HU Deyong, CHEN Shanshan, QIAO Kun, CAO Shisong. Integrating CART Algorithm and Multi-source Remote Sensing Data to Estimate Sub-pixel Impervious Surface Coverage: A Case Study from Beijing Municipality, China[J]. Chinese Geographical Science, 2017, 27(4): 614-625. doi: 10.1007/s11769-017-0882-x
Citation: HU Deyong, CHEN Shanshan, QIAO Kun, CAO Shisong. Integrating CART Algorithm and Multi-source Remote Sensing Data to Estimate Sub-pixel Impervious Surface Coverage: A Case Study from Beijing Municipality, China[J]. Chinese Geographical Science, 2017, 27(4): 614-625. doi: 10.1007/s11769-017-0882-x

Integrating CART Algorithm and Multi-source Remote Sensing Data to Estimate Sub-pixel Impervious Surface Coverage: A Case Study from Beijing Municipality, China

doi: 10.1007/s11769-017-0882-x
Funds:  Under the auspices of National Natural Science Foundation of China (No. 41671339)
More Information
  • Corresponding author: CHEN Shanshan.E-mail:amchenshanshan@163.com
  • Received Date: 2016-05-02
  • Rev Recd Date: 2016-09-01
  • Publish Date: 2017-08-27
  • The sub-pixel impervious surface percentage (SPIS) is the fraction of impervious surface area in one pixel, and it is an important indicator of urbanization. Using remote sensing data, the spatial distribution of SPIS values over large areas can be extracted, and these data are significant for studies of urban climate, environment and hydrology. To develop a stabilized, multi-temporal SPIS estimation method suitable for typical temperate semi-arid climate zones with distinct seasons, an optimal model for estimating SPIS values within Beijing Municipality was built that is based on the classification and regression tree (CART) algorithm. First, models with different input variables for SPIS estimation were built by integrating multi-source remote sensing data with other auxiliary data. The optimal model was selected through the analysis and comparison of the assessed accuracy of these models. Subsequently, multi-temporal SPIS mapping was carried out based on the optimal model. The results are as follows: 1) multi-seasonal images and nighttime light (NTL) data are the optimal input variables for SPIS estimation within Beijing Municipality, where the intra-annual variability in vegetation is distinct. The different spectral characteristics in the cultivated land caused by the different farming characteristics and vegetation phenology can be detected by the multi-seasonal images effectively. NLT data can effectively reduce the misestimation caused by the spectral similarity between bare land and impervious surfaces. After testing, the SPIS modeling correlation coefficient (r) is approximately 0.86, the average error (AE) is approximately 12.8%, and the relative error (RE) is approximately 0.39. 2) The SPIS results have been divided into areas with high-density impervious cover (70%-100%), medium-density impervious cover (40%-70%), low-density impervious cover (10%-40%) and natural cover (0%-10%). The SPIS model performed better in estimating values for high-density urban areas than other categories. 3) Multi-temporal SPIS mapping (1991-2016) was conducted based on the optimized SPIS results for 2005. After testing, AE ranges from 12.7% to 15.2%, RE ranges from 0.39 to 0.46, and r ranges from 0.81 to 0.86. It is demonstrated that the proposed approach for estimating sub-pixel level impervious surface by integrating the CART algorithm and multi-source remote sensing data is feasible and suitable for multi-temporal SPIS mapping of areas with distinct intra-annual variability in vegetation.
  • [1] Arnold Jr C L, Gibbons C J, 1996. Impervious surface coverage: the emergence of a key environmental indicator. Journal of the American Planning Association, 62(2): 243-258. doi: 10.1080/01944369608975688
    [2] Breiman L, Friedman J, Olshen R, 1984. Classification and Regression Tree. New York: Chapman and Hall.
    [3] Cao Liqin, Li Pingxiang, Zhang Liangpei et al., 2012. Estimating impervious surfaces using the fuzzy ARTMAP. Geomatics and Information Science of Wuhan University, 37(10): 1236-1239. (in Chinese)
    [4] Friedl M A, Brodley C E, Strahler A H, 1999. Maximizing land cover classification accuracies produced by decision trees at continental to global scales. IEEE Trans on Geoscience and Remote Sensing, 37(2): 969-977. doi: 10.1109/36.752215
    [5] Gao Zhihong, Zhang Lu, Li Xinyan et al., 2010. Detection and analysis of urban land use changes through multi-temporal impervious surface mapping. Journal of Remote Sensing, 14(3): 593-606. (in Chinese)
    [6] Homer C, Dewitz J, Yang L et al., 2015. Completion of the 2011 national land cover database for the conterminous United States representing a decade of land cover change information. Photogrammetric Engineering and Remote Sensing, 81(5): 346-354. doi: 10.14358/PERS.81.5.345
    [7] Huang C, Townshend J R G, 2003. A stepwise regression tree for nonlinear approximation: applications to estimating subpixel land cover. International Journal of Remote Sensing, 24(1): 75-90. doi: 10.1080/01431160110115032
    [8] Imhoff M L, Zhang Ping, Wolfe R E et al., 2010. Remote sensing of the urban heat island effect across biomes in the continental USA. Remote Sensing of Environment, 114(3): 504-513. doi: 10.1016/j.rse.2009.10.008
    [9] Jiang Liming, Liao Mingsheng, Lin Hui et al., 2008. Estimating urban impervious surface percentage with ERS-1/2 InSAR data. Journal of Remote Sensing, 12(1): 176-185. (in Chinese)
    [10] Jin H, Mountrakis G, 2013. Integration of urban growth modelling products with image-based urban change analysis. International Journal of Remote Sensing, 34(15): 5468-5486. doi: 10.1080/01431161.2013.791760
    [11] Lawrence R, Bunn A, Powell S, 2004. Classification of remotely sensed imagery using stochastic gradient boosting as a refinement of classification tree analysis. Remote Sensing of Environment, 90(3): 331-336. doi: 10.1016/j.rse.2004.01.007
    [12] Li J X, Song C H, Cao L et al., 2011. Impacts of landscape structure on surface urban heat islands: a case study of Shanghai, China. Remote Sensing of Environment, 115(12): 3249-3263. doi: 10.1016/j.rse.2011.07.008
    [13] Li Qian, Li Caili, Rui Hanyi et al., 2010. Estimate of impervious surface percent based on different brightness of cart method with remote sensing images. Water Resources and Power, (12): 45-48. (in Chinese)
    [14] Li Xiaoning, Zhang Youjing, She Yuanjian et al., 2013. Estimation of impervious surface percentage of river network regions using an ensemble leaning of CART analysis. Remote Sensing for Land and Resources, 25(4): 174-179. (in Chinese)
    [15] Liu Y H, Niu Z, Wang C Y, 2005. Research and application of the decision tree classification using MODIS data. Journal of Remote Sensing, 9(4): 405-411. doi: 10.11834/jrs.20050459
    [16] Ma Q, He C, Wu J et al., 2014. Quantifying spatiotemporal patterns of urban impervious surfaces in China: an improved assessment using nighttime light data. Landscape and Urban Planning, 130(4): 36-49. doi:10.1016/j.landurbplan.2014. 06.009
    [17] Michie D, Spiegelhalter D J, Taylor C C, 1994. Machine Learning, Neural and Statistical Classification. New York: Ellis Horwood.
    [18] Patel N, Mukherjee R, 2014. Extraction of impervious features from spectral indices using artificial neural network. Arabian Journal of Geosciences, 8(6): 3729-3741. doi:10.1007/s 12517-014-1492-x
    [19] Sanbum L, Lathrop R G, 2006. Subpixel analysis of Landsat ETM/sup+using self-organizing map (SOM) neural networks for urban land cover characterization. IEEE Transactions on Geoscience and Remote Sensing, 44(6): 1642-1654. doi: 10.1109/TGRS.2006.869984
    [20] Su Y, Chen X, Wang C, et al., 2015. A new method for extracting built-up urban areas using DMSP-OLS nighttime stable lights: a case study in the Pearl River Delta, southern China. Giscience and Remote Sensing, 52(2): 218-238. doi: 10.1080/15481603.2015.1007778
    [21] Wang H, Wu B F, Li X S, 2011. Extraction of impervious surface in Hai Basin using remote sensing. Journal of Remote Sensing, 15(2): 388-400. doi: 10.11834/jrs.20110288
    [22] Weng Q, 2012. Remote sensing of impervious surfaces in the urban areas: requirements, methods, and trends. Remote Sensing of Environment, 117(2): 34-49. doi: 10.1016/j.rse.2011.02.030
    [23] Wu C, Murray A T, 2003. Estimating impervious surface distribution by spectral mixture analysis. Remote Sensing of Environment, 84(23): 493-505. doi:10.1016/S0034-4257 (02)00136-0
    [24] Xian G, Crane M, 2005. Assessments of urban growth in the Tampa Bay watershed using remote sensing data. Remote Sensing of Environment, 97(22): 203-215. doi:10.1016/j.rse. 2005.04.017
    [25] Xiao Rongbo, Ouyang Zhiyun, Cai Yunnan, 2007. Urban landscape pattern study based on sub-pixel estimation of impervious surface. Acta Ecologica Sinica, 27(8): 3189-3197. (in Chinese)
    [26] Yang L M, Jiang L M, Lin H et al., 2009. Quantifying sub-pixel urban impervious surface through fusion of optical and InSAR imagery. Giscience and Remote Sensing, 46(2): 161-171. doi: 10.2747/1548-1603.46.2.161
    [27] Yang L, Huang C, Homer C G et al., 2003. An approach for mapping large-area impervious surfaces: synergistic use of Landsat-7 ETM+ and high spatial resolution imagery. Canadian Journal of Remote Sensing, 29(2): 230-240. doi: 10.5589/m02-098
    [28] Yang X, 2006. Estimating landscape imperviousness index from satellite imagery. IEEE Geosience and Remote Sensing Letters, 3(1): 6-9. doi: 10.1109/LGRS.2005.853929
    [29] Zhang L, Weng Q, 2016. Annual dynamics of impervious surface in the Pearl River Delta, China, from 1988 to 2013, using time series Landsat imagery. Isprs Journal of Photogrammetry and Remote Sensing, 113(3): 86-96. doi:10.1016/j.isprsjprs.2016. 01.003
    [30] Zhang Lu, Gao Zhihong, Liao Mingsheng et al., 2010. Estimating urban impervious surface percentage with multi-source remote sensing data. Geomatics and Information Science of Wuhan University, 35(10): 1212-1216. (in Chinese)
    [31] Zhou J, Chen Y H, Zhang X et al., 2013. Modelling the diurnal variations of urban heat islands with multi-source satellite data. International Journal of Remote Sensing, 34(21): 7568-7588. doi: 10.1080/01431161.2013.821576
    [32] Zhou Ji, Chen Yunhao, Zhang Jinshui et al., 2007. Urban impervious surface abundance estimation in Beijing based on remote sensing. Remote Sensing for Land and Resources, 19(3): 13-17. (in Chinese)
  • 加载中
通讯作者: 陈斌, bchen63@163.com
  • 1. 

    沈阳化工大学材料科学与工程学院 沈阳 110142

  1. 本站搜索
  2. 百度学术搜索
  3. 万方数据库搜索
  4. CNKI搜索

Article Metrics

Article views(317) PDF downloads(846) Cited by()

Proportional views
Related

Integrating CART Algorithm and Multi-source Remote Sensing Data to Estimate Sub-pixel Impervious Surface Coverage: A Case Study from Beijing Municipality, China

doi: 10.1007/s11769-017-0882-x
Funds:  Under the auspices of National Natural Science Foundation of China (No. 41671339)
    Corresponding author: CHEN Shanshan.E-mail:amchenshanshan@163.com

Abstract: The sub-pixel impervious surface percentage (SPIS) is the fraction of impervious surface area in one pixel, and it is an important indicator of urbanization. Using remote sensing data, the spatial distribution of SPIS values over large areas can be extracted, and these data are significant for studies of urban climate, environment and hydrology. To develop a stabilized, multi-temporal SPIS estimation method suitable for typical temperate semi-arid climate zones with distinct seasons, an optimal model for estimating SPIS values within Beijing Municipality was built that is based on the classification and regression tree (CART) algorithm. First, models with different input variables for SPIS estimation were built by integrating multi-source remote sensing data with other auxiliary data. The optimal model was selected through the analysis and comparison of the assessed accuracy of these models. Subsequently, multi-temporal SPIS mapping was carried out based on the optimal model. The results are as follows: 1) multi-seasonal images and nighttime light (NTL) data are the optimal input variables for SPIS estimation within Beijing Municipality, where the intra-annual variability in vegetation is distinct. The different spectral characteristics in the cultivated land caused by the different farming characteristics and vegetation phenology can be detected by the multi-seasonal images effectively. NLT data can effectively reduce the misestimation caused by the spectral similarity between bare land and impervious surfaces. After testing, the SPIS modeling correlation coefficient (r) is approximately 0.86, the average error (AE) is approximately 12.8%, and the relative error (RE) is approximately 0.39. 2) The SPIS results have been divided into areas with high-density impervious cover (70%-100%), medium-density impervious cover (40%-70%), low-density impervious cover (10%-40%) and natural cover (0%-10%). The SPIS model performed better in estimating values for high-density urban areas than other categories. 3) Multi-temporal SPIS mapping (1991-2016) was conducted based on the optimized SPIS results for 2005. After testing, AE ranges from 12.7% to 15.2%, RE ranges from 0.39 to 0.46, and r ranges from 0.81 to 0.86. It is demonstrated that the proposed approach for estimating sub-pixel level impervious surface by integrating the CART algorithm and multi-source remote sensing data is feasible and suitable for multi-temporal SPIS mapping of areas with distinct intra-annual variability in vegetation.

HU Deyong, CHEN Shanshan, QIAO Kun, CAO Shisong. Integrating CART Algorithm and Multi-source Remote Sensing Data to Estimate Sub-pixel Impervious Surface Coverage: A Case Study from Beijing Municipality, China[J]. Chinese Geographical Science, 2017, 27(4): 614-625. doi: 10.1007/s11769-017-0882-x
Citation: HU Deyong, CHEN Shanshan, QIAO Kun, CAO Shisong. Integrating CART Algorithm and Multi-source Remote Sensing Data to Estimate Sub-pixel Impervious Surface Coverage: A Case Study from Beijing Municipality, China[J]. Chinese Geographical Science, 2017, 27(4): 614-625. doi: 10.1007/s11769-017-0882-x
Reference (32)

Catalog

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return