Please wait a minute...
Remote Sensing for Natural Resources    2021, Vol. 33 Issue (3) : 164-172     DOI: 10.6046/zrzyyg.2020297
Population spatialization based on geographically weighted regression model considering spatial stability of parameters
XIAO Dongsheng1,2,3(), LIAN Hong1,2()
1. School of Civil Engineering and Surveying and Mapping, Southwest Petroleum University, Chengdu 610500, China
2. Disaster Prevention and Emergency Research Center of Mapping and Remote Sensing Geographic Information of Southwest Petroleum University, Chengdu 610500, China
3. Public Security and Emergency Research Institute, Sichuan Normal University, Chengdu 610068, China
Download: PDF(3434 KB)   HTML
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks    

The theories on population spatialization tend to be mature in recent years. However, the spatial stability of the variables and parameters used in population spatialization modeling has been scarcely focused on. With the land use data, night-time light data, and demographic data as the data sources, this study proposed a novel precise population spatialization method based on a semi-parametric geographically weighted regression model (S-GWR). Then a permanent population spatialization model on a county scale was built using the method proposed in this study and then was verified using the Sichuan Province as the study area. In this study, the spatial stability of parameters and variables were obtained using the S-GWR model while the characteristics of the variables were analyzed, in order to improve the accuracy of population estimation. Finally, the population spatial distribution map (SDP) with a resolution of 1 km of Sichuan Province in 2010 was formed. The results show that the coefficient of determination coefficient of the S-GWR model was 0.903, which is higher than that of traditional regression models and indicates better fitting effects. The S-GWR model was verified using two commonly used population datasets, and the verification results are as follows. At a county level, the overall average error of the study area and the relative error of each district and county in the SDP all approximated to 0, and thus the SDP was more precise than the other two datasets. At a township level, the mean relative error, mean absolute error, and root mean square error of SDP were 34.54%, 5 715.703, and 12 085.932, respectively, which were all lower than those of the other two datasets. Meanwhile, the SDP showed more favorable dispersion effects than the other datasets. Furthermore, the number of the towns whose population was accurately estimated was 185 in the SDP, which was higher than that in the other two datasets. Therefore, the accuracy of population spatialization can be improved by considering the spatial stability of parameters.

Keywords semi-parametric geographically weighted regression      spatial stability      night-time light data      land use      population spatialization     
ZTFLH:  TP79  
Corresponding Authors: LIAN Hong     E-mail:;
Issue Date: 24 September 2021
E-mail this article
E-mail Alert
Articles by authors
Dongsheng XIAO
Cite this article:   
Dongsheng XIAO,Hong LIAN. Population spatialization based on geographically weighted regression model considering spatial stability of parameters[J]. Remote Sensing for Natural Resources, 2021, 33(3): 164-172.
URL:     OR
Fig.1  Night light data map and land use distribution map of Sichuan Province
数据类型 数据年份 分辨率
DMSP/OLS数据 2010年 30″ 美国地球物理国家数据中心
土地利用数据 2010年 1:10万 中国科学院资源环境科学数据中心
人口统计数据 2010年 县、乡镇 四川省统计局
行政区划 2010年 1:10万 原国家测绘局
CGPD 2010年 1 km 中国国家资源环境科学数据中心
GPWv4 2010年 30″ 美国国际地球科学网络中心
Tab.1  Data type and source
Fig.2  Flow chart of population
土地利用类型 相关系数 土地利用类型 相关系数
水田 0.734**① 中覆盖度草地 -0.448**
旱地 0.555** 低覆盖度草地 -0.323**
有林地 -0.438** 水域
灌木林 -0.488** 城镇用地 0.554**
疏林地 -0.108 农村居民用地 0.387**
其他林地 -0.115 其他建成区 0.144*
高覆盖度草地 -0.356** 未利用地
Tab.2  The correlation coefficient between land use types and population data
变量 F统计量 F检验自由度 DIFF of Criterion
水田 2.755 253 2.266 149.509 -0.721 729
旱地 6.148 736 2.850 149.509 -11.687 572
城镇用地LE 22.965 443 2.377 149.509 -49.330 235
城镇用地NL 11.587 845 2.045 149.509 -20.590 824
城镇用地NU 1.382 923 1.882 149.509 2.441 081
农村居民用地LE 1.663 454 0.495 149.509 0.483 673
农村居民用地NL 0.761 547 0.615 149.509 1.267 335
农村居民用地NU 5.406 091 3.707 149.509 -11.939 404
其他建成区LE 0.089 571 2.341 149.509 6.646 620
其他建成区NL 0.666 850 2.706 149.509 5.785 913
其他建成区NU 0.627 823 1.342 149.509 2.966 391
最优带宽 62.000 最小AICc 4 786.266
Tab.3  Parameter estimation and parameter stationarity test of geographically weighted model
评价指标 全局OLS 局部GWR 半参数S-GWR
R2 0.798 0.877 0.903
adjR2 0.785 0.843 0.867
AICc 4 846.167 4 810.764 4 786.267
Tab.4  Evaluation of goodness of fit of three models
Fig.3  Spatial distribution of population in 2010
Fig.4  Relative error box chart of three kinds of datasets
MAE/ 5 715.703 7 997.774 7 256.342
MRE/% 34.54 47.48 45.43
RMSE/ 12 085.932 18 846.285 16 997.919
Tab.5  Accuracy comparison of three datasets
相对误差分级 SDP GPWv4 CGPD
严重低估 48 51 56
一般低估 97 101 114
准确估计 185 151 158
一般高估 107 107 97
严重高估 63 90 75
Tab.6  Statistical table of relative error classification in 500 villages and towns(个)
Fig.5  Relative error ratio of villages and towns
[1] 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.
doi: 10.18306/dlkxjz.2017.10.012
[1] Tan M, Liu K, Liu L, et al. Spatialization of 30 m grid population in Pearl River Delta based on stochastic forest model[J]. Progress in Geography, 2017, 36(10):1304-1312.
[2] 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
[2] Bai Z Q, Wang J L, Yang F. Research progress in spatialization of populationdata[J]. Progress in Geography, 2013, 32(11):1692-1702.
[3] 肖东升, 杨松. 基于夜间灯光数据的人口空间分布研究综述[J]. 国土资源遥感, 2019, 31(3):10-19.doi: 10.6046/gtzyyg.2019.03.02.
doi: 10.6046/gtzyyg.2019.03.02
[3] Xiao D S, Yang S. A survey of population spatial distribution based on night light data[J]. Remote Sensing for Land and Resources, 2019, 31(3):10-19.doi: 10.6046/gtzyyg.2019.03.02.
doi: 10.6046/gtzyyg.2019.03.02
[4] Elvidge C D, Baugh K E, Dietz J B, et al. Radiance calibration of DMSP-OLS low-light imaging data of human settlements[J]. Remote Sensing Enviroment, 1999, 68,77-88.
doi: 10.1016/S0034-4257(98)00098-4 url:
[5] Zhang Q L, Seto K C. Mapping urbanization dynamics at regional and global scales using multi-temporal DMSP/OLS nighttime light data[J]. Remote Sensing of Environment, 2011, 115(9):2320-2329.
doi: 10.1016/j.rse.2011.04.032 url:
[6] 陈晴, 侯西勇, 吴莉. 基于土地利用数据和夜间灯光数据的人口空间化模型对比分析——以黄河三角洲高效生态经济区为例[J]. 人文地理, 2014, 29(5):94-100.
[6] Chen Q, Hou X Y, Wu L. Comparison of population spatialization models based on land use data and DMSP/OLS data respectively:A case study in the efficient ecological economic zone of the Yellow River Delta[J]. Human Geography, 2014, 29(5):94-100.
[7] 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.
[7] Yang X C, Gao D W, Ding M J, et al. Spatialization of population statistics based on multi-source remote sensing data and DEM:A case study of Zhejiang Province[J]. Resources and Environment in the Yangtze Basin, 2013, 22(6):729-734.
[8] 赵利利, 孟芬, 马才学. 基于多源遥感数据的武汉市人口空间分布格局演化[J]. 地域研究与开发, 2016, 35(3):165-169.
[8] Zhao L L, Meng F, Ma C X. Spatial distribution pattern evolution of Wuhan population based on multi-source remote sensing data[J]. Areal Research and Development, 2016, 35(3):165-169.
[9] 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
[9] Hu Y F, Zhao G H, Zhang Q L. Population spatialization in Sichuan and Chongqing based on night lighting and LUC data[J]. Journal of Geo-Information Science, 2018, 20(1):68-78.
[10] 黄杰, 闫庆武, 刘永伟. 基于DMSP/OLS与土地利用的江苏省人口数据空间化研究[J]. 长江流域资源与环境, 2015, 24(5):735-741.
[10] Huang J, Yan Q W, Liu Y W. Spatial analysis of population data in Jiangsu Province based on DMSP/OLS and land use[J]. Resources and Environment in the Yangtze Basin, 2015, 24(5):735-741.
[11] 丁文秀, 赵伟, 左德霖, 等. 基于土地利用分类模型和重力模型耦合的人口分布模拟——以武汉市人口数据为例[J]. 大地测量与地球动力学, 2011, 31(s1):127-131.
[11] Ding W X, Zhao W, Zuo D L, et al. Population distribution simulation based on coupling of land use classification model and gravity model:A case study of Wuhan population data[J]. Geodesy and Geodynamics, 2011, 31(s1):127-131.
[12] Fotheringham A S, Brunsdon C. Local forms of spatial analysis[J]. Geographical Analysis, 2010, 31,340-358.
doi: 10.1111/gean.1999.31.issue-4 url:
[13] 王珂靖, 蔡红艳, 杨小唤. 多元统计回归及地理加权回归方法在多尺度人口空间化研究中的应用[J]. 地理科学进展, 2016, 35(12):1494-1505.
doi: 10.18306/dlkxjz.2016.12.006
[13] Wang K J, Cai H Y, Yang X H. Application of multivariate statistical regression and geographically weighted regression in the study of multi-scale population spatialization[J]. Progress in Geography, 2016, 35(12):1494-1505.
[14] 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.
doi: 10.3724/SP.J.1047.2014.00435
[14] Zhang J C, Wang Y H. Simulation of rural population spatial distribution based on land use classification:A case study of Hefeng County,Hubei Province[J]. Journal of Geo-Information Science, 2014, 16(3):435-442.
[15] 陈晴, 侯西勇. 集成土地利用数据和夜间灯光数据优化人口空间化模型[J]. 地球信息科学学报, 2015, 17(11):1370-1377.
doi: 10.3724/SP.J.1047.2015.01370
[15] Chen Q, Hou X Y. Integrating land use data and night light data to optimize population spatialization model[J]. Journal of Geo-Information Science, 2015, 17(11):1370-1377.
[16] 王明明, 王卷乐. 基于夜间灯光与土地利用数据的山东省乡镇级人口数据空间化[J]. 地球信息科学学报, 2019, 21(5):699-709.
doi: 10.12082/dqxxkx.2019.180497
[16] Wang M M, Wang J L. Spatialization of township population data in Shandong Province based on night lighting and land use data[J]. Journal of Geo-Information Science, 2019, 21(5):699-709.
[17] 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, 18:1295-1304.
[18] 四川统计局. 四川统计年鉴[M]. 北京: 中国统计出版社, 2010.
[18] Statistical Bureau of Sichuan Province. Sichuan statistical yearbook[M]. Beijing: China Statistics Press, 2010.
[19] 杨继瑞, 李月起, 汪锐. 川渝地区: “一带一路”和长江经济带的战略支点[J]. 经济体制改革, 2015(4):58-64.
[19] Yang J R, Li Y Q, Wang R. Sichuan and Chongqing region:Strategic fulcrum of the Belt and Road initiatives and Yangtze River economic zone[J]. Reform of Economic System, 2015(4):58-64.
[20] 刘纪远, 宁佳, 匡文慧, 等. 2010—2015年中国土地利用变化的时空格局与新特征[J]. 地理学报, 2018, 73(5):789-802.
doi: 10.11821/dlxb201805001
[20] Liu J Y, Ning J, Kuang W H, et al. Spatial and temporal patterns and new characteristics of land use change in China from 2010 to 2015[J]. Acta Geographica Sinica, 2018, 73(5):789-802.
[1] YANG Yujin, YANG Fan, XU Zhenni, LI Zhu. Analysis and optimization of the spatio-temporal coordination between the ecological services and economic development in the Dongting Lake area[J]. Remote Sensing for Natural Resources, 2023, 35(3): 190-200.
[2] ZHOU Shisong, TANG Yuqi, CHENG Yuxiang, ZOU Bin, FENG Huihui. Spatial heterogeneity of the correlation between water quality and land use in the Chenjiang River basin, Chenzhou City[J]. Remote Sensing for Natural Resources, 2023, 35(3): 230-240.
[3] LIANG Jintao, CHEN Chao, ZHANG Zili, LIU Zhisong. A random forest-based method integrating indices and principal components for classifying remote sensing images[J]. Remote Sensing for Natural Resources, 2023, 35(3): 35-42.
[4] XIONG Dongyang, ZHANG Lin, LI Guoqing. MaxEnt-based multi-class classification of land use in remote sensing image interpretation[J]. Remote Sensing for Natural Resources, 2023, 35(2): 140-148.
[5] WANG Haiwen, JIA Junqing, LI Beichen, DONG Yongping, HA Sier. Assessing intensive urban land use based on remote sensing images and industry survey data[J]. Remote Sensing for Natural Resources, 2023, 35(2): 149-156.
[6] HUA Yongchun, CHEN Jiahao, SUN Xiaotian, PEI Zhiyong. Analysis of landscape ecology risk of the Yellow River basin in Inner Mongolia[J]. Remote Sensing for Natural Resources, 2023, 35(2): 220-229.
[7] LIU Chunlin, XIA Jianxin. Dynamic simulation of land use based on the LSTM-CA model[J]. Remote Sensing for Natural Resources, 2022, 34(4): 122-128.
[8] YANG Lianwei, ZHAO Juan, ZHU Jiatian, LIU Lei, ZHANG Ping. Spatial-temporal change and prediction of carbon stock in the ecosystem of Xi’an based on PLUS and InVEST models[J]. Remote Sensing for Natural Resources, 2022, 34(4): 175-182.
[9] SHI Shushu, DOU Yinyin, CHEN Yongqiang, KUANG Wenhui. Remote sensing monitoring based analysis of the spatio-temporal changing characteristics of regional urban expansion and urban land cover in China’s coastal zones[J]. Remote Sensing for Natural Resources, 2022, 34(4): 76-86.
[10] WU Linlin, LI Xiaoyan, MAO Dehua, WANG Zongming. Urban land use classification based on remote sensing and multi-source geographic data[J]. Remote Sensing for Natural Resources, 2022, 34(1): 127-134.
[11] SONG Qi, FENG Chunhui, MA Ziqiang, WANG Nan, JI Wenjun, PENG Jie. Simulation of land use change in oasis of arid areas based on Landsat images from 1990 to 2019[J]. Remote Sensing for Natural Resources, 2022, 34(1): 198-209.
[12] WU Jiang, LIU Chun, YING Shen, YU Ting. Spatial delineation methods of urban areas[J]. Remote Sensing for Natural Resources, 2021, 33(4): 89-97.
[13] SANG Xiao, ZHANG Chengye, LI Jun, ZHU Shoujie, XING Jianghe, WANG Jinyang, WANG Xingjuan, LI Jiayao, YANG Ying. Application of intensity analysis theory in the land use change in Yijin Holo Banner under the background of coal mining[J]. Remote Sensing for Natural Resources, 2021, 33(3): 148-155.
[14] DENG Xiaojin, JING Changqing, GUO Wenzhang, Yan Yujiang, CHEN Chen. Surface albedos of different land use types in the Junggar Basin[J]. Remote Sensing for Natural Resources, 2021, 33(3): 173-183.
[15] WANG Qingchuan, XI Yantao, LIU Xinran, ZHOU Wen, XU Xinran. Spatial-temporal response of ecological service value to land use change: A case study of Xuzhou City[J]. Remote Sensing for Natural Resources, 2021, 33(3): 219-228.
Full text



Copyright © 2017 Remote Sensing for Natural Resources
Support by Beijing Magtech