Please wait a minute...
img

官方微信

遥感技术与应用  2022, Vol. 37 Issue (2): 379-388    DOI: 10.11873/j.issn.1004-0323.2022.2.0379
LUCC专栏     
超大城市土地覆盖与热环境的随机森林回归模型研究
王美雅1(),徐涵秋2()
1.闽南师范大学 历史地理学院,福建 漳州 363000
2.福州大学 环境与资源学院,福州大学遥感信息工程研究所,福建省水土流失遥感监测评估与灾害防治重点实验室,福建 福州 350116
Study on the Random Forest Regression Model of Land Cover and Thermal Environment in Megacities
Meiya Wang1(),Hanqiu Xu2()
1.School of History and Geography,Minnan Normal University,Zhangzhou 363000,China
2.College of Environment and Resources; Institute of Remote Sensing Information Engineering; Fujian Provincial Key Laboratory of Remote Sensing of Soil Erosion and Disaster Prevention,Fuzhou University,Fuzhou 350116,China
 全文: PDF(5252 KB)   HTML
摘要:

目前对于超大城市土地覆盖和热环境定量模型研究报道不足,这主要是因为大城市地表温度和地表生物物理组分之间存在复杂的潜在非线性关系,这使得准确评估城市热环境情况遇到了严峻的技术挑战。研究选取中外6个典型超大城市(北京、上海、广州、伦敦、纽约和东京)为研究对象,以Landsat遥感影像为主要数据源,利用单通道算法反演各城市地表温度,采用随机森林回归模型(RFR)建立土地覆盖类型与城市热环境定量关系模型(LCT),综合分析城市土地覆盖因子与热环境间的多维定量关系。土地覆盖与地表温度的定量关系显示,城市地表热场的空间结构在很大程度上被下垫面用地类型所左右,不透水面会导致高温热场的聚集,而植被和水体则有降温作用。6个超大城市地表覆盖结构变化产生的升温/降温效应有所差异,北京、上海、纽约和东京等城市区域的植被和水体降温效应较广州和伦敦显著。基于随机森林回归方法建立了NDVI、MNDWI和NDISI等3种土地覆盖类型与城市热环境的综合定量关系模型(LCT),模型得到的精度高于基于多元线性回归方法建立的模型。LCT_RF模型的R2值在0.623~0.826之间,比LCT_MLR模型高0.021~0.074;RMSE比LCT_MLR模型低0.07℃~0.35℃。研究超大城市土地覆盖与城市热环境的互动作用机理,能为未来生态城市建设提供宝贵建议。

关键词: 超大城市土地覆盖城市热环境遥感随机森林回归模型    
Abstract:

Rapid urbanization has led to rapid change in land cover and the landsurface heat balance in megacities. Due to the complex potential nonlinear relationship between land surface temperature and surface biophysical components in megacities, the quantitative models and the response mechanism between land cover and thermal environment in megacities is not yet clear. Takesix Chinese and foreign megacities (Beijing, Shanghai, Guangzhou, London, New York and Tokyo) as the study area, Landsat images were used to comprehensively analyze the quantitative relationship between urban land cover factors and thermal environment. The single-channel algorithm was used to retrieve the land surface temperature of thesix megacities.The random forest regression model was used to establish the quantitative relationship (LCT) model between land cover types and urban thermal environment (LST). The quantitative relationship between land cover type and LST showed that the LST was closely related to urban land surface types. The spatial pattern of the urban thermal field depends to a great extent on the spatial distribution pattern of the urban land surface types. The impervious surface will lead to the accumulation of high LST fields, while vegetation and water had a significant cooling effect. The land cover compositionin six megacities had different heating/cooling effects. In urban areas, such as Beijing, Shanghai, New York, and Tokyo, the cooling effects of vegetation and water were more pronounced than thosein Guangzhou and London. The established LCTmodel between the three land cover types, NDVI, MNDWI, and NDISI, and the urban thermal environment showed that the LCT model had higher precisionthan that was based on the multiple linear regression method. The R2 value of the LCT_RF model is 0.021~0.074, which is higher than that of the LCT_MLR model. The RMSE is 0.07℃~0.35℃, which is lower than that of the LCT_MLR model.It will be helpful for future construction of eco-cities by studying the interaction mechanism between the land cover and the urban thermal environment in megacities.

Key words: Megacities    Land cover    Urban heat environment    Remote sensing    Random forest regression model
收稿日期: 2021-10-21 出版日期: 2022-06-17
ZTFLH:  P237  
基金资助: 国家重点研发计划专项课题(2016YFA0600302);福建省创新战略研究项目(2020R0155);闽南师范大学校长基金项目(KJ19013)
通讯作者: 徐涵秋     E-mail: 286097145@qq.com;hxu@fzu.edu.cn
作者简介: 王美雅(1991-),女,福建泉州人,博士,副教授,主要从事环境与资源遥感研究。E?mail: 286097145@qq.com
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章  
王美雅
徐涵秋

引用本文:

王美雅,徐涵秋. 超大城市土地覆盖与热环境的随机森林回归模型研究[J]. 遥感技术与应用, 2022, 37(2): 379-388.

Meiya Wang,Hanqiu Xu. Study on the Random Forest Regression Model of Land Cover and Thermal Environment in Megacities. Remote Sensing Technology and Application, 2022, 37(2): 379-388.

链接本文:

http://www.rsta.ac.cn/CN/10.11873/j.issn.1004-0323.2022.2.0379        http://www.rsta.ac.cn/CN/Y2022/V37/I2/379

图1  研究区Landsat 遥感影像
图2  随机森林回归模型建立过程
图3  6个超大城市地表温度反演结果
城市日期过空时间卫星LST均值/℃平均LST差值/℃
北京2015/8/2211:48a.m.MODIS37.6910.135
10:53a.m.Landsat37.556
上海2015/8/311:36a.m.MODIS38.557-0.855
10:24a.m.Landsat37.702
广州2015/10/1810:48a.m.MODIS32.7670.823
10:52a.m.Landsat33.590
伦敦2015/10/210:24a.m.MODIS19.177-1.312
10:58a.m.Landsat17.865
纽约2015/8/2610:12a.m.MODIS31.6000.869
10:39a.m.Landsat32.469
东京2015/10/911:42a.m.MODIS26.7451.314
10:15a.m.Landsat28.059
表1  地表温度反演精度对比
图4  植被、水体和不透水面比例与地表温度回归散点图
城市LCT_RF(3指数)LCT_MLR(3指数)
R2RMSE/℃R2RMSE/℃
北京0.6561.6460.6351.956
上海0.7751.3470.7541.592
广州0.7261.5070.6861.613
伦敦0.6230.8820.5590.954
纽约0.8261.8140.7522.164
东京0.7611.6360.6981.897
表2  LCT_RF和LCT_MLR方法预测LST精度对比
图5  6个城市LCT_RF(3 指数)模型结果
图6  6个城市LCT_MLR(3 指数)模型结果
1 KuangWenhui, Yang Tianrong, Liu Ailin, et al. An Eco-City model for regulating urban land cover structure and thermal environment: Taking Beijing as an example[J]. Science China Earth Sciences,2017,47(7):847-859.
1 匡文慧, 杨天荣, 刘爱琳, 等. 城市地表覆盖结构组分与热环境调控模型(EcoCity)研究——以北京城市为例 [J]. 中国科学: 地球科学, 2017, 47(7): 847-859.
2 Wang Yu, Tang Li, Zhu Haitao,et al. The study of urban thermal environment dynamicsand attribution analysis basedon multiple remote sensing dataset: In the case of Shenzhen[J]. Acta EcologicaSinica, 2021,41(22):8771-8782.
2 王煜,唐力,朱海涛,等.基于多源遥感数据的城市热环境响应与归因分析——以深圳市为例[J].生态学报,2021,41(22):8771-8782.
3 Xu H Q, Wang M Y, Shi T T, et al. Prediction of ecological effects of potential population and impervious surface increases using a Remote Sensing based Ecological Index(RSEI)[J]. Ecological Indicators, 2018, 93: 730-740.
4 Zhang Xiaodong, Zhao Yinxin, Chu Xiaodong, et al. Spatial and temporal evolution characteristics of thermal environment and its influencing factors in urban area of Yinchuan City based on remote sensing [J]. Research of Soil and Water Conservation, 2020, 27(6): 180-187.
4 张晓东, 赵银鑫,褚小东,等. 基于遥感的银川市城区热环境及其影响因素的时空演变特征 [J]. 水土保持研究, 2020, 27(6): 180-187.
5 Gao Yang, XiongJuhua, Wu Hao,et al. Frontier hotspotsand development directions of geographical science research:From a perspective of national natural science foundation application keywords in 2021[J/OL]. Scientia GeographicaSinica:1-16.
5 高阳,熊巨华,吴浩,等.2021年度自然科学基金申请书关键词透视地理科学研究前沿热点与发展方向[J/OL].地理科学:1-16..
6 Li Deren. Brain cognition and spatial cognition: On integration of geospatial big data and artificial intelligence[J]. Geomatics and Information Science of Wuhan University,2018,43(12): 1761-1767.
6 李德仁. 脑认知与空间认知—论空间大数据与人工智能的集成 [J]. 武汉大学学报: 信息科学版,2018,43(12):1761-1767.
7 Zhang Fei, Shao Yuan, Huang Hui,et al.Reviewof urban remote sensing researchinthe last two decades[J]. Acta Ecologica Sinica,2021,41(8):3255-3276.
7 张飞, 邵媛, 黄晖,等. 近20年城市遥感研究现状及其发展趋势[J]. 生态学报,2021,41(8):3255-3276.
8 Feyisa G L, Meilby H, Jenerette G D, et al. Locally optimized separability enhancementIndices for urban land cover mapping: Exploring thermal environmental consequences of rapid urbanization in Addis Ababa,Ethiopia[J].Remote Sen-sing of Environment,2016,175:14-31.
9 Yang Yuting, Tang Jiafa,BianJinhu,et al. Seasonal variations in the relationship between land sur‐face yemperature and impervious surface percentage in Kolkata[J]. Remote Sensing Technology and Application,2021,36(1):79-89.
9 杨玉婷,汤家法,边金虎,等.加尔各答市地表温度与不透水面比例季相相关性研究[J].遥感技术与应用,2021,36(01):79-89.
10 Zheng B J, Myint S W, Fan C. Spatial configuration of anthropogenic land cover impacts on urban warming[J]. Landscape and Urban Planning, 2014, 130: 104-111.
11 Chen Y J, Yu S X. Impacts of urban landscape patterns on urban thermal variations in Guangzhou, China[J]. International Journal of Applied Earth Observation and Geoinformation, 2017, 54: 65-71.
12 Kotharkar R, Bagade A. Evaluating urban heat island in the criticalLocal climate zones of an Indian city[J]. Landscape and Urban Planning, 2018, 169: 92-104.
13 Nguyen T, Yu X X, Zhang Z M, et al. Relationship betweentypes of urban forest and PM2.5 capture at three growth stages of leaves[J]. Journal of Environmental Sciences,2015,27:33-41.
14 Balcik F B. Determining the impact of urban components on land surface temperature of istanbul by using remote sensing indices[J]. Environmental Monitoring and Assessment, 2014, 186(2): 859-872.
15 Nsubuga F W N, Botai J O, Olwoch J M, et al. Detecting changes in surface water area of lake Kyoga sub-basin using remotely sensed imagery in a changing climate[J]. Theoretical and Applied Climatology, 2017, 127(1-2): 327-337.
16 XuHanqiu. Urban expansion process in the center of the fuzhou basin, Southeast China in 1976-2006[J]. Scientia Geographica Snica, 2011,31(3):351-357.
16 徐涵秋.近30 a来福州盆地中心的城市扩展进程[J]. 地理科学,2011,31(3):351-357.
17 Shen H F, Huang L W, Zhang L P, et al. Long-term and fine-scale satellite monitoring of the urban heat island effect by the fusion of multi-temporal and multi-sensor remote sensed data: A 26-year case study of the city of wuhan in China[J]. Remote Sensing of Environment, 2016, 172: 109-125.
18 Son N T, Thanh B X. Decadal assessment of urban sprawl and its effects on local temperature using landsat data in Cantho city,Vietnam[J].Sustainable Cities and Society,2018,36:81-91.
19 Van de Voorde T, Jacquet W, Canters F. Mapping form and function in urban areas: An approach based on urban metrics and continuous impervious surface data[J]. Landscape and Urban Planning, 2011, 102(3): 143-155.
20 Chander G, Markham B L, Helder D L. Summary of current radiometric calibration coefficients for landsat MSS, TM, ETM+, and EO-1 ALI sensors[J]. Remote Sensing of Environment, 2009, 113(5): 893-903.
21 CharvzJr P S. Image-based atmospheric corrections-revisited and revised[J]. Photogrammetric Engineering and Remote Sensing,1996,62(9):1025-1036.
22 Jiménez-Muñoz J C, Cristobal J, Sobrino J A, et al. Revision of the single-channel algorithm for land surface temperature retrieval from landsat thermal-infrared data[J]. IEEE Transactions on Geoscience and Remote Sensing,2009,47(1): 339-349.
23 Jiménez-Muñoz J C, Sobrino J A. A generalized single-channel method for retrieving land surface temperature from remote sensing data[J]. Journal of Geophysical Research Atmos-pheres, 2003,108(D22): 4688.
24 Jiménez-Muñoz J C, Sobrino J A, Skoković D, et al. Land surface temperature retrieval methods from Landsat8 thermal infrared sensor data[J]. IEEE Geoscience & Remote Sensing Letters, 2014, 11(10): 1840-1843.
25 Dematte J A M, Sayao V M, Rizzo R, et al. Soil class and attribute dynamics and their relationship with natural vegetation based on satellite remote sensing[J].Geoderma,2017,302:39-51.
26 Tulbure M G, Broich M, Stehman S V, et al. Surface water extent dynamics from three decades of seasonally continuous landsat time series at subcontinental scale in a semiarid region [J]. Remote Sensing of Environment,2016,178,142-157.
27 Li Deren, Luo Hui, Shao Zhenfeng. Review of impervious surface mapping using remote sensing technology and its application[J]. Geomatics and Information Science of Wuhan University, 2016, 41(5): 569-703.
27 李德仁, 罗晖, 邵振峰. 遥感技术在不透水层提取中的应用与展望[J]. 武汉大学学报(信息科学版), 2016, 41(5): 569-703.
28 XuH Q.Analysis of impervious surface and its impact on urban heat environment using the Normalized Difference Impervious Surface Index (NDISI)[J]. Photogrammetric Engineering & Remote Sensing, 2010,76(5):557-565.
29 Wentz E A.Getting started with geographic information systems, 3rd edition[J]. International Journal of Geographical Information Science, 2002, 16(2): 204-205.
30 Breiman L. Random forests[J]. Machine Learning, 2001, 45(1): 5-32.
31 JiaJiaqiong, Liu Wanqing, MengQingyan, et al. Estimation of maize leaf area index based on GF-1 WFV image and machine learning random algorithm[J]. Journal of Image and Graphics, 2018, 23(5):719-729.
31 贾洁琼, 刘万青, 孟庆岩, 等. 基于GF-1 WFV影像和机器学习算法的玉米叶面积指数估算[J]. 中国图象图形学报, 2018, 23(5): 719-729.
32 Du P J, Samat A, Waske B, et al. Random forest and rotation forest for fully polarized SAR image classification using polarimetric and spatial features[J]. ISPRS Journal of Photogrammetry and Remote Sensing,2015,105: 38-53.
[1] 王婷,邹滨,邹峥嵘,李沈鑫,郑忠. 秸秆焚烧遥感监测进展分析与展望[J]. 遥感技术与应用, 2022, 37(2): 279-289.
[2] 盖一铭,阿里木·赛买提,王伟,吉力力·阿不都外力. 基于样本迁移的干旱区地表覆盖快速更新[J]. 遥感技术与应用, 2022, 37(2): 333-341.
[3] 王永前,何孟琦,张洋,杨世琦,高阳华. 基于高分五号DPC数据的细模态气溶胶光学厚度反演[J]. 遥感技术与应用, 2022, 37(2): 451-459.
[4] 张飞舟,刘华亮,张立福,岑奕,孙雪剑,张红明. 高分辨率光学遥感影像变化检测算法在地震灾情调查中的应用[J]. 遥感技术与应用, 2022, 37(2): 306-318.
[5] 付涵,范湘涛,严珍珍,杜小平. 基于深度学习的遥感图像目标检测技术研究进展[J]. 遥感技术与应用, 2022, 37(2): 290-305.
[6] 郭长庆,张学霞,侯亚丽,匡文慧. 基于多源时空信息的西宁和拉萨近70年来城市扩展过程重现及地表覆盖变化分析[J]. 遥感技术与应用, 2022, 37(2): 342-353.
[7] 王修成,张黎明. 一种基于同态公钥加密的遥感影像数字指纹方案[J]. 遥感技术与应用, 2022, 37(2): 532-538.
[8] 姜亚楠,张春雷,张欣,徐权威,张舒涛,周锐. 利用提升树模型综合Gabor和LPQ特征进行遥感地物识别[J]. 遥感技术与应用, 2022, 37(2): 515-523.
[9] 刘娜,张风丽,李志坤,邵芸,庞雷,李璐. 基于SAR与NL数据的建成区提取及其在WRF风场模拟优化中应用[J]. 遥感技术与应用, 2022, 37(2): 488-498.
[10] 黄耀欢,熊标,杨海军,伍程斌,朱海涛. 入河排污口遥感排查进展评述[J]. 遥感技术与应用, 2022, 37(1): 24-33.
[11] 赵天玮,朱文彬,裴亮,宝康妮. 三江源蒸散发遥感估算及其时空分布特征研究[J]. 遥感技术与应用, 2022, 37(1): 137-147.
[12] 赵辉,王泽根,雷光斌,边金虎,李爱农. 缅甸土地覆被遥感制图和空间格局分析[J]. 遥感技术与应用, 2022, 37(1): 148-160.
[13] 王茜,宋开山,毛德华,焉恒琦,谭晓宇,王宗明. 1980~2018朝鲜半岛西海岸滨海湿地演化分析[J]. 遥感技术与应用, 2022, 37(1): 108-116.
[14] 张红月,李宜展,陈思明,黄铭瑞,孙玉. 近10 a全球遥感科学研究的时空动态分析[J]. 遥感技术与应用, 2022, 37(1): 45-60.
[15] 杨凤珠,王震山,张乾,孙善磊,柳艺博. 多源日光诱导叶绿素荧光产品在中国地区的一致性研究[J]. 遥感技术与应用, 2022, 37(1): 125-136.