021/12 01/c233088-35031445.html, 2021-12-01 ]
[47]	柏中强, 王卷乐, 杨雅萍,等. 基于乡镇尺度的中国25省区人口分布特征及影响因素[J]. 地理学报, 2015, 70(8):1229-1242. doi: 10.11821/dlxb201508004
	[ Bo Z Q , Wang J L, Yang Y P, et al. Characterizing spatial patterns of population distribution at township level across the 25 provinces in China[J]. Acta Geographica Sinica, 2015, 70(8):1229-1242. ] DOI: 10.11821/dlxb201508004 doi: 10.11821/dlxb201508004
[48]	Liu Y, Delahunty T, Zhao N, et al. These lit areas are undeveloped: Delimiting China's urban extents from thresholded nighttime light imagery[J]. International Journal of Applied Earth Observation and Geoinformation, 2016, 50: 39-50. DOI: 10.1016/j.jag.2016.02.011 doi: 10.1016/j.jag.2016.02.011
[49]	方瑜, 欧阳志云, 郑华,等. 中国人口分布的自然成因[J]. 应用生态学报, 2012, 23(12):3488-3495. pmid: 23479895
	[ Fang Y, Ouyang Z Y, Zheng H, et al. Natural forming causes of China population distribution[J]. Chinese Journal of Applied Ecology, 2012, 23(12):3488-3495. ] DOI: 10.13287/j.1001-9332.2012.0434 doi: 10.13287/j.1001-9332.2012.0434 pmid: 23479895
[50]	杨续超, 高大伟, 丁明军,等. 基于多源遥感数据及DEM的人口统计数据空间化--以浙江省为例[J]. 长江流域资源与环境, 2013, 22(6):729-734.
	[ Yang X CB,Gao D W, Ding M J, et al. Modeling population density using multi-sensor remote sensing data and DEM: A case study of Zhejing Province[J]. Resources and Environment in the Yangtze Basin, 2013, 22(6):729-734. ]

数据源	类型/分辨率	年份	数据来源
人口统计数据	表格	2010	《中国统计年鉴2011》第六次人口普查资料
		2020	环渤海地区各市第七次人口普查统计公报
高程	栅格/1''		美国宇航局（National Aeronautics and Space Administration,NASA）与日本经济产业省共同推出的ASTER GDEM V2数据集
坡度	栅格/1''		基于DEM数据提取
夜间灯光	栅格/30''	2010	美国国家海洋和大气管理局（National Oceanic and Atmospheric Administration,NOAA）, DMSP/OLS传感器
	栅格/500 m	2020	Chen等^[39]生产的“类NPP-VIIRS”夜间灯光数据集
NDVI	栅格/250 m	2010/2020	MOD13Q1数据集
建成区	栅格/0.4''	2012	德国航空航天中心的全球城市足迹数据（Global Urban Footprint,GUF）^[40]
	栅格/30 m	2018	Kuang等的CLUD-Urban产品^[41]
POI	矢量点	2010	百度地图开放平台
		2020	高德地图开发平台
路网	矢量线	2011	中国科学院资源与环境数据中心
		2019	Open Street Map（OSM）
WorldPop数据集	栅格/3''	2010/2020	WorldPop项目官网 http://www.worldpop.org/

数据来源	数据类别	数量/个	数据类别	数量/个	数据类别	数量/个
百度地图开发平台	政府机构	79 721	高速服务区	4 756	医院	31 752
	机场	84	收费站	2 637	学校科研院所	54 454
	轨道交通站点	2 477	银行	58 171	公司企业	134 335
	汽车站	1 409	商业大厦	5 864	公园广场	2 429
	公交车站	78 166	零售行业	159 441	住宅小区	32 753
	加油（气）站	22 649	宾馆酒店	21 539	其他	97 177
	停车场	25 963	餐饮娱乐业	131 853
高德地图开发平台	政府机关及社会团体	385 066	高速服务区	295 422	体育休闲服务	114 001
	交通设施服务	435 451	收费站	97 633	生活服务	188 239
	加油（气）站	27 168	银行	43 109	风景名胜	83 195
	道路附属设施	7 434	商业大厦	130 917	公共设施	36 549
	金融保险服务	145 478	科教文化服务	495 534
	商务住宅	215 414	公司企业	112 611

	数据集	MAE	RMSE	%RMSE
环渤海地区	预测数据	11 240.09	18 942.01	49.02
环渤海地区	WorldPop数据集	14 098.98	23 066.32	59.70
辽宁省	预测数据	11 277.59	19 308.57	67.92
辽宁省	WorldPop数据集	13 916.92	23 646.23	83.17
京津冀	预测数据	10 721.40	17 836.59	49.19
京津冀	WorldPop数据集	13 058.71	22 040.99	60.78
山东省	预测数据	12 962.12	20 213.69	40.01
山东省	WorldPop数据集	15 782.21	24 026.49	47.55

数据集	验证区域	R²	MAE	RMSE	%RMSE
本文结果	北京320个街道	0.6669	21 499.69	36 633.69	55.15
WorldPop数据集	北京320个街道	0.4488	27 501.50	47 121.44	70.94

数据集	研究区域	面积/km²	数据种类	变量数量	解释变量
Zhou等^[23]	重庆九城区	5472.68	夜间灯光、POI、水域、DEM、坡度	18	夜间灯光强度、14类POI核密度、与水体距离、高程、坡度
谭敏等^[28]	珠江三角洲	5.54万	夜间灯光、道路、水域、建成区、DEM、坡度	13	夜间光照强度、与道路的距离、与水的距离、坡度、高程、4种道路的长度等
本文成果	环渤海地区	51.8万	夜间灯光、道路、POI、建成区、NDVI、DEM、坡度	7	夜间灯光强度、道路核密度、融合后POI核密度、建成区、NDVI、高程、坡度
WorldPop 数据集	中美洲、南美洲、非洲和亚洲		土地利用、NPP、夜灯、平均年降水量、平均年温度,POI、道路、河流、水体	74	13类土地利用（分类数据和欧式距离）、NPP、夜间灯光强度、平均年降水量、平均年温度、、高程、坡度、到河流的距离、到道路的距离、20类POI（分类数据和欧式距离）