基于随机森林模型的西藏人口分布格局及影响因素

doi:10.11821/dlxb201904004

地理学报 ›› 2019, Vol. 74 ›› Issue (4): 664-680.doi: 10.11821/dlxb201904004

基于随机森林模型的西藏人口分布格局及影响因素

王超¹(), 阚瑷珂²(), 曾业隆³, 李国庆⁴, 王民¹, 次仁⁵

1. 北京师范大学地理科学学部,北京 100875
2. 成都理工大学地球物理学院,成都 610059
3. 中国科学院遥感与数字地球研究所,北京 100101
4. 鲁东大学资源与环境工程学院,烟台 264025
5. 西藏自治区科技信息研究所,拉萨 850000

收稿日期:2017-08-31 修回日期:2019-03-11 出版日期:2019-04-25 发布日期:2019-04-23
作者简介:
作者简介：王超(1992-), 女, 山西晋城人, 硕士生, 研究方向为区域可持续发展。E-mail: lrningxiang@163.com
基金资助:
西藏自治区自然科学基金项目(XZ2017ZRG-100, 2015ZR-13-56);国家科技支撑计划(2014BAL07B02-2);中国清洁发展机制基金赠款项目(2014058)

Population distribution pattern and influencing factors in Tibet based on random forest model

Chao WANG¹(), Aike KAN²(), Yelong ZENG³, Guoqing LI⁴, Min WANG¹, Ren CI⁵

1. School of Geography, Faculty of Geographical Science, Beijing Normal University, Beijing 100875, China
2. College of Geophysics, Chengdu University of Technology, Chengdu 610059, China
3. Institute of Remote Sensing and Digital Earth, CAS, Beijing 100101, China
4. School of Resources and Environmental Engineering, Ludong University, Yantai 264025, Shandong, China
5. Institute of Science & Technology Information of Tibet Autonomous Region, Lhasa 85000, China;

Received:2017-08-31 Revised:2019-03-11 Published:2019-04-25 Online:2019-04-23
Supported by:
Natural Science Foundation of Tibet Autonomous Region, No.XZ2017ZRG-100, No.2015ZR-13-56;The National Key Technology R&D Program of China, No.2014BAL07B02-2;Grants Program of China Clean Development Mechanism Fund, No.2014058

摘要/Abstract

摘要：

在乡镇尺度下厘清人口分布格局及其影响因素与区域差异,对在生态脆弱区制定可持续发展政策具有重大指导意义。基于2010年西藏自治区的乡镇尺度人口普查数据,提取人口密度和空间因子,利用空间统计方法分析了人口分布的疏密特征和集聚特征,对比运用多元线性回归方法和随机森林回归方法探索该地区人口分布的影响因素及其区域差异。结果表明：① 西藏乡镇人口密度在空间上表现出极强的非均衡性,其总体趋势是东南高西北低,高密度区与大江大河及主要交通干线具有较强的空间耦合性;② 大致以波绒乡（聂拉木县）—岗尼乡（安多县）为西藏的人口分界线,人口集聚的“核心—边缘”特征明显;③ 多元线性回归方法中,人造地表指数对人口分布的影响程度最大,随后依次为夜间灯光指数和路网密度;④ 利用随机森林方法进行的人口密度预测比多元线性回归方法精度高,可以用来对影响因子的重要性进行排序;排序在前六位的影响因子由高到低依次为夜间灯光指数、人造地表指数、路网密度、工业总产值、GDP和多年平均气温,它们与人口密度均呈正相关关系;地形地貌要素中以海拔和坡度的贡献率最大且与人口密度均呈负相关关系;⑤ 西藏人口分布格局的影响因素及其相互作用呈现出明显的区域差异特征,河谷是西藏地区人口的集聚区,主要分布在拉萨河谷、年楚河谷以及三江河谷;⑥ 通过随机森林回归分析,可以利用概念模型来表达人口分布影响因素,将主导因素概括为土地利用结构、道路通达度及城镇化水平。

关键词: 人口分布, 影响因素, 乡镇尺度, 随机森林, 概念模型

Abstract:

Clarifying the spatial pattern of population distribution, its influencing factors and regional differences at the township level is of great guiding significance for formulating sustainable development policies in ecologically fragile areas. Based on the population census data of Tibet at the township level in 2010, the population density and spatial factors were extracted. The density and clustering characteristics of the population distribution were analyzed by spatial statistical method. The multiple linear regression method and the random forest regression method were used to explore the population influencing factors and their regional differences of population distribution. The results showed that: (1) The population density of Tibet at the township level showed a strong spatial non-equilibrium. The general trend was high in the southeast and low in the northwest, and there was a strong spatial coupling between the main rivers and the main traffic trunks in high density area. (2) The "core-edge" characteristic of population clustering was obvious, and roughly to the wave of Borong (Nyalam County)-Gangni (Anduo County) as the demarcation line. (3) In the multiple linear regression method, the artificial surface index had the greatest influence on the population distribution, followed by the nighttime light index and road network density. (4) Random forest method was more accurate than multiple linear regression method to predict the population density, which can be used to sort the importance of the influencing factors. The influencing factors of the first six factors were the night light index, artificial surface index, road network density, industrial output value, GDP and multi-year average temperature, and these factors were positively correlated with population density. Among topographic factors, the contribution rate of elevation and slope was the largest, which was negatively correlated with population density. (5) The influencing factors and their interactions of population distribution in Tibet showed obvious regional differences. The valley was a gathering area for population in the study region, mainly in Lhasa River Valley, Nianchu River Valley and Sanjiang River Valley. (6) Through the analysis of random forest regression, the conceptual model can be used to express the influencing factors of population distribution, and the dominant factors were summarized as land use structure, road accessibility and urbanization level.

Key words: population distribution, influencing factor, township scale, random forest, conceptual model

王超, 阚瑷珂, 曾业隆, 李国庆, 王民, 次仁. 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.

Chao WANG, Aike KAN, Yelong ZENG, Guoqing LI, Min WANG, Ren CI. Population distribution pattern and influencing factors in Tibet based on random forest model[J]. Acta Geographica Sinica, 2019, 74(4): 664-680.

图/表 10

表1

影响人口分布的因素

影响因素	影响因子	描述
地形地貌(A)	海拔(A₁)	地形地貌是影响人口分布的最基本因素之一：随着海拔高度的增加,地形起伏度呈现逐渐升高趋势,人口也随之减少^[20];在中国人口大多居住在坡度小于15°的地区^[19];而坡向是构成地形地貌因素的重要定量指标,通过调节各自然要素的分配影响人口分布,已有研究将其作为乡镇尺度人口分布的影响因子^[28]。
	坡度(A₂)
	坡向(A₃)
	地形起伏度(A₄)
气候(B)	多年平均降雨量(B₁)	人类对不同水热条件影响下的资源和环境条件具有选择偏好,在较广的范围内,人口密度与气温、降水量呈显著的正相关关系^[29]。
气候(B)	多年平均气温(B₂)
植被覆盖(C)	NDVI(C)	以NDVI为代表的植被指数能反映植被覆盖情况,一方面显示了人类生产生活所依赖的植被资源分布,另一方面则展示了不适宜居住区的空间分布(如沙漠和密林)^[30]。
土地利用(D)	土地利用指数(D_n)	根据“无土地则无人口”原则,人口分布受特定的土地利用类型影响,且土地利用面积与人口分布具有强相关性^[22]。
河流(E)	河网密度(E₁)	河流一方面为人们提供充足而稳定的水源,另一方面造就沿岸地势低平、土壤肥沃的格局,为人们居住生活、基础设施建设和发展生产提供适宜的空间^[20]。
河流(E)	距河流距离(E₂)
道路(F)	路网密度(F₁)	基于交通条件的区域可达性与人口分布关系密切,该因素对欠发达地区人口集聚所起的作用远大于发达地区^[15]。
道路(F)	距道路距离(F₂)	基于交通条件的区域可达性与人口分布关系密切,该因素对欠发达地区人口集聚所起的作用远大于发达地区^[15]。
经济发展(G)	夜间灯光指数(G₁)	夜间灯光亮度是城镇化的一个解释性指标,能反映城镇化水平,根据灯光影像的亮度值和人口距离衰减定律可以估算人口总数和人口分布^[31,32];也可以在一定程度上反映GDP,但两者的定量关系仍存在较大不确定性,并且夜间灯光指数反映的是消费而非生产^[33],不能完全替代经济统计数据;另外它还能反映区域的总体能源消耗量^[34,35]。一般来说,区域人口分布与经济发展之间具有较强的一致性,产业结构的差异也会影响人口分布^[36,37]。
	GDP(G₂)
	工业总产值(G₃)
	农林牧渔业产值(G₄)

表1

图1

表2

图2

表3

图3

图4

图5

表4

图6

参考文献 60

[1]	Jiang Dong, Yang Xiaohuan, Wang Naibin, et al.Study on spatial distribution of population based on remote sensing and GIS. Advances in Earth Science, 2002, 17(5): 734-738. doi: 10.3321/j.issn:1001-8166.2002.05.016
	[江东, 杨小唤, 王乃斌, 等. 基于RS、GIS 的人口空间分布研究. 地球科学进展, 2002,17(5): 734-738.] doi: 10.3321/j.issn:1001-8166.2002.05.016
[2]	Ferretti V, Pomarico S.Ecological land suitability analysis through spatial indicators: An application of the Analytic Network Process technique and Ordered Weighted Average approach. Ecological Indicators, 2013, 34: 507-519. doi: 10.1016/j.ecolind.2013.06.005
[3]	Kleidon A.Climatic constraints on maximum levels of human metabolic activity and their relation to human evolution and global change. Climatic Change, 2009, 95(3/4): 405-431. doi: 10.1007/s10584-008-9537-3
[4]	Yang Jun, Guan Xin, Li Xiangyun, et al.Study on the relations between the LUCC and demographic factors in the past 10 years of Tarim River Basin. Journal of Arid Land Resources and Environment, 2006, 2(2): 114-117. doi: 10.3969/j.issn.1003-7578.2006.02.022
	[杨君, 关欣, 李香云, 等. 近10年塔里木河流域土地利用/土地覆被变化与人口因素关系研究. 干旱区资源与环境, 2006, 2(2): 114-117.] doi: 10.3969/j.issn.1003-7578.2006.02.022
[5]	Feng Zhiming, Yang Yanzhao, You Zhen, et al.Research on the suitability of population distribution at the county level in China. Acta Geographica Sinica, 2014, 59(6): 723-737. doi: 10.11821/dlxb201406001
	[封志明, 杨艳昭, 游珍, 等. 基于分县尺度的中国人口分布适宜度研究. 地理学报, 2014, 59(6): 723-737.] doi: 10.11821/dlxb201406001
[6]	Li Jiaming, Lu Dadao, Xu Chengdong, et al.Spatial heterogeneity and its changes of population on the two sides of Hu Line. Acta Geographica Sinica, 2017, 72(1): 148-160. doi: 10.11821/dlxb201701012
	[李佳洺, 陆大道, 徐成东, 等. 胡焕庸线两侧人口的空间分异性及其变化. 地理学报, 2017, 72(1): 148-160.] doi: 10.11821/dlxb201701012
[7]	Mo Shenguo, Zhang Baiping, Cheng Weiming, et al.Major environmental effects of the Tibetan Plateau. Progress in Geography, 2004, 23(2): 88-96. doi: 10.11820/dlkxjz.2004.02.011
	[莫申国, 张百平, 程维明, 等. 青藏高原的主要环境效应. 地理科学进展, 2004, 23(2): 88-96.] doi: 10.11820/dlkxjz.2004.02.011
[8]	Cai Yunlong, Song Changqing, Leng Shuying.Future development trends and priority areas of physieal geography in China. Scientia Geographica Sinica, 2009, 29(5): 619-626
	[蔡运龙, 宋长青, 冷疏影. 中国自然地理学的发展趋势与优先领域. 地理科学, 2009, 29(5): 619-626.]
[9]	Luo Lifang, Zhang Keli, Kong Yaping, et al.Temporal and spatial distribution of soil loss on Tibet-Qing Plateau. Journal of Soil and Water Conservation, 2004, 18(1): 58-62.
	[罗利芳, 张科利, 孔亚平, 等. 青藏高原地区水土流失时空分异特征. 水土保持学报, 2004, 18(1): 58-62.]
[10]	Niu Yafei.The study of environment in the Plateau of Qing-Tibet. Progress in Geography, 1999, 18(2): 69-77. doi: 10.3969/j.issn.1007-6301.1999.02.010
	[牛亚菲. 青藏高原生态环境问题研究. 地理科学进展, 1999, 18(2): 69-77.] doi: 10.3969/j.issn.1007-6301.1999.02.010
[11]	Sun Honglie, Zheng Du, Yao Tandong, et al.Protection and construction of the national ecological security shelter zone on Tibetan Plateau. Acta Geographica Sinica, 2012, 67(1): 3-12. doi: 10.11821/xb201201001
	[孙鸿烈, 郑度, 姚檀栋, 等. 青藏高原国家生态安全屏障保护与建设. 地理学报, 2012, 67(1): 3-12.] doi: 10.11821/xb201201001
[12]	Gao Zhiqiang, Liu Jiyuan, Zhuang Dafang.The relations analysis between ecological environmental quality of Chinese land resources and population. Journal of Remote Sensing, 1999, 3(1): 67-71. doi: 10.3321/j.issn:1007-4619.1999.01.011
	[高志强, 刘纪远, 庄大方. 基于遥感和GIS的中国土地资源生态环境质量同人口分布的关系研究. 遥感学报, 1999, 3(1): 67-71.] doi: 10.3321/j.issn:1007-4619.1999.01.011
[13]	Liao Shunbao, Sun Jiulin.Quantitative analysis of relationship between population distribution and environmental factors in Qinghai-Tibet Plateau. China Population, Resources and Environment, 2003, 13(3): 65-70. doi: 10.3969/j.issn.1002-2104.2003.03.014
	[廖顺宝, 孙九林. 青藏高原人口分布与环境关系的定量研究. 中国人口·资源与环境, 2003, 13(3): 65-70.] doi: 10.3969/j.issn.1002-2104.2003.03.014
[14]	Qin Xiaojing.The spatial-temporal patterns and coupling relationship of animals husbandry and rural laborers across Tibet [D]. Nanchong: China West Normal University, 2016.
	[秦小静. 西藏自治区畜牧业与乡村人口的时空格局及耦合关系[D]. 南充: 西华师范大学, 2016.]
[15]	Wang Zhenbo, Xu Jiangang, Zhu Chuangeng, et al.The county accessibility divisions in China and its correlation with population distribution. Acta Geographica Sinica, 2010, 65(4): 416-426. doi: 10.11821/xb201004004
	[王振波, 徐建刚, 朱传耿, 等. 中国县域可达性区域划分及其与人口分布的关系. 地理学报, 2010, 65(4): 416-426.] doi: 10.11821/xb201004004
[16]	Liao Shunbao, Li Zehui.Study on spatialization of population census data based on relationship between population distribution and land use: Taking Tibet as an example. Journal of Natural Resources, 2003, 18(6): 659-665. doi: 10.11849/zrzyxb.2003.06.003
	[廖顺宝, 李泽辉. 基于人口分布与土地利用关系的人口数据空间化研究: 以西藏自治区为例. 自然资源学报, 2003, 18(6): 659-665.] doi: 10.11849/zrzyxb.2003.06.003
[17]	Liao Shunbao, Sun Jiulin.GIS based spatialization of population census data in Qinghai-Tibet Plateau. Acta Geographica Sinica, 2003, 58(1): 25-33. doi: 10.3321/j.issn:0375-5444.2003.01.004
	[廖顺宝, 孙九林. 基于GIS的青藏高原人口统计数据空间化. 地理学报, 2003, 58(1): 25-33.] doi: 10.3321/j.issn:0375-5444.2003.01.004
[18]	Luo Yong.Study on distribution of population and the sustainable development of ecological environment in Tibet [D]. Chengdu: Chengdu University of Technology, 2010.
	[罗永. 西藏人口分布与生态环境可持续发展研究[D]. 成都: 成都理工大学, 2010.]
[19]	Feng Zhiming, Tang Yan, Yang Yanzhao, et al.The relief degree of land surface in China and its correlation with population distribution. Acta Geographica Sinica, 2007, 62(10): 1073-1082. doi: 10.3321/j.issn:0375-5444.2007.10.007
	[封志明, 唐焰, 杨艳昭, 等. 中国地形起伏度及其与人口分布的相关性. 地理学报, 2007, 62(10): 1073-1082.] doi: 10.3321/j.issn:0375-5444.2007.10.007
[20]	Zhao Tongtong, Song Bangguo, Chen Yuansheng, et al.Analysis of population distribution and its spatial relationship with terrain elements in the Yarlung Zangbo River, Nyangqu River and Lhasa River Region, Tibet. Journal of Geo-Information Science, 2017, 19(2): 225-237. doi: 10.3724/SP.J.1047.2017.00225
	[赵彤彤, 宋邦国, 陈远生, 等. 西藏一江两河地区人口分布与地形要素关系分析. 地球信息科学学报, 2017, 19(2): 225-237.] doi: 10.3724/SP.J.1047.2017.00225
[21]	Bai Zhongqiang, Wang Juanle, Yang Yaping, et al.Characterizing spatial patterns of population distribution at township level across the 25 provinces in China. Acta Geographica Sinica, 2015, 70(8): 1229-1242. doi: 10.11821/dlxb201508004
	[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. 地理学报, 2015, 70(8): 1229-1242.] doi: 10.11821/dlxb201508004
[22]	Dong Nan, Yang Xiaohuan, Cai Hongyan.Research progress and perspective on the spatialization of population data. Journal of Geo-Information Science, 2016, 18(10): 1295-1304. doi: 10.3724/SP.J.1047.2016.01295
	[董南, 杨小唤, 蔡红艳. 人口数据空间化研究进展. 地球信息科学学报, 2016, 18(10): 1295-1304.] doi: 10.3724/SP.J.1047.2016.01295
[23]	Song Guobao, Li Zhenghai, Bao Yajing, et al.Spatial distribution pattern of population density in vertical ridge valley region and its influencing factors. Chinese Science Bulletin, 2007, 52(Suppl.2): 78-85.
	[宋国宝, 李政海, 鲍雅静, 等. 纵向岭谷区人口密度的空间分布规律及其影响因素. 科学通报, 2007, 52(Suppl.2): 78-85.]
[24]	Tang Jiayun.The research of population distribution pattern of space and time in Gansu province and its influencing factors [D]. Wuhan: Central China Normal University, 2015.
	[唐嘉韵. 甘肃省人口分布的时空格局及其影响因素研究[D]. 武汉: 华中师范大学, 2015.]
[25]	Zhang Lei, Wang Linlin, Zhang Xudong, et al.The basic principle of random forest and its applications in ecology: A case study of Pinus yunnanensis. Acta Ecologica Sinica, 2014, 34(3): 650-659. doi: 10.5846/stxb201306031292
	[张雷, 王琳琳, 张旭东, 等. 随机森林算法基本思想及其在生态学中的应用: 以云南松分布模拟为例. 生态学报, 2014, 34(3): 650-659.] doi: 10.5846/stxb201306031292
[26]	Yu Bohua, Lv Changhe.Assessment of ecological vulnerability on the Tibetan Plateau. Geographical Research, 2011, 30(12): 2289-2295. doi: 10.11821/yj2011120016
	[于伯华, 吕昌河. 青藏高原高寒区生态脆弱性评价. 地理研究, 2011, 30(12): 2289-2295.] doi: 10.11821/yj2011120016
[27]	Hu Huanyong.Distribution of China's Population. Shanghai: East China Normal University Press, 1983.
	[胡焕庸. 论中国人口之分布. 上海: 华东师范大学出版社, 1983.]
[28]	Wang Lei, Cai Yunlong.Spatial down-scaling analysis and simulation of population density in Maotiaohe Basin, Guizhou Province. Progress in Geography, 2011, 30(5): 635-640. doi: 10.11820/dlkxjz.2011.05.017
	[王磊, 蔡运龙. 人口密度的空间降尺度分析与模拟: 以贵州猫跳河流域为例. 地理科学进展, 2011, 30(5): 635-640.] doi: 10.11820/dlkxjz.2011.05.017
[29]	Fang Yu, Ouyang Zhiyun, Zheng Hua, et al.Natural forming causes of China population distribution. Chinese Journal of Applied Ecology, 2012, 23(12): 3488-3495.
	[方瑜, 欧阳志云, 郑华, 等. 中国人口分布的自然成因. 应用生态学报, 2012, 23(12): 3488-3495.]
[30]	Zhuo L, Ichinose T, Zheng J, et al.Modelling the population density of China at the pixel level based on DMSP/OLS non-radiance-calibrated night-time light images. International Journal of Remote Sensing, 2009, 30(4): 1003-1018. doi: 10.1080/01431160802430693
[31]	Sutton P, Roberts C, Elvidge C, et al.A comparison of nighttime satellite imagery and population density for the continental united states. Photogrammetric Engineering and Remote Sensing, 1997, 63(11): 1303-1313.
[32]	Ma T, Zhou C H, Pei T, et al.Quantitative estimation of urbanization dynamics using time series of DMSP/OLS nighttime light data: A comparative case study from China's cities. Remote Sensing of Environment, 2012, 124(9): 99-107. doi: 10.1016/j.rse.2012.04.018
[33]	Wu J S, Wang Z, Li W F, et al.Exploring factors affecting the relationship between light consumption and GDP based on DMSP/OLS nighttime satellite imagery. Remote Sensing of Environment, 2013, 134(7): 111-119. doi: 10.1016/j.rse.2013.03.001
[34]	Xie Y H, Weng Q H.World energy consumption pattern as revealed by DMSP-OLS nighttime light imagery. Giscience and Remote Sensing, 2016, 53(2): 265-282. doi: 10.1080/15481603.2015.1124488
[35]	He C Y, Ma Q, Li T, et al.Spatiotemporal dynamics of electric power consumption in Chinese Mainland from 1995 to 2008 modeled using DMSP/OLS stable nighttime lights data. Journal of Geographical Sciences, 2012, 22(1): 125-136. doi: 10.1007/s11442-012-0916-3
[36]	Jia Zhanhua, Gu Guofeng.Temporal-Spatial evolution characteristics and its influence factors about population distribution in Northeast China. Economic Geography, 2016, 36(12): 60-68. doi: 10.15957/j.cnki.jjdl.2016.12.009
	[贾占华, 谷国锋. 东北地区人口分布的时空演变特征及影响因素. 经济地理, 2016, 36(12): 60-68.] doi: 10.15957/j.cnki.jjdl.2016.12.009
[37]	Feng Zhiming, Liu Xiaona.Multi-scale studies on the space consistency between population distribution and economic development in China. Population and Economics, 2013(2): 3-11. doi: 10.3969/j.issn.1000-4149.2013.02.001
	[封志明, 刘晓娜. 中国人口分布与经济发展空间一致性研究. 人口与经济, 2013(2): 3-11.] doi: 10.3969/j.issn.1000-4149.2013.02.001
[38]	Wang Junbang, Ye Hui, Wang Juwu, et al.1 km spatial resolution of temperature and precipitation in China in 2000-2012 raster data set. Science Data Bank, 2016.
	[王军邦, 叶辉, 王居午, 等. 2000-2012年全国气温和降水1 km网格空间插值数据集 . Science Data Bank, 2016.]
[39]	Nestola E, Calfapietra C, Emmerton C A, et al.Monitoring grassland seasonal carbon dynamics, by integrating MODIS NDVI, proximal optical sampling, and eddy covariance measurements. Remote Sensing, 2016, 8(3): 260-285. doi: 10.3390/rs8030260
[40]	Li Z, Huffman T, Mcconkey B, et al.Monitoring and modeling spatial and temporal patterns of grassland dynamics using time-series MODIS NDVI with climate and stocking data. Remote Sensing of Environment, 2013, 138(11): 232-244. doi: 10.1016/j.rse.2013.07.020
[41]	Jun C, Ban Y F, Li S N.Open access to Earth land-cover map. Nature, 2014, 514(7523): 434-434. doi: 10.1038/514434c pmid: 25341776
[42]	Brovelli M A, Molinari M E, Hussein E, et al.The first comprehensive accuracy assessment of GlobeLand30 at a national level: Methodology and results. Remote Sensing, 2015, 7(4): 4191-4212. doi: 10.3390/rs70404191
[43]	Chen J, Chen J, Liao A P, et al.Global land cover mapping at 30 m resolution: A POK-based operational approach. Isprs Journal of Photogrammetry and Remote Sensing, 2015, 103: 7-27. doi: 10.1016/j.isprsjprs.2014.09.002
[44]	Kuang W H, Chen L J, Liu J Y, et al.Remote sensing-based artificial surface cover classification in Asia and spatial pattern analysis. Science China-Earth Sciences, 2016, 59(9): 1720-1737. doi: 10.1007/s11430-016-5295-7
[45]	Lu Nan, Zhang Weiwei, Chen Lijun, et al.Estimation of large regional urban and rural population density based on the differences of population distribution between urban and rural: Take Shandong Province as example. Geodaetica et Cartographica Sinica, 2015, 44(12): 1384-1391. doi: 10.11947/j.AGCS.2015.20150005
	[鲁楠, 张委伟, 陈利军, 等. 顾及城乡差异的大区域人口密度估算: 以山东省为例. 测绘学报, 2015,44(12): 1384-1391.] doi: 10.11947/j.AGCS.2015.20150005
[46]	Xie H, Du L, Liu S C, et al.Dynamic monitoring of agricultural fires in China from 2010 to 2014 using MODIS and GlobeLand30 data. ISPRS International Journal of Geo-Information, 2016, 5(10): 172. doi: 10.3390/ijgi5100172
[47]	Chen Peiyang, Zhu Xigang.Regional inequalities in China at different scales. Acta Geographica Sinica, 2012, 67(8): 1085-1097. doi: 10.11821/xb201208007
	[陈培阳, 朱喜钢. 基于不同尺度的中国区域经济差异. 地理学报, 2012, 67(8): 1085-1097.] doi: 10.11821/xb201208007
[48]	Ma Xiaodong, Ma Ronghua, Xu Jiangang.Spatial structure of cities and towns with ESDA-GIS framework. Acta Geographica Sinica, 2004, 59(6): 1048-1057. doi: 10.3321/j.issn:0375-5444.2004.06.029
	[马晓冬, 马荣华, 徐建刚. 基于ESDA-GIS的城镇群体空间结构. 地理学报, 2004, 59(6): 1048-1057.] doi: 10.3321/j.issn:0375-5444.2004.06.029
[49]	Cheng Weiming, Zhou Chenghu, Chai Huixia, et al.Quantitative extraction and analysis of basic morphological types of land morphology in China. Journal of Geo-information Science, 2009, 11(6): 725-736. doi: 10.3969/j.issn.1560-8999.2009.06.007
	[程维明, 周成虎, 柴慧霞, 等. 中国陆地地貌基本形态类型定量提取与分析. 地球信息科学学报, 2009, 11(6): 725-736.] doi: 10.3969/j.issn.1560-8999.2009.06.007
[50]	Wang Kejing, Cai Hongyan, Yang Xiaohuan.Multiple scale spatialization of demographic data with multi-factor linear regression and geographically weighted regression models. Progress in Geography, 2016, 35(12): 1494-1505. doi: 10.18306/dlkxjz.2016.12.006
	[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. 地理科学进展, 2016, 35(12): 1494-1505.] doi: 10.18306/dlkxjz.2016.12.006
[51]	Tian Yongzhong, Chen Shupeng, Yue Tianxiang, et al.Simulation of Chinese population density based on land use. Acta Geographica Sinica, 2004, 59(2): 283-292. doi: 10.3321/j.issn:0375-5444.2004.02.015
	[田永中, 陈述彭, 岳天祥, 等. 基于土地利用的中国人口密度模拟. 地理学报, 2004, 59(2): 283-292.] doi: 10.3321/j.issn:0375-5444.2004.02.015
[52]	Breiman L.Random forests. Machine Learning, 2001, 45(1): 5-32. doi: 10.1023/A:1010933404324
[53]	Fang Kuangnan, Wu Jianbin, Zhu Jianping, et al.A review of technologies on random forests. Statistics and Information Forum, 2011, 26(3): 32-38. doi: 10.3969/j.issn.1007-3116.2011.03.006
	[方匡南,吴见彬,朱建平,等.随机森林方法研究综述.统计与信息论坛,2011, 26(3): 32-38.] doi: 10.3969/j.issn.1007-3116.2011.03.006
[54]	Zeng C Q, Zhou Y, Wang S X, et al.Population spatialization in China based on night-time imagery and land use data. International Journal of Remote Sensing, 2011, 32(24): 9599-9620. doi: 10.1080/01431161.2011.569581
[55]	Wang L, Feng Z M, Yang Y Z.The change in population density from 2000 to 2010 and its influencing factors in China at the county scale. Journal of Geographical Sciences, 2015, 25(4): 485-496. doi: 10.1007/s11442-015-1181-z
[56]	Liu Jinsong.A review of population geography research in China. Acta Geographica Sinica, 2014, 69(8): 1177-1189. doi: 10.11821/dlxb201408012
	[刘劲松. 中国人口地理研究进展. 地理学报, 2014, 69(8): 1177-1189.] doi: 10.11821/dlxb201408012
[57]	Shi X L, Wang W, Shi W J.Progress on quantitative assessment of the impacts of climate change and human activities on cropland change. Journal of Geographical Sciences, 2016, 26(3): 339-354. doi: 10.1007/s11442-016-1272-5
[58]	Yao Yonghui, Zhang Baiping.MODIS-based estimation of air temperature and heating-up effect of the Tibetan Plateau. Acta Geographica Sinica, 2013, 68(1): 95-107. doi: 10.3969/j.issn.0375-5444.2013.01.011
	[姚永慧, 张百平. 基于MODIS数据的青藏高原气温与增温效应估算. 地理学报, 2013, 68(1): 95-107.] doi: 10.3969/j.issn.0375-5444.2013.01.011
[59]	Zhou Qianqian, Ding Jianli, Tang Mengying, et al.Inversion of soil organic matter content in oasis typical of arid area and its influencing factors. Acta Pedologica Sinica, 2018, 55(2): 313-324.
	[周倩倩, 丁建丽, 唐梦迎, 等. 干旱区典型绿洲土壤有机质的反演及影响因素研究. 土壤学报, 2018, 55(2): 313-324.]
[60]	Liu Li, Han Mei, Liu Yubin, et al.Spatial distribution of wetland vegetation biomass and its influencing factors in the Yellow River Delta Nature Reserve. Acta Ecologica Sinica, 2017, 37(13): 4346-4355. doi: 10.5846/stxb201508241763
	[刘莉, 韩美, 刘玉斌, 等. 黄河三角洲自然保护区湿地植被生物量空间分布及其影响因素. 生态学报, 2017, 37(13): 4346-4355.] doi: 10.5846/stxb201508241763

人口密度分级(人/km²)	统计单元个数(个)	总人口(人)	人口占比(%)	总面积(km²)	面积占比(%)
0~1	102	235880	7.86	768471	63.82
1~4	189	550149	18.33	244664	20.32
4~7	115	482070	16.06	91516	7.60
7~10	75	378282	12.60	45631	3.79
10~40	126	870345	28.99	51935	4.31
40~70	7	43936	1.46	918	0.08
70~100	1	6621	0.22	74	0.01
100~400	6	142181	4.74	722	0.06
400~700	2	93542	3.12	172	0.01
>700	1	199159	6.63	68	0.01

影响因子	序号	与人口密度相关系数	与人口总数相关系数	相关系数平均值
海拔	A₁	-0.137^**	-0.172^**	-0.155
坡度	A₂	-0.058	-0.058	-
坡向	A₃	0.013	0.016	-
地形起伏度	A₄	-0.043	-0.058	-
多年平均降雨量	B₁	-0.057	-0.02	-
多年平均气温	B₂	0.171^**	0.197^**	0.184
NDVI	C	-0.001	0.047	-
冰川和永久积雪指数	D₁	-0.044	-0.047	-
草地指数	D₂	-0.043	-0.008	-
耕地指数	D₃	0.078	0.088^*	-
灌木指数	D₄	0.067	0.049	-
裸地指数	D₅	-0.05	-0.100^*	-
人造地表指数	D₆	0.942^**	0.810^**	0.876
森林指数	D₇	-0.025	-0.009	-
湿地指数	D₈	-0.015	-0.02	-
水体指数	D₉	-0.023	-0.021	-
苔原指数	D₁₀	-0.005	0.072	-
河网密度	E₁	0.498^**	0.437^**	0.468
距河流距离	E₂	-0.045	-0.071	-
路网密度	F₁	0.664^**	0.630^**	0.647
距道路距离	F₂	-0.048	-0.089^*	-
夜间灯光指数	G₁	0.902^**	0.792^**	0.847
GDP	G₂	0.398^**	0.490^**	0.444
工业总产值	G₃	0.453^**	0.452^**	0.453
农林牧渔业产值	G₄	0.036	0.327^**	-

地区	R²	MAE	排序1	排序2	排序3	排序4	排序5	排序6
拉萨市	0.98	50.84	G₁	D₆	B₂	G₃	A₁	D₂
昌都地区	0.96	1.94	A₁	D₆	G₁	B₂	G₂	D₃
山南地区	0.95	3.36	D₃	B₂	A₁	D₆	G₁	D₁
日喀则地区	0.97	3.53	D₆	G₁	D₃	F₁	B₂	A₁
那曲地区	0.92	0.60	C	A₁	B₁	B₂	F₁	D₆
阿里地区	0.98	0.30	D₆	G₁	D₃	B₂	F₁	D₁
林芝地区	0.87	1.16	G₁	D₆	F₁	F₂	D₈	A₂

基于随机森林模型的西藏人口分布格局及影响因素

Population distribution pattern and influencing factors in Tibet based on random forest model

RichHTML

PDF (PC)

赞

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 10

参考文献 60

相关文章 15

Metrics

本文评价

[1]	胡畔, 陈波, 史培军. 中国暴雨洪涝灾情时空格局及影响因素[J]. 地理学报, 2021, 76(5): 1148-1162.
[2]	郭付友, 佟连军, 仇方道, 李一鸣. 黄河流域生态经济走廊绿色发展时空分异特征与影响因素识别[J]. 地理学报, 2021, 76(3): 726-739.
[3]	徐羽, 李秀彬, 辛良杰. 中国耕地规模化流转租金的分异特征及其影响因素[J]. 地理学报, 2021, 76(3): 753-763.
[4]	董广辉, 仇梦晗, 李若, 陈发虎. 探讨过去人地关系演变机制的“支点”概念模型[J]. 地理学报, 2021, 76(1): 15-29.
[5]	曹智, 刘彦随, 李裕瑞, 王永生. 中国专业村镇空间格局及其影响因素[J]. 地理学报, 2020, 75(8): 1647-1666.
[6]	魏素豪, 李晶, 李泽怡, 宗刚. 中国农业竞争力时空格局演化及其影响因素[J]. 地理学报, 2020, 75(6): 1287-1300.
[7]	刘敏, 郝炜. 山西省国家A级旅游景区空间分布影响因素研究[J]. 地理学报, 2020, 75(4): 878-888.
[8]	古恒宇, 孟鑫, 沈体雁, 崔娜娜. 中国城市流动人口居留意愿影响因素的空间分异特征[J]. 地理学报, 2020, 75(2): 240-254.
[9]	戚伟, 刘盛和, 周亮. 青藏高原人口地域分异规律及“胡焕庸线”思想应用[J]. 地理学报, 2020, 75(2): 255-267.
[10]	段德忠, 杜德斌. 全球高科技产品贸易结构演化及影响因素[J]. 地理学报, 2020, 75(12): 2759-2776.
[11]	熊鹰, 章芳. 基于多源数据的长沙市人居热环境效应及其影响因素分析[J]. 地理学报, 2020, 75(11): 2443-2458.
[12]	杨青山, 刘鉴, 张郁, 杨维旭. 满洲里口岸—城市关系演变的多尺度因素影响分析[J]. 地理学报, 2020, 75(10): 2146-2163.
[13]	周扬, 黄晗, 刘彦随. 中国村庄空间分布规律及其影响因素[J]. 地理学报, 2020, 75(10): 2206-2223.
[14]	张凯煌, 千庆兰, 杨青生. 中国城市土地城镇化多层级影响因素分析[J]. 地理学报, 2020, 75(1): 179-193.
[15]	刘卫东, 唐志鹏, 夏炎, 韩梦瑶, 姜宛贝. 中国碳强度关键影响因子的机器学习识别及其演进[J]. 地理学报, 2019, 74(12): 2592-2603.