基于随机森林模型的城市不透水面提取研究——以呼和浩特市为例

doi:10.7522/j.issn.1000-0240.2018.0089

冰川冻土 ›› 2018, Vol. 40 ›› Issue (4): 828-836.doi: 10.7522/j.issn.1000-0240.2018.0089

基于随机森林模型的城市不透水面提取研究——以呼和浩特市为例

郜燕芳¹, 李俊明², 刘东伟¹, 任周鹏³, 王楠楠⁴

1. 内蒙古大学生态与环境学院, 内蒙古呼和浩特 010021;
2. 山西财经大学统计学院, 山西太原 030006;
3. 中国科学院地理科学与资源研究所, 北京 100101;
4. 河南大学环境与规划学院, 河南开封 475004

收稿日期:2018-03-01 修回日期:2018-07-25 出版日期:2018-08-25 发布日期:2018-10-08
通讯作者: 刘东伟,E-mail:liudw@imu.edu.cn. E-mail:liudw@imu.edu.cn
作者简介:郜燕芳(1990-),女,内蒙古乌兰察布人,技术员,2017年在内蒙古大学获硕士学位,从事环境生态学研究.E-mail:gaoyf@lreis.ac.cn
基金资助:
国家自然科学基金项目（41571090；41201539；31560146）资助

Research on extraction of urban impervious surface based on random forest model: a case study in Hohhot

GAO Yanfang¹, LI Junming², LIU Dongwei¹, REN Zhoupeng³, WANG Nannan⁴

1. School of Ecology and Environment, Inner Mongolia University, Hohhot 010021, China;
2. School of Statistics, Shanxi University of Finance and Economics, Taiyuan 030006, China;
3. Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing 100101, China;
4. College of Environment and Planning, Henan University, Kaifeng 475001, China

Received:2018-03-01 Revised:2018-07-25 Online:2018-08-25 Published:2018-10-08

摘要/Abstract

摘要： 城市不透水面信息对于城市生态环境动态演化过程研究具有重要意义。以Landsat 8遥感影像为数据源，以呼和浩特市为实证区域，进行了随机森林模型应用于城市不透水面的提取研究，并与目前应用广泛的支持向量机模型进行了对比分析。研究表明：在不同的抽样比例训练样本条件下，随机森林模型对于城市不透水面的提取精度均优于支持向量机的提取精度；对于随机森林模型和支持向量机模型，70%的训练样本比例均为最佳训练样本抽样比例。在该抽样比例下，随机森林模型提取城市不透水面的总体分类精度为93.29%，Kappa系数为0.9051，支持向量机模型的总体分类精度为91.26%，Kappa系数为0.8757；随机森林模型对于城市裸土的识别度较高，能更好地将城市裸土和不透水面进行区分，而支持向量机模型对于城市裸土、不透水面和绿地的区分能力均弱于随机森林模型。综合而言，随机森林模型对城市不透水面的提取精度优于支持向量机模型，随机森林模型可以有效应用于城市不透水面提取领域，进一步丰富了城市不透水面提取方法体系构成。

关键词: 不透水面, 随机森林, Landsat 8, 支持向量机

Abstract: Urban impervious surface information is essential for the research of dynamic evolution of urban ecological environment. In this paper, based on Landsat 8 remote sensing image, taking Hohhot city as a case, the urban impervious surface has been extracted by using random forest model and compared with the widely applicable support vector machine model. The research results showed that (1) the accuracy of the extraction of urban impervious surface by random forest model is better than that of the support vector machine model under the condition of various proportion of sampling training samples; (2) 70% of the proportion of training sample is the most optimal for either random forest model or support vector machine model. On the basis of the most optimal proportion of training sample, the overall classification accuracy of extraction of urban impervious surface with random forest model is 93.29% with a Kappa coefficient of 0.9051. The classification accuracy of the support vector machine model is 91.26% with a Kappa coefficient of 0.8757; (3) the random forest model has a more sensitive recognition to urban bare soil, and can better distinguish the urban bare soil from the impervious surface, while the support vector machine model cannot accurately distinguish the bare soil, impermeable surface and the green space. In short, the random forest model can more effectively and accurately extract urban impervious surface from Landsat 8 image and be applied in the field of extracting urban impervious surface, enriching the method system of extracting urban impervious surface.

Key words: impermeable surface, random forest, Landsat 8, support vector machine

中图分类号:

TP751

郜燕芳, 李俊明, 刘东伟, 任周鹏, 王楠楠. 基于随机森林模型的城市不透水面提取研究——以呼和浩特市为例[J]. 冰川冻土, 2018, 40(4): 828-836.

GAO Yanfang, LI Junming, LIU Dongwei, REN Zhoupeng, WANG Nannan. Research on extraction of urban impervious surface based on random forest model: a case study in Hohhot[J]. JOURNAL OF GLACIOLOGY AND GEOCRYOLOGY, 2018, 40(4): 828-836.

参考文献

[1] Slonecker E, Jennings D, Garofalo D. Remote sensing of impervious surfaces:a review[J]. Remote Sensing Reviews, 2001, 20(3):227-255.
[2] Yang Xiaojun, Liu Zhi. Use of satellite-derived landscape imperviousness index to characterize urban spatial growth[J]. Computers Environment and Urban Systems, 2005, 29(5):524-540.
[3] Weng Qihao, Lu Dengsheng, Schubring J. Estimation of land surface temperature-vegetation abundance relationship for urban heat island studies[J]. Remote Sensing of Environment, 2004, 89(4):467-483.
[4] Lu Dengsheng, Weng Qihao, Li Guiying. Residential population estimation using a remote sensing derived impervious surface approach[J]. International Journal of Remote Sensing, 2006, 27(6):3553-3570.
[5] Azar D, Graesser J, Engstrom R, et al. Spatial refinement of census population distribution using remotely sensed estimates of impervious surfaces in Haiti[J]. International Journal of Remote Sensing, 2010, 31(21):5635-5655.
[6] Ha Shangchen, Alimujiang Kasimu. Analysis of the impact factors of urban heat island effect based on the intensive land use level[J]. Journal of Glaciology and Geocryology, 2016, 38(1):270-278.[哈尚辰, 阿里木江·卡斯木. 基于土地集约利用水平的城市热岛效应影响因子分析[J]. 冰川冻土, 2016, 38(1):270-278.]
[7] Weng Qihao, Hu Xuefei, Lu Dengsheng. Extracting impervious surface from hyper spectral imagery with linear spectral mixture analysis[J]. Remote Sensing of Impervious Surfaces, 2008, 93-118.
[8] Hou Bozhan, Chen Shujiang, Hou Jiannan, et al. Remote sensing study of urban spatial expansion in Kashgar City based on multisource and multi temporal datasets in the last 70 years[J]. Journal of Glaciology and Geocryology, 2016, 38(3):836-844.[侯博展, 陈蜀江, 侯建楠, 等. 基于多源多时相数据集的喀什市近70 a城区空间扩展遥感研究[J]. 冰川冻土, 2016, 38(3):836-844.]
[9] Li Junfeng, Pan Jinghu. Spatial expansion of cities at county-level or above in Gansu Province from 1992 to 2012 based on DMSP nighttime light images[J]. Journal of Glaciology and Geocryology, 2016, 38(3):829-835.[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):829-835.]
[10] Yuan Fei, Wu Changshan, Bauer M. Comparison of spectral analysis techniques for impervious surface estimation using landsat imagery[J]. Photogrammetric Engineering and Remote Sensing, 2008, 74(8):1045-1055.
[11] Weng Qihao, Hu Xuefei. Medium spatial resolution satellite imagery for estimating and mapping urban impervious surfaces using LSMA and ANN[J]. IEEE Transactions on Geoscience and Remote Sensing, 2008, 46(8):2397-2406.
[12] Cheng Xi, Shen Zhanfeng, Luo Jiancheng, et al. Estimating impervious surface base on comparison of spectral mixture analysis and support vector machine methods[J]. Journal of Remote Sensing, 2011, 15(6):1228-1241.[程熙, 沈占锋, 骆剑承, 等. 利用混合光谱分解与SVM估算不透水面覆盖率[J]. 遥感学报, 2011, 15(6):1228-1241.]
[13] Deng Chengbin, Wu Changshan. The use of single-date MODIS imagery for estimating large-scale urban impervious surface fraction with spectral mixture analysis and machine learning techniques[J]. Isprs Journal of Photogrammetry and Remote Sensing, 2013, 86(4):100-110.
[14] Jia Kun, Li Qiangzi, Tian Yichen, et al. A review of classification methods of remote sensing imagery[J]. Spectroscopy and Spectral Analysis, 2011, 31(10):2618-2623.[贾坤, 李强子, 田亦陈, 等. 遥感影像分类方法研究进展[J]. 光谱学与光谱分析, 2011, 31(10):2618-2623.]
[15] Breiman L. Arcing classifier (with discussion and a rejoinder by the author)[J]. Annals of Statistics, 1998, 26(3):801-849.
[16] Boulesteix A, Janitza S, Kruppa J, et al. Overview of random forest methodology and practical guidance with emphasis on computational biology and bioinformatics[J]. Wiley Interdisciplinary Reviews:Data Mining and Knowledge Discovery, 2012, 2(6):493-507.
[17] Hohhot Statistical Bureau. Hohhot economic statistic yearbook[M]. Beijing:China Economic Statistics Press, 2015.[呼和浩特市统计局. 呼和浩特经济统计年鉴[M]. 北京:中国统计出版社, 2015.]
[18] Weng Qihao, Liu Xuefei, Liu Hua. Estimating impervious surfaces using linear spectral mixture analysis with multitemporal ASTER images[J]. International Journal of Remote Sensing, 2009, 30(18):4807-4830.
[19] Breiman L. Random Forests[J]. Machine Learning, 2001, 45(1):5-32.
[20] Breiman L. Bagging predictors[J]. Machine Learning, 1996, 24(2):123-140.
[21] Ho T. The random subspace method for constructing decision forests[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998, 20(8):832-844.
[22] Breiman L, Friedman J, Olshen R, et al. Classification and regression trees (CART)[J]. Encyclopedia of Ecology, 1984, 40(3):582-588.
[23] Chen Chao, Liaw A, Breiman L. Using random forest to learn imbalanced data[R]. Berkeley:University of California, 2004:1-12.
[24] Cortes C, Vapnik V. Support-vector networks[J]. Machine Learning, 1995, 20(3):273-297.
[25] Luo Jiancheng, Zhou Chenghu, Liang Yi, et al. Support vector machine for spatial feature extraction and classification of remotely sensed imagery[J]. Journal of Remote Sensing, 2002, 6(1):50-55.[骆剑承, 周成虎, 梁怡, 等. 支撑向量机及其遥感影像空间特征提取和分类的应用研究[J]. 遥感学报, 2002, 6(1):50-55.]
[26] He Lingmin, Shen Zhangquan, Kong Fansheng, et al. Study on multi-source remote sensing images classification with SVM[J]. Journal of Image and Graphics, 2007, 12(4):649-654.[何灵敏, 沈掌泉, 孔繁胜, 等. SVM在多源遥感图像分类中的应用研究[J]. 中国图象图形学, 2007, 12(4):649-654.]
[27] Shen Xin, Cao Lin, Xu Ting, et al. Classification of Pinus massoniana and secondary deciduous tree species in northern subtropical region based on high resolution and hyperspectral remotely sensed data[J]. Chinese Journal of Plant Ecology, 2015, 39(12):1125-1135.[申鑫, 曹林, 徐婷, 等. 基于高分辨率与高光谱遥感影像的北亚热带马尾松及次生落叶树种的分类[J]. 植物生态学报, 2015, 39(12):1125-1135.]
[28] Chen Yanfeng, Yin Linke, Cao Qiumei, et al. Vegetation information extraction and analysis of Xinjiang Altay Two-River Source Nature Reserve[J]. Arid Land Geography, 2016, 39(4):843-850.[陈艳锋, 尹林克, 曹秋梅, 等. 新疆阿勒泰两河源自然保护区植被信息提取与分析[J]. 干旱区地理, 2016, 39(4):843-850.]
[29] Zheng Pu, Deng Zhengdong, Guan Hongjun, et al. Study of the snow cover extraction method based on ETM+ data:take Manas River basin as an example[J]. Journal of Glaciology and Geocryology, 2014, 36(5):1151-1159.[郑璞, 邓正栋, 关洪军, 等. 基于ETM+的积雪提取方法研究:以新疆玛纳斯河流域为例[J]. 冰川冻土, 2014, 36(5):1151-1159.]
[30] Laba Zhuoma, Qiu Yubao, Cidan Basang, et al. The validation of MODIS daily snow-cover products after cloudremoval in Tibet Autonomous Region[J]. Journal of Glaciology and Geocryology, 2016, 38(1):159-169.[拉巴卓玛, 邱玉宝, 次旦巴桑, 等. 西藏高原MODIS每日积雪产品去云算法过程对比验证研究[J]. 冰川冻土, 2016, 38(1):159-169.]
[31] Carlson T, Arthur S. The impact of land use-land cover changes due to urbanization on surface microclimate and hydrology:a satellite perspective[J]. Global & Planetary Change, 2000, 25(1/2):49-65.
[32] Song Junwei, Zhang Youjing, Li Xinchuan, et al. Comparison between GF-1 and Landsat-8 images in land cover classification[J]. Progress in Geography, 2016, 35(2):255-263.[宋军伟, 张友静, 李鑫川, 等. 基于GF-1与Landsat-8影像的土地覆盖分类比较[J]. 地理科学进展, 2016, 35(2):255-263.]

基于随机森林模型的城市不透水面提取研究——以呼和浩特市为例

Research on extraction of urban impervious surface based on random forest model: a case study in Hohhot

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 2

Metrics

本文评价

推荐阅读 0

[1]	金学杰, 周剑. 基于SEBS模型和Landsat 8数据的黑河下游蒸散发时空特性分析[J]. 冰川冻土, 2017, 39(3): 572-582.
[2]	郭淑海, 杨国靖, 李清峰, 赵传成. 新疆阿克苏河上游高寒草甸蒸散发观测与估算[J]. 冰川冻土, 2015, 37(1): 241-248.