当前中国正处于快速城市化发展阶段，截至2021年中国城市化率已达63.89%。城市的不断扩张引发一系列社会问题，其中因大量青壮年劳动力由农村涌入城市谋生导致的局地“人口空心化”现象引起学术界的关注。大量农村人口迁移导致局地人口在数量和结构上发生显著变化，乡村人口数量锐减，人口老龄化及少儿化，土地撂荒等问题突显。中国已于2021年实现脱贫攻坚目标任务。2021年2月21日，《中共中央国务院关于全面推进乡村振兴加快农业农村现代化的意见》发布。显然，人口成为巩固脱贫成果及实现乡村振兴的重要保障。然而不断加剧的人口空心化对实现乡村振兴带来了巨大的挑战。因此，人口空心化研究具有重要理论与实践价值。

识别人口空心化时空分布特征是解决人口空心化问题的前提与必要条件。前人针对人口空心化的研究虽取得一定进展，但目前仍存瓶颈：1）人口普查与统计数据现势性较差、时空分辨率低，更新缓慢，难以揭示行政区划内部人口时空分布异质性；2）人口空心化时空动态特征不清，且已有研究时空覆盖度低，难以满足局地对人口空心化特征识别的需要；3）人口空心化驱动机制不明，难以厘清人口空心化的动因。

中部地区是我国重要的能源基地、交通枢纽、农产品基地和劳动力输出基地，为了振兴中部地区，2006年中共中央、国务院发出了《关于促进中部地区崛起的若干意见》。然而，2021年5月11日公布的第七次全国人口普查结果显示中部地区人口占25.83%，与2010年相比，中部的地区下降0.79个百分点。人口空心化对实现中部地区崛起形成严峻挑战。基于此，本文选择中部六省为研究区，以人口空心化程度为研究对象，基于夜间灯光遥感影像、社会感知数据和已有数据资料，利用随机森林模型估算人口空心化程度，生产人口空心化程度地图数据产品；基于标准误差椭圆、坡度模型对中部六省人口空心化程度时空动态进行研究；建立影响因素与人口空心化程度定量关系模型，基于地理探测器进行人口空心化驱动机制研究。研究结果可为实现乡村振兴提供基础数据支撑，具有重要的科学意义和应用价值。

主要研究结论如下：

本文利用熵权法构建人口空心化程度的指数，并对研究区进行潜在人口空心化地区的识别，最后利用随机森林模型，地理加权回归模型以及多元线性回归模型进行人口空心化程度模拟。经过筛选，共保留6742个潜在人口空心化区域，结果显示大多集中在农村地区；各省潜在空心化乡镇数量占乡镇总数的比例排序为：江西省（86%）>湖南省（84%）>湖北省（72%）>安徽省（68%）>山西省（63%）>河南省（61%），从数量上来看，江西省的潜在人口空心化地区数量最多，河南省的潜在空心化地区数量最少；多模型人口空心化建模与验证的结果显示：随机森林模型精度（R_c²=0.6152，R_v²=0.595）＞地理加权回归模型精度（R_c²=0.4279，R_v²=0.386）＞多元线性回归模型精度（R_c²=0.1041，R_v²=0.0729）。因此，随机森林模型为人口空心化模型模拟的最佳模型。

本文利用人口空心化指数得到乡镇尺度人口空心化分布图，利用最佳模型得到栅格尺度人口空心化分布地图，并进行空间自相关诊断以及时空动态特征分析。中部六省人口空心化呈现“北高南低”的分布，栅格尺度分布图更能显示出区域内部的空间异质性；2016年-2020年人口空心化呈现“北降南升”的分布以及人口空心化“重心南移”的变化趋势，其分布呈现高度空间自相关性。最后，通过分析发现中部六省人口空心化分布以及程度可能受到自然地理，社会经济以及国家政策的影响。

本文基于地理探测器方法对中部六省人口空心化现象进行驱动机制研究。因子探测结果显示中部六省人口空心化主要受到自然要素影响（其中NDVI对因变量解释力最强），其次为气象要素以及空气污染变量；交互探测结果显示两要素的交互作用一定大于单一要素，与因子探测结果一致，自然要素间的交互作用对中部六省人口空心化影响最大（其中NDVI与各变量的交互作用解释力最强），其次为气象要素以及空气污染变量与各类因子间的交互作用；区位交通以及社会经济因子无论从单一因子的解释力还是与其他变量的交互解释力来说，对人口空心化的影响都是不显著的。

At present, China is in the stage of rapid urbanization development. As of 2021, China's urbanization rate has reached 63.89%. The continuous expansion of cities has caused a series of social problems. Among them, the phenomenon of local "population hollowing" caused by the influx of a large number of young and middle-aged laborers from rural areas to cities to make a living has attracted the attention of academic circles. The migration of a large number of rural populations has led to significant changes in the number and structure of the local population. The number of rural populations has dropped sharply, the population is aging and children are aging, and problems such as land abandonment are prominent. China has achieved the goal of poverty alleviation by 2021. On February 21, 2021, the "Opinions of the Central Committee of the Communist Party of China and the State Council on Comprehensively Promoting Rural Revitalization and Accelerating Agricultural and Rural Modernization" was released. Obviously, population has become an important guarantee for consolidating the achievements of poverty alleviation and realizing rural revitalization. However, the ever-increasing population hollowing has brought great challenges to the realization of rural revitalization. Therefore, the study of population hollowing has important theoretical and practical value.

Identifying the temporal and spatial distribution characteristics of population hollowing is the premise and necessary condition to solve the problem of population hollowing. Although previous studies on population hollowing have made some progress, there are still bottlenecks: 1) Population census and statistical data have poor current status, low spatial and temporal resolution, and slow updating, making it difficult to reveal the heterogeneity of population spatial and temporal distribution within administrative divisions; 2) The spatiotemporal dynamic characteristics of population hollowing are unclear, and the coverage of existing studies is low, which makes it difficult to meet the needs of local identification of population hollowing characteristics; 3) The driving mechanism of population hollowing is unclear, and it is difficult to clarify the motivation of population hollowing.

The central region is an important energy base, transportation hub, agricultural product base and labor export base in China. In order to revitalize the central region, the Central Committee of the Communist Party of China and the State Council issued "Several Opinions on Promoting the Rise of the Central Region" in 2006. However, the results of the seventh national census released on May 11, 2021 showed that the central region accounted for 25.83% of the population, a decrease of 0.79 percentage points compared with 2010. Population hollowing poses a serious challenge to the rise of the central region. Based on this, this paper selects the six central provinces as the research area, takes the degree of population hollowing as the research object, and uses the random forest model to estimate the degree of population hollowing based on nighttime light remote sensing images, social perception data and existing data, and the production population hollowing. Degree map data product; based on standard error ellipse and slope model to study the spatiotemporal dynamics of population hollowing degree in six central provinces; establish a quantitative relationship model between influencing factors and population hollowing degree, and conduct research on the driving mechanism of population hollowing based on geographic detectors. The research results can provide basic data support for the realization of rural revitalization, and have important scientific significance and application value.

The main contents are as follows:

(1) In this paper, the entropy weight method is used to construct an index of the degree of population hollowing, and the potential population hollowing area is identified in the study area. Finally, the random forest model, the geographically weighted regression model and the multiple linear regression model are used to simulate the population hollowing degree. After screening, a total of 6,742 potential population hollowing areas were retained, and the results showed that most of them were concentrated in rural areas; the proportion of potential hollowing townships in each province to the total number of townships was ranked as follows: Jiangxi Province (86%) > Hunan Province (84%) > Hubei Province Province (72%) > Anhui Province (68%) > Shanxi Province (63%) > Henan Province (61%), in terms of quantity, Jiangxi Province has the largest number of potential population hollow areas, and Henan Province has the largest number of potential hollow areas The number is the least; the results of multi-model population hollowing modeling and validation show that: random forest model accuracy (Rc2=0.6152, Rv2=0.595) > geographic weighted regression model accuracy (Rc2=0.4279, Rv2=0.386) > multiple linear regression model accuracy (Rc2=0.1041, Rv2=0.0729). Therefore, the random forest model is the best model simulated by the population hollowing model.

(2) This paper uses the population hollowing index to obtain the population hollowing distribution map at the township scale, and uses the best model to obtain the population hollowing distribution map at the grid scale. The population hollowing of the six central provinces shows the distribution of "high in the north and low in the south", and the grid-scale distribution map can better show the spatial heterogeneity within the region; the hollowing of the population from 2016 to 2020 shows the distribution of "falling in the north and rising in the south" As well as the trend of population hollowing "center of gravity moving south", its distribution shows a high degree of spatial autocorrelation. Finally, through analysis, it is found that the distribution and degree of population hollowing in the six central provinces may be affected by physical geography, social economy and national policies.

This paper studies the driving mechanism of population hollowing in six central provinces based on the geographic detector method. The factor detection results show that the population hollowing in the six central provinces is mainly affected by natural factors (in which NDVI has the strongest explanatory power for the dependent variable), followed by meteorological factors and air pollution variables; the interaction detection results show that the interaction between the two factors must be greater than that of a single factor. Consistent with the factor detection results, the interaction between natural factors has the greatest impact on population hollowing in the six central provinces (in which the interaction between NDVI and each variable has the strongest explanatory power), followed by meteorological factors and the relationship between air pollution variables and various factors. Interactions; location traffic and socioeconomic factors have no significant effect on population hollowing in terms of the explanatory power of a single factor or the interaction with other variables.

[1] 李卓倩. 不同地域条件下村庄空心化特征评价及驱动机制研究[D]. 河南农业大学, 2020.

[2] 陈坤秋, 王良建, 李宁慧. 中国县域农村人口空心化——内涵、格调与机理[J]. 人口与经济, 2018(1): 28-37.

[3] 郑殿元, 文 琦, 王 银, 等. 中国村域人口空心化分异机制及重构策略[J]. 经济地理, 2019, 39(2): 161-168, 189.

[4] 周祝平. 中国农村人口空心化及其挑战[J]. 人口研究, 2008, 32(2): 45-52.

[5] 陈涛, 陈池波. 人口外流背景下县域城镇化与农村人口空心化耦合评价研究[J]. 农业经济问题, 2017, 38(04): -66+111.

[6] 李彩红. 新型城镇化下河南农村空心化问题研究[J]. 农村经济与科技, 2020, 31(05): 268-270.

[7] 孙超杰. 湖北省农村人口空心化影响因素研究[D]. 中南财经政法大学, 2019.

[8] Zhang T, Wang Y, Liu Y, et al. Establishing an economic insurance system under a multiple dynamic evolution mechanism after rural hollowing renovation[J]. Resources Science, 2016, 38(05).

[9] Guo B, Bian Y, Zhang D, Su Y, Wang X, Zhang B, et al. Estimating Socio-Economic Parameters via Machine Learning Methods Using Luojia1-01 Nighttime Light Remotely Sensed Images at Multiple Scales of China in 2018. IEEE Access, 2021a, 9, 34352-34365. https://doi.org/10.1109/ACCESS.2021. 3059865.

[10] Zhu X, Li Q, Shen M, Chen J, et al. A methodology for multiple cropping index extraction based on NDVI time-series. Natural Resour, 2008, 23, 534–544.

[11] Liang H, Guo Z, Wu J, et al. GDP spatialization in Ningbo City based on NPP/VIIRS night-time light and auxiliary data using random forest regression. Advances in Space Research, 2020a, 65(1).

[12] Langford M, Higgs G, et al. Urban population distribution models and service accessibility estimation [J]. Comput. Environ. Urban Syst. 2008, 32, 66–80.

[13] Zeng C, Zhou Y, et al. Population spatialization in China based on night-time imagery and land use data [J]. Int. J. Remote Sens. 2011, 24, 9599–9620.

[14] Silvan-Cardenas J L, Wang L, et al. Assessing fine-spatial-resolution remote sensing for small-area population estimation [J]. Int. J. Remote Sens. 2010, 31, 5605–5634.

[15] Calka B, Nowak Da Costa J, et al. Fine scale population density data and its application in risk assessment [J]. Geomat. Nat. Hazards Risk, 2017, 8, 1440–1455.

[16] Guo B, Zhang D, Zhang D, Su Y, Wang X, et al. Detecting spatiotemporal dynamic of regional electric consumption using NPP-VIIRS nighttime stable light data–A case study of Xi'an, China. IEEE Access, 2020a, 8, 171694-171702.

[17] Wang C, Chen Z, Yang C, Li Q, et al. Analyzing parcel-level relationships between Luojia 1-01 nighttime light intensity and artificial surface features across Shanghai, China: A comparison with NPP-VIIRS data. International Journal of Applied Earth Observations and Geoinformation, 2020a, 85.

[18] Niu T, Chen Y, et al. Measuring urban poverty using multi-source data and a random forest algorithm: A case study in Guangzhou. Sustainable Cities and Society, 2020, 54.

[19] Zhang F, Zhang D, Liu Y, et al. Representing place locales using scene elements. Computers, Environment and Urban Systems, 2018, 71, 153–164.

[20] Joshua B, Gabriel C, et al. Predicting poverty and wealth from mobile phone metadata. Science, 2015, 350(6264), 1073–1076.

[21] Long Y, Shen Z. Geospatial Analysis to Support Urban Planning in Beijing. Springer, Cham, 2015, 116.

[22] Hu L, He S, Han Z, Xiao H, et al. Monitoring housing rental prices based on social media: An integrated approach of machine-learning algorithms and hedonic modeling to inform equitable housing policies. Land Use Policy, 2019, 82, 657–673.

[23] Ye T, Zhao N, Yang X, Ouyang Z, et al. Improved population mapping for China using remotely sensed and points-of-interest data within a random forests model. Science of the Total Environment, 2019, 658, 936-946. https://doi.org/10.1016/j.scitotenv.2018.12.276.

[24] Levin N, and Duke Y. High spatial resolution night-time light images for demographic and socio-economic studies. Remote Sensing of Environment, 2012, 119, 1-10.

[25] Lu L, Weng Q, Xie Y, Guo H, et al. An assessment of global electric power consumption using the Defense Meteorological Satellite Program-Operational Linescan System nighttime light imagery[J]. Energy, 2019, 189.

[26] Mills G, Pleijel H, et al. Tropospheric Ozone Assessment Report: Present-day tropospheric ozone distribution and trends relevant to vegetation. Elem Sci Anth, 2018, 6(1).

[27] Zhao N, Liu Y, et al. Forecasting China's GDP at the pixel level using nighttime lights time series and population images. GIScience & Remote Sensing. 2017, 54, 407-25.

[28] Shi K, Chang Z, Chen Z, Wu J, et al. Identifying and evaluating poverty using multisource remote sensing and point of interest (POI) data: A case study of Chongqing, China. J. Clean. Prod, 2020, 255.

[29] Ingacheva A, Kokhan V. Mapping China' s Ghost Cities through the Combination of Nighttime Satellite Data and Daytime Satellite Data. Proceedings 32nd European Conference on Modelling and Simulation(ECMS), 2018, 10(7).

[30] 张妍. 山地丘陵地区农村“空心化”水平时空演变及分异机制研究[D]．四川师范大学, 2019.

[31] 刘巍. 农村人口空心化现状及影响因素分析[D]．南京师范大学, 2011.

[32] 苏碧芳. 统筹城乡户籍制度改革与农村人口空心化: 挑战与应对[J]. 安徽农业科学, 2011, 39(36): 22725－22726＋22747.

[33] 张昭. 关于河北省空心村治理的理论探讨[J]. 河北师范大学学报, 1998, (36): 144－147.

[34] 程连生, 冯文勇, 蒋立宏. 太原盆地东南部农村聚落空心化机理分析[J]. 地理学报，2001(04): 437－446.

[35] 刘彦随, 刘玉, 崔荣新, 中国农村空心化的地理学研究与整治实践[J]. 地理学报, 2009, 64(10): 1193－1202

[36] 王进业, 张军. “空心村”综合症[J]. 乡镇经济, 2003(07): 17.

[37] 曾学龙. 贫困地区“空心村”现象的出路与新农村建设探讨[J]. 甘肃农业, 2006（10）: 31.

[38] 陈明星. 新农村建设要谨防“空心化”倾向[J]. 农家顾问，2007(09)：1－2.

[39] 陈坤秋, 王良健, 李宁慧．中国县域农村人口空心化一内涵、格局与机理[J]. 人口与经济, 2018, (01): 28－37．

[40] 薛力. 城市化背景下的“空心村”现象及其对策探讨——以江苏省为例[J]. 城市规划，2001（06）: 8－13．

[41] 王成新, 姚士谋, 陈彩虹. 中国农村聚落空心化问题实证研究[J]. 地理科学, 2005（03）: 3257－3262.

[42] 龙花楼, 李裕瑞, 刘彦随. 中国空心化村庄演化特征及其动力机制[J]. 地理学报, 2009，64(10): 1203-1213.

[43] 宋金平, 谭勇剑, 李利锋. 中国农村社区演化的型式及动力机制[J]. 人文地理, 1999(03): 41－45

[44] 邹新树. 农民工向城市流动的动因: “推一理论的现实解读[J]. 农村经济, 2005(10): 104－109.

[45] 张茜, 张俊. 农村“空心化”现象的经济学解释[J]. 生产力研究, 2008(08): 34－35.

[46] 杨永芳, 刘玉振, 艾少伟. “空心村”问题成因分析及解决对策[J]. 安徽农业科学, 2007(26): 8333-8336.

[47] 王庆民. 城乡统筹背景下农村“空心化”治理研究—基于重庆市涪陵区现状调查[J]. 农家参谋, 2017(15): 28－30.

[48] 李坚诚, 胡巍巍, 郑銮娟, 等. 广东省饶平县“空心村”整治研究[J]. 南方农村, 2014, 30(03): 45－49.

[49] 崔卫国, 李裕瑞, 刘彦随. 中国重点农区农村空心化的特征、机制与调控—以河南省郸城县为例[J]. 资源科学, 2011, 33(11): 2014－2021.

[50] 李河辉. 浅析农村空心化及空心村治理[D]. 云南师范大学, 2014. 

[51] 田光进. 基于GIS的中国农村居民点用地分析[J]. 遥感信息, 2003(02): 32－35.

[52] 张小华. 农村“空心化”及其对农业生产发展的影响[D]. 华中师范大学, 2011.

[53] 王伟勤. 西部地区农村空心化风险及其治理探析[J]. 西北大学学报（哲学社会科学版）, 2014, 44（05）: 69－75.

[54] 李令文. 村级治理视角下的中国农村空心化问题研究[D]. 云南大学, 2009.

[55] 胡智超, 彭建, 杜悦悦, 等. 基于供给侧结构性改革的空心村综合整治研究[J]. 地理学报, 2016, 71（12）: 2119－2128.

[56] 李长印. 河南省“空心村”治理的模式、经验及启示[J]. 农业部管理干部学院学报, 2013（03）: 52－55.

[57] 杨亚军. 空心村扶贫问题研究[J]. 农家参谋, 2018（13）: 10.

[58] 何振嘉, 张永锋. 渭北台塬丘陵区空心村整治工程实践—以澄城县浴子河村为例[J]. 农业与技术, 2019, 39(18): 169－171.

[59] 曹雁翎. 国内外流动人口半城市化问题研究综述[J]. 北方经贸, 2016(08): 18－19.

[60] 陈池波, 韩占兵. 农村空心化、农民荒与职业农民培育[J]. 中国地质大学学报（社会科学版）, 2013, 13(01): 74－80＋139.

[61] 陈纪波, 王桂芝, 陆金帅, 李洁. 基于SEM模型的流动人口迀移意愿研究[J]. 统计与信息论坛, 2013, 28(10): 90－94.

[62] 陈坤秋, 王良健, 李宁慧. 中国县域农村人口空心化—内涵、格局与机理[J]. 人口与经济, 2018(01): 28－37.

[63] 陈涛, 陈池波. 人口外流背景下县域城镇化与农村人口空心化耦合评价研究[J]. 农业经济问题, 2017, 38(04): 58－66＋111.

[64] 陈涛, 陈池波. 中国农村人口空心化测量指标改进研宄[J]. 中国地质大学学报（社会科学版）, 2017, 17(01): 149－155.

[65] 程连生, 冯文勇, 蒋立宏. 太原盆地东南部农村聚落空心化机理分析[J]. 地理学报, 2001(04): 437－446.

[66] 崔冰. 习近平对马克思主义生态文明观的继承和发展[J]. 学理论, 2018(06): 5－6＋15.

[67] 丁延庆, 王绍达, 叶晓阳. 为什么有些地方政府撤并了更多农村学校？[J]. 教育经济评论, 2016, 1(04): 3－34.

[68] 房秀兰, 何瑞文. 农村的空心化与发展成果的公平惠及[J]. 法制与社会, 2013(04): 211－212.

[69] 费景汉, C. 拉尼斯. 劳动力剩余与经济的发展[M]. 北京: 华夏出版社, 1989.

[70] 冯文勇. 农村聚落空心化问题探讨——以太原盆地东南部为例[J]. 农业现代化研究, 2002(04): 267－269.

[71] 付霏. 人口老龄化对经济增长的影响研究[D]. 山东大学, 2018.

[72] 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.

[73] 姜明亮. 中部六省省会城市商品住宅价格差异及影响因素研究[D]. 山西财经大学, 2021.

[74] 李佳璟. 我国中部六省区域协调发展动态综合评价[D]. 吉林财经大学, 2021.

[75] 康振英. 中部六省城市空气质量时空特征及影响因素分析[D]. 中南财经政法大学, 2020.

[76] 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-Sensors Calib ration Earth System Science Data, 2021, 13(3), 899-906.

[77] Guo B, Wang X, Zhang D, Pei L, et al. A land use regression application into simulating spatial distribution characteristics of particulate matter (PM2.5) concentration in city of Xi’an, China. Pol. J. Environ. Stud, 2020b, 29, 4065–4076.

[78] Sun X. Green city and regional environmental economic evaluation based on entropy method and GIS[J]. Environmental Technology & Innovation, 2021, 101667-.

[79] Xue J, et al. Water abundance evaluation of a burnt rock aquifer using the AHP and entropy weight method: a case study in the Yongxin coal mine, China. Environmental Earth Sciences, 2021, 80(11), 1-12.

[80] Hong Y, Shen R, Cheng H, et al. Estimating lead and zinc concentrations in peri-urban agricultural soils through reflflectance spectroscopy: effects of fractional-order derivative and random forest. Sci. Total Environ, 2019, 651, 1969–1982.

[81] Wei J, Huang W, Li Z, Xue W, Peng Y, et al. Estimating 1-kmresolution PM2.5 concentrations across China using the space-time random forest approach. Remote Sens. Environ, 2019, 231, 111221.

[82] Lan Z, Chun Y. Beautiful Village Planning and Construction:A Practice of Human Settlement Improvement in Jiangsu Province[J]. China City Planning Review, 2014, 23(01): 40-50.

[83] He Q, Huang B. Satellite-based mapping of daily high-resolution ground PM2.5 in China via space-time regression modeling. Remote Sens. Environ, 2018, 206, 72–83.

[84] Steininger M, Defries R, Belward A. Satellite estimation of tropical secondary forest above-ground biomass: data from Brazil and Bolivia. Int. J. Remote Sens, 2000, 21(6-7), 1139-1157.

[85] Yin D, Gui J, et al. Multidimensional measurement of poverty and its spatio-temporal dynamics in China from the perspective of development geography. Journal of Geographical Sciences, 2021, 31(01): 130-148.

[86] Guo B, Wang Y, et al. Determining the effects of socioeconomic and environmental determinants on chronic obstructive pulmonary disease (COPD) mortality using geographically and temporally weighted regression model across Xi'an during 2014–2016[J]. Science of the Total Environment, 2021c, 756.

[87] Song W, Jia H, Huang J, Zhang Y. A satellite-based geographically weighted regression model for regional PM2.5 estimation over the Pearl River Delta region in China. Remote Sens. Environ, 2014, 154, 1–7.

[88] Pei L, Wang X, Guo B, Guo H, Yu Y. Do air pollutants as well as meteorological factors impact Corona Virus Disease 2019 (COVID-19)? Evidence from China based on the geographical perspective. Environ Sci Pollut R, 2021, 28, 35584-96.

[89] Breiman L. Random Forests. Mach. Learn, 2001, 45(1), 5-32.

[90] Zheng D, Rademacher J, et al. Estimating aboveground biomass using Landsat 7 ETM+ data across a managed landscape in northern Wisconsin, USA. Remote Sens. Environ, 2004, 93(3), 402-411.

[91] Ham J, Chen Y, et al. Investigation of the random forest framework for classification of hyperspectral data. IEEE Trans. Geosci. Remote Sens, 2005, 43(3), 492-501.

[92] Wei J, et al. Improved 1 km resolution PM. estimates across China using enhanced space-time extremely randomized trees. Atmos. Chem. Phys, 2020, 20, 3273-3289.

[93] Xu Z. Influencing Factors and Urbanization Effects of the Spatial Pattern of Floating Population in Anhui Province[J]. Journal of Landscape Research, 2019, 11(05).

[94] Dotto A, Dalmolin R, et al. A systematic study on the application of scatter-corrective and spectral-derivative preprocessing for multivariate prediction of soil organic carbon by Vis-NIR spectra. GEODERMA, 2018, 314, 262–274.

[95] Guo B, Wang X, Pei L, et al. Wang, Y. Identifying the spatiotemporal dynamic of PM2.5 concentrations at multiple scales using geographically and temporally weighted regression model across China during 2015–2018. Sci. Total Environ, 2021d, 751, 141765.

[96] Guo B, Su Y, Pei L, Wang X, Zhang B, Zhang D, et al. Ecological risk evaluation and source apportionment of heavy metals in park playgrounds: a case study in Xi’an, Shaanxi Province, a northwest city of China. Environ Sci Pollut R, 2020c, 27, 24400-12.

[97] Guo B, Su Y, Pei L, Wang X, Wei X, Zhang B, et al. Contamination, Distribution and Health Risk Assessment of Risk Elements in Topsoil for Amusement Parks in Xi’an, China. Pol J Environ Stud, 2021e, 30, 601-17.

[98] Liang X, Tang X, Luo Y, et al. Effects of policies and containment measures on control of COVID-19 epidemic in Chongqing. World Journal of Clinical Cases, 2020b, 8(14): 2959-2976.

[99] Guo B, Wang X, Pei L, Su Y, Zhang D, Wang Y. Identifying the spatiotemporal dynamic of PM2.5 concentrations at multiple scales using geographically and temporally weighted regression model across China during 2015–2018[J]. Science of the Total Environment, 2021, 751.

[100] Kenu E, Ganu V, Calys-Tagoe B N, et al. Application of geographical information system (GIS) technology in the control of Buruliulcer in Ghana. BMC Public Health, 2014, 14, 724.

[101] Wang J F, Li X H, Christakos G, Liao Y L, Zhang T, Gu X, Zheng X Y. Geographical detectors-based health risk assessment and its application in the neural tube defects study of the Heshun Region, China. Int J Geogr Inf Sci, 2010, 24(1): 107–127.

[102] Gao J, Jiang Y, Anker Y. Contribution analysis on spatial tradeoff/synergy of Karst soil conservation and water retention for various geomorphological types: Geographical detector application[J]. Ecological Indicators, 2021, 125.

[103] Wang J F, Hu Y. Environmental health risk detection with GeogDetector. Environ Model Softw, 2012, 33: 114–115.

[104] Leng G, Feng X, Qiu H. Income effects of poverty alleviation relocation program on rural farmers in China[J]. Journal of Integrative Agriculture, 2021, 20(4):

[105] 李玥. 保定市农村空心化现状分析及发展对策探究[D]. 河北农业大学, 2018.

[106] 宋宁. 城镇化背景下农村“空心化”问题研究[J]. 农村经济与科技,2021,32(11): 229-231.

[107] 李枝秀. 传统村落“空心化”的原因分析与治理策略[J]. 老区建设, 2015(08): 34-36.

[108] 高汝熹, 李志能, 陈建明, 郁义鸿. 东京都心三区人口状况及对上海的启示[J].社会科学, 1997(03): 48-52.

[109] 郑殿元, 文琦, 王银, 米欢. 中国村域人口空心化分异机制及重构策略[J]. 经济地理, 2019, 39(02): 161-168+189.

[110] 王良健, 陈坤秋, 李宁慧. 中国县域农村人口空心化程度的测度及时空分异特征[J]. 人口学刊, 2017, 39(05): 14-24.

[111] 胡一鸣, 伍旭中. 安徽省县域农村人口空心化空间分异及影响因素研究[J].云南农业大学学报(社会科学), 2020, 14(06): 25-31.

[112] 曹广忠, 陈思创, 刘涛. 中国五大城市群人口流入的空间模式及变动趋势[J]. 地理学报, 2021, 76(06): 1334-1349.

[113] Wu Q, Chen J. The Effect and Influence of Tourism Poverty Alleviation of Residents in Poor Areas:A Case Study of Key Tourism Poverty Alleviation Villages in Northern Guangdong[J].Journal of Landscape Research, 2021, 13(02): 89-94.

[114] Rodríguez-Puerta F, et al. Comparison of Machine Learning Algorithms for Wildland-Urban Interface Fuelbreak Planning Integrating ALS and UAV-Borne LiDAR Data and Multispectral Images. Drones, 2020, 4(2).

[115] Ganggayah M, Taib N, Har Y, Lio P, et al. Predicting factors for survival of breast cancer patients using machine learning techniques. BioMed Central, 2019, 19(1).

[116] Qi W, Yi J. Spatial pattern and driving factors of migrants on the Qinghai-Tibet Plateau: Insights from short-distance and long-distance population migrants[J].Journal of Geographical Sciences, 2021, 31(02):215-230.

[117] En W, Xue B, Yang J, Lu C. Effects of the Northeast China Revitalization Strategy on Regional Economic Growth and Social Development[J].Chinese Geographical Science, 2020, 30(05):791-809.

[118] Ye Y, Wang C, Zhang H, Yang J, Liu Z, Wu K, Deng Y. Spatiotemporal analysis of COVID-19 risk in Guangdong Province based on population migration[J].Journal of Geographical Sciences, 2020, 30(12): 1985-2001.

[119] Liang X, Tang X, Luo Y, Zhang M, et al. Effects of policies and containment measures on control of COVID-19 epidemic in Chongqing. World Journal of Clinical Cases, 2020b, 8(14): 2959-2976.

[120] Yin Y, Zhang Y. Environmental Pollution Evaluation of Urban Rail Transit Construction Based on Entropy Weight Method. Nature Environment and Pollution Technology, 2021, 20(2), 819-824.

[121] 肖琴. 乡村振兴战略背景下城郊村“空心化”治理研究[D]. 南昌大学, 2019.

[122] 喻磊. 小城镇周边空心村的治理研宄[D]. 安徽大学, 2013.

[123] Wang X, et al. Comparison of sampling schemes for spatial prediction of soil organic carbon in Northern China. Sciences in Cold and Arid Regions, 2020b, 12(04): 200-216.

[124] Xu P, Lin M, Jin P. Spatio-temporal Dynamics of Urbanization in China Using DMSP/OLS Nighttime Light Data from 1992–2013[J]. Chinese Geographical Science, 2021, 31(01): 70-80.

[125] Zhao F, Ding J, Zhang S, Luan G, Song L, et al. Estimating Rural Electric Power Consumption Using NPP-VIIRS Night-Time Light, Toponym and POI Data in Ethnic Minority Areas of China[J]. Remote Sensing, 2020, 12(17), 2836-2836.

[126] Shi K, Yu B, Huang C, Wu J, et al. Exploring spatiotemporal patterns of electric power consumption in countries along the Belt and Road. Energy, 2018, 150, 847-859.

[127] Gu B, Fan L, Ying Z, Xu Q, Luo W, Ge Y, et al. Socioeconomic constraints on the technological choices in rural sewage treatment[J]. Environmental Science and Pollution Research, 2016, 23 (20):

[128] Guo B, Wang Y, Pei L, Yu Y, Liu F, Zhang D, Wang X, Su Y, Zhang D, Zhang B, Guo H. Determining the effects of socioeconomic and environmental determinants on chronic obstructive pulmonary disease (COPD) mortality using geographically and temporally weighted regression model across Xi'an during 2014–2016[J]. Science of the Total Environment, 2021, 756.