基于随机森林模型的城市扩张三维特征时空变化及机制分析
|
摘要
当前从二维角度已不能准确描述城市扩张的真实情况,而从三维角度定量研究城市扩张对解决城市问题有重要意义。该文以广州市主城区的社区为单元,基于2005年、2010年、2015年地表建筑数据,利用城市三维扩张指标和城市驱动因子,结合随机森林模型,分析三维扩张格局并探究三维扩张的机制。结果表明:1)2005-2015年,前5年研究区三维扩张速度较快,其中平均建筑体积指标增长最快;2)城市三维扩张指标的增长主要从研究区中心的越秀区向白云区北部、天河区东部和荔湾区西南部呈辐射状分布;3)研究期内,对城市三维扩张影响较大的主要为生活服务设施、地铁、公交站点以及综合商业中心,其中地铁站的影响力不断增大。此外,火车站和市中心的影响也越来越显著,并且随着时间的演变,各驱动力因子之间的影响力差异变小。
At present,analyzing the urban expansion from two-dimensional perspective is not able to accurately describe the reality of urban spatial expansion.Therefore,to address urbanization issues,it′s of great significance to conduct a quantitative research from three-dimensional perspective.This paper,taking communities in the main urban area of Guangzhou as study case,analyzed the spatio-temporal patterns of urban 3D expansion based on the 3D expansion indexes embodying the features of ground building data in 2005,2010 and 2015,as well as explored the driving mechanism of urban 3D expansion through the random forest model.The results showed that:1) The urban 3D expansion indexes of study area have witnessed a rapider increase in the period of 2005-2010 than 2010-2015,and the average building volume grew fastest.2) The value increase of urban 3D expansion indexes was mainly radiating from Yuexiu District,a center region of the study area,to the north of Baiyun District,the east of Tianhe District and the southwest of Liwan District.3) In the period of 2005-2015,the urban 3D expansion was mainly affected by social amenities,metro stations,public transportation stations and integrated commercial centers,among which the influence of metro stations continued to increase.In addition,the impacts of railway stations and city downtown become more and more significant.It is noteworthy that,the differences regarding the influence among various driving forces become smaller as time goes on.
At present,analyzing the urban expansion from two-dimensional perspective is not able to accurately describe the reality of urban spatial expansion.Therefore,to address urbanization issues,it′s of great significance to conduct a quantitative research from three-dimensional perspective.This paper,taking communities in the main urban area of Guangzhou as study case,analyzed the spatio-temporal patterns of urban 3D expansion based on the 3D expansion indexes embodying the features of ground building data in 2005,2010 and 2015,as well as explored the driving mechanism of urban 3D expansion through the random forest model.The results showed that:1) The urban 3D expansion indexes of study area have witnessed a rapider increase in the period of 2005-2010 than 2010-2015,and the average building volume grew fastest.2) The value increase of urban 3D expansion indexes was mainly radiating from Yuexiu District,a center region of the study area,to the north of Baiyun District,the east of Tianhe District and the southwest of Liwan District.3) In the period of 2005-2015,the urban 3D expansion was mainly affected by social amenities,metro stations,public transportation stations and integrated commercial centers,among which the influence of metro stations continued to increase.In addition,the impacts of railway stations and city downtown become more and more significant.It is noteworthy that,the differences regarding the influence among various driving forces become smaller as time goes on.
引文
[1] 吴巍,陈敏,王楠,等.中国城镇用地扩展时空异质性研究进展[J].地理与地理信息科学,2017,33(6):57-63.
[2] ZHAO S Q,ZHOU D C,ZHU C.Spatial and temporal dimensions of urban expansion in China[J].Sustainable Cities and Society,2015,17:141-150.
[3] 李俊峰,潘竟虎.基于夜间灯光的1992-2012年甘肃省城市空间扩展研究[J].冰川冻土,2016,38(3):263-269.
[4] NGUYEN L H,NGHIEM S V,HENEBRY G M.Expansion of major urban areas in the US Great Plains from 2000 to 2009 using satellite scatterometer data[J].Remote Sensing of Environment,2018,204:524-533.
[5] 王钊,杨山,王玉娟,等.基于最小阻力模型的城市空间扩展冷热点格局分析——以苏锡常地区为例[J].经济地理,2016,36(3):57-64.
[6] LIU X P,LI X,CHEN Y M,et al.A new landscape index for quantifying urban expansion using multi-temporal remotely sensed data[J].Landscape Ecology,2010,25(5):671-682.
[7] LIU J Y,ZHANG Q,HU Y F.Regional differences of China′s urban expansion from late 20th to early 21st century based on remote sensing information[J].Chinese Geographical Science,2012,22(1):1-14.
[8] 王新生,刘纪远,庄大方,等.中国特大城市空间形态变化的时空特征[J].地理学报,2005,60(3):392-400.
[9] 张培峰,胡远满.不同空间尺度三维建筑景观变化[J].生态学杂志,2013,32(5):1319-1325.
[10] 国安东,李永化,杨俊.基于多距离空间聚类的城市建筑景观时空分异研究[J].测绘通报,2017(2):110-113.
[11] HARVEY C.Measuring Streetscape Design for Livability Using Spatial Data and Methods[D].Vermont:The University of Vermont and State Agricultural College,2014.
[12] ZHANG W X,LI W D,ZHANG C R,et al.Analyzing horizontal and vertical urban expansions in three East Asian megacities with the SS-coMCRF model[J].Landscape and Urban Planning,2018,177:114-127.
[13] 李雪铭,朱健亮,王勇.居住小区容积率空间差异——以大连市为例[J].地理科学进展,2015,34(6):33-41.
[14] 焦利民,李泽慧,许刚,等.武汉市城市空间集聚要素的分布特征与模式[J].地理学报,2017,72(8):106-117.
[15] 秦静,方创琳,王洋,等.基于三维计盒法的城市空间形态分维计算和分析[J].地理研究,2015,34(1):87-98.
[16] 乔伟峰,刘彦随,王亚华,等.2000年以来南京城市三维空间扩展特征[J].地理研究,2015,34(4):70-80.
[17] 文雅,龚建周,胡银根,等.基于生态安全导向的城市空间扩展模拟与分析[J].地理研究,2017,36(3):116-126.
[18] LI X M,ZHOU W Q,OUYANG Z Y.Forty years of urban expansion in Beijing:What is the relative importance of physical,socioeconomic,and neighborhood factors?[J].Applied Geography,2013,38:1-10.
[19] ZHANG Q W,SU S L.Determinants of urban expansion and their relative importance:A comparative analysis of 30 major metropolitans in China[J].Habitat International,2016,58:89-107.
[20] 张亦汉,黎夏,刘小平,等.耦合遥感观测和元胞自动机的城市扩张模拟[J].遥感学报,2013,17(4):872-886.
[21] LIU X P,LIANG X,LI X,et al.A future land use simulation model (FLUS) for simulating multiple land use scenarios by coupling human and natural effects[J].Landscape and Urban Planning,2017,168:94-116.
[22] 徐海龙,尹海伟,孔繁花,等.基于潜力—约束和SLEUTH模型松散耦合的南京城市扩展模拟[J].地理研究,2017,36(3):127-138.
[23] 周淑丽,陶海燕,卓莉.基于矢量的城市扩张多智能体模拟——以广州市番禺区为例[J].地理科学进展,2014,33(2):202-210.
[24] 陈凯,刘凯,柳林,等.基于随机森林的元胞自动机城市扩展模拟——以佛山市为例[J].地理科学进展,2015,34(8):3-12.
[25] 田贺,梁迅,黎夏,等.基于SD模型的中国2010―2050年土地利用变化情景模拟[J].热带地理,2017,37(4):107-121.
[26] ARSANJANI J J,HELBICH M,KAINZ W,et al.Integration of logistic regression,Markov chain and cellular automata models to simulate urban expansion[J].International Journal of Applied Earth Observation and Geoinformation,2013,21:265-275.
[27] 乔伟峰.土地利用视角下的南京城市空间多维扩展研究[D].南京:南京师范大学,2013.
[28] 杨俊,国安东,席建超,等.城市三维景观格局时空分异特征研究——以大连市中山区为例[J].地理学报,2017,72(4):88-98.
[29] QIN J,FANG C Y,WANG Y,et al.Evaluation of three-dimensional urban expansion:A case study of Yangzhou City,Jiangsu Province,China[J].Chinese Geographical Science,2015,25(2):224-236.
[30] 陈飞.基于GIS和CA的城市三维空间扩展研究[D].大连:辽宁师范大学,2016.
[31] ZHANG W X,LI W D,ZHANG C R,et al.Detecting horizontal and vertical urban growth from medium resolution imagery and its relationships with major socioeconomic factors[J].International Journal of Remote Sensing,2017,38(12):3704-3734.
[32] SALVATI L,ZITTI M,SATERIANO A.Changes in city vertical profile as an indicator of sprawl:Evidence from a Mediterranean urban region[J].Habitat International,2013,38:119-125.
[33] 秦静,方创琳,王洋.基于元胞自动机的城市三维空间增长仿真模拟[J].地球信息科学学报,2013,15(5):662-671.
[34] HE Q S,LIU Y L,ZENG C,et al.Simultaneously simulate vertical and horizontal expansions of a future urban landscape:A case study in Wuhan,central China[J].International Journal of Geographical Information Science,2017,31(10):1907-1928.
[35] 杨青生,黎夏.基于遗传算法自动获取CA模型的参数——以东莞市城市发展模拟为例[J].地理研究,2007(2):229-237.
[36] 张大川,刘小平,姚尧,等.基于随机森林CA的东莞市多类土地利用变化模拟[J].地理与地理信息科学,2016,32(5):33-40.
[37] 郭平,周伟,袁涛,等.衰退型资源城市土地利用时空变化及驱动因素分析[J].水土保持研究,2016(4):191-198.
[38] 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):122-130.
[39] 李亭,田原,邬伦,等.基于随机森林方法的滑坡灾害危险性区划[J].地理与地理信息科学,2014,30(6):29-34.
[40] 邵琦,陈云浩,李京.基于卫星遥感和气象再分析资料的北京市PM2.5浓度反演研究[J].地理与地理信息科学,2018,34(3):32-38.
[41] 白琳,徐永明,何苗,等.基于随机森林算法的近地表气温遥感反演研究[J].地球信息科学学报,2017(3):390-397.
[42] 张密芳,胡曼,李明阳.基于PALSAR全极化数据的城市森林蓄积量估测[J].南京林业大学学报(自然科学版),2016(6):56-62.
[2] ZHAO S Q,ZHOU D C,ZHU C.Spatial and temporal dimensions of urban expansion in China[J].Sustainable Cities and Society,2015,17:141-150.
[3] 李俊峰,潘竟虎.基于夜间灯光的1992-2012年甘肃省城市空间扩展研究[J].冰川冻土,2016,38(3):263-269.
[4] NGUYEN L H,NGHIEM S V,HENEBRY G M.Expansion of major urban areas in the US Great Plains from 2000 to 2009 using satellite scatterometer data[J].Remote Sensing of Environment,2018,204:524-533.
[5] 王钊,杨山,王玉娟,等.基于最小阻力模型的城市空间扩展冷热点格局分析——以苏锡常地区为例[J].经济地理,2016,36(3):57-64.
[6] LIU X P,LI X,CHEN Y M,et al.A new landscape index for quantifying urban expansion using multi-temporal remotely sensed data[J].Landscape Ecology,2010,25(5):671-682.
[7] LIU J Y,ZHANG Q,HU Y F.Regional differences of China′s urban expansion from late 20th to early 21st century based on remote sensing information[J].Chinese Geographical Science,2012,22(1):1-14.
[8] 王新生,刘纪远,庄大方,等.中国特大城市空间形态变化的时空特征[J].地理学报,2005,60(3):392-400.
[9] 张培峰,胡远满.不同空间尺度三维建筑景观变化[J].生态学杂志,2013,32(5):1319-1325.
[10] 国安东,李永化,杨俊.基于多距离空间聚类的城市建筑景观时空分异研究[J].测绘通报,2017(2):110-113.
[11] HARVEY C.Measuring Streetscape Design for Livability Using Spatial Data and Methods[D].Vermont:The University of Vermont and State Agricultural College,2014.
[12] ZHANG W X,LI W D,ZHANG C R,et al.Analyzing horizontal and vertical urban expansions in three East Asian megacities with the SS-coMCRF model[J].Landscape and Urban Planning,2018,177:114-127.
[13] 李雪铭,朱健亮,王勇.居住小区容积率空间差异——以大连市为例[J].地理科学进展,2015,34(6):33-41.
[14] 焦利民,李泽慧,许刚,等.武汉市城市空间集聚要素的分布特征与模式[J].地理学报,2017,72(8):106-117.
[15] 秦静,方创琳,王洋,等.基于三维计盒法的城市空间形态分维计算和分析[J].地理研究,2015,34(1):87-98.
[16] 乔伟峰,刘彦随,王亚华,等.2000年以来南京城市三维空间扩展特征[J].地理研究,2015,34(4):70-80.
[17] 文雅,龚建周,胡银根,等.基于生态安全导向的城市空间扩展模拟与分析[J].地理研究,2017,36(3):116-126.
[18] LI X M,ZHOU W Q,OUYANG Z Y.Forty years of urban expansion in Beijing:What is the relative importance of physical,socioeconomic,and neighborhood factors?[J].Applied Geography,2013,38:1-10.
[19] ZHANG Q W,SU S L.Determinants of urban expansion and their relative importance:A comparative analysis of 30 major metropolitans in China[J].Habitat International,2016,58:89-107.
[20] 张亦汉,黎夏,刘小平,等.耦合遥感观测和元胞自动机的城市扩张模拟[J].遥感学报,2013,17(4):872-886.
[21] LIU X P,LIANG X,LI X,et al.A future land use simulation model (FLUS) for simulating multiple land use scenarios by coupling human and natural effects[J].Landscape and Urban Planning,2017,168:94-116.
[22] 徐海龙,尹海伟,孔繁花,等.基于潜力—约束和SLEUTH模型松散耦合的南京城市扩展模拟[J].地理研究,2017,36(3):127-138.
[23] 周淑丽,陶海燕,卓莉.基于矢量的城市扩张多智能体模拟——以广州市番禺区为例[J].地理科学进展,2014,33(2):202-210.
[24] 陈凯,刘凯,柳林,等.基于随机森林的元胞自动机城市扩展模拟——以佛山市为例[J].地理科学进展,2015,34(8):3-12.
[25] 田贺,梁迅,黎夏,等.基于SD模型的中国2010―2050年土地利用变化情景模拟[J].热带地理,2017,37(4):107-121.
[26] ARSANJANI J J,HELBICH M,KAINZ W,et al.Integration of logistic regression,Markov chain and cellular automata models to simulate urban expansion[J].International Journal of Applied Earth Observation and Geoinformation,2013,21:265-275.
[27] 乔伟峰.土地利用视角下的南京城市空间多维扩展研究[D].南京:南京师范大学,2013.
[28] 杨俊,国安东,席建超,等.城市三维景观格局时空分异特征研究——以大连市中山区为例[J].地理学报,2017,72(4):88-98.
[29] QIN J,FANG C Y,WANG Y,et al.Evaluation of three-dimensional urban expansion:A case study of Yangzhou City,Jiangsu Province,China[J].Chinese Geographical Science,2015,25(2):224-236.
[30] 陈飞.基于GIS和CA的城市三维空间扩展研究[D].大连:辽宁师范大学,2016.
[31] ZHANG W X,LI W D,ZHANG C R,et al.Detecting horizontal and vertical urban growth from medium resolution imagery and its relationships with major socioeconomic factors[J].International Journal of Remote Sensing,2017,38(12):3704-3734.
[32] SALVATI L,ZITTI M,SATERIANO A.Changes in city vertical profile as an indicator of sprawl:Evidence from a Mediterranean urban region[J].Habitat International,2013,38:119-125.
[33] 秦静,方创琳,王洋.基于元胞自动机的城市三维空间增长仿真模拟[J].地球信息科学学报,2013,15(5):662-671.
[34] HE Q S,LIU Y L,ZENG C,et al.Simultaneously simulate vertical and horizontal expansions of a future urban landscape:A case study in Wuhan,central China[J].International Journal of Geographical Information Science,2017,31(10):1907-1928.
[35] 杨青生,黎夏.基于遗传算法自动获取CA模型的参数——以东莞市城市发展模拟为例[J].地理研究,2007(2):229-237.
[36] 张大川,刘小平,姚尧,等.基于随机森林CA的东莞市多类土地利用变化模拟[J].地理与地理信息科学,2016,32(5):33-40.
[37] 郭平,周伟,袁涛,等.衰退型资源城市土地利用时空变化及驱动因素分析[J].水土保持研究,2016(4):191-198.
[38] 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):122-130.
[39] 李亭,田原,邬伦,等.基于随机森林方法的滑坡灾害危险性区划[J].地理与地理信息科学,2014,30(6):29-34.
[40] 邵琦,陈云浩,李京.基于卫星遥感和气象再分析资料的北京市PM2.5浓度反演研究[J].地理与地理信息科学,2018,34(3):32-38.
[41] 白琳,徐永明,何苗,等.基于随机森林算法的近地表气温遥感反演研究[J].地球信息科学学报,2017(3):390-397.
[42] 张密芳,胡曼,李明阳.基于PALSAR全极化数据的城市森林蓄积量估测[J].南京林业大学学报(自然科学版),2016(6):56-62.