基于Google Earth Engine的环渤海地区土地覆盖分类

doi:10.13287/j.1001-9332.202012.014

摘要/Abstract

摘要： 环渤海地区由于城市和经济发展,导致土地覆盖快速变化,对其进行高精度实时的变化监测是相关研究的重要基础。传统单机处理模式难以进行大尺度和长时间序列的快速监测,而整合海量数据的遥感大数据云计算平台的出现使其成为可能。本研究基于Google Earth Engine(GEE)处理平台,采用决策树(CART)方法对研究区2000—2019年土地覆盖进行解译分类,并综合分析研究区土地覆盖变化及对比不同数据源解译结果。结果表明: 基于GEE平台能够实现大区域快速土地覆盖分类,对沿海湿地和其他覆盖类型具有较高的分类精度,与实测点对比达到80%以上。相较于Landsat影像,基于Sentinel-2A影像的解译结果在精度上有较大的提高,总体分类精度从85%提高到95%,地表更多细节信息得到体现。2000年,研究区湿地、建设用地、耕地、林地和水体的面积分别为1612.5、5734.9、32074.8、11853、3504.3 km²,分别占总面积的2.9%、10.5%、58.6%、21.6%、6.4%。到2019年,湿地减少了775.1 km²,下降40.1%;建设用地增加5310.5 km²,增加了92.6%;耕地、林地和水体分别下降了1841.6、1823.5、870.3 km²,分别下降5.7%、24.8%、48.1%。说明沿海的城市化过程导致建设用地占用其他类型,是研究区土地覆盖变化的最主要驱动力。

关键词: Google earth engine, Sentinel-2A影像, 土地覆盖, 湿地提取, CART分类

Abstract: The land cover of Bohai Rim region has changed greatly due to urbanization and economic development. Monitoring the land cover with high accuracy and real time is the most important basis for relevant researches. Traditional single-machine processing mode is difficult to realize rapid monitoring for large-scale and long-time series. The emergence of remote sensing big data makes it possible to combine computing platform and massive data. The land cover maps of study area were interpreted based on Google Earth Engine (GEE) platform with decision tree (CART) method from 2000 to 2019. The land cover change was analyzed, and the interpretation results using different data sources were compared. The results showed that the GEE platform could realize the rapid land cover interpretation in a large area, which interpreted coastal wetlands and other cover types with high accuracy over 80% comparing the surveyed points. Compared with Landsat images, the Sentinel-2A images interpretation results had a great improvement in accuracy, which increased from 85% to 95%, and thus more detailed surface information could be reflected. In 2000, the area of wetland, build-up area, farmland, forest, and water in the study area were 1612.5, 5734.9, 32074.8, 11853 and 3504.3 km², accounting for 2.9%, 10.5%, 58.6%, 21.6% and 6.4% respectively. By 2019, wetlands had been reduced by 775.1 km², with a decline of 40.1%; built-up area increased by 5310.5 km² with an increasing rate of 92.6%. The area of farmland, forestland and water area decreased 1841.6, 1823.5 and 870.3 km², with a decreasing rate of 5.7%, 24.8% and 48.1%, respectively. The coastal urbanization process caused the occupation of built-up area to other land use types, which was the main driving force of land cover change in the study area.

Key words: Google Earth Engine, Sentinel-2A image, land-cover, wetland extraction, CART classification.

于莉莉, 孙立双, 张丹华, 刘淼, 谢志伟, 平晓莹. 基于Google Earth Engine的环渤海地区土地覆盖分类[J]. 应用生态学报, 2020, 31(12): 4091-4098.

YU Li-li, SUN Li-shuang, ZHANG Dan-hua, LIU Miao, XIE Zhi-wei, PING Xiao-ying. Extraction of land-cover and wetland area in Bohai Rim region based on Google Earth Engine.[J]. Chinese Journal of Applied Ecology, 2020, 31(12): 4091-4098.

参考文献

[1] Schneider A, Friedl MA, Potere D. Mapping global urban areas using MODIS 500-m data: New methods and datasets based on ‘Urban Ecoregions'. Remote Sensing of Environment, 2010, 114: 1733-1746
[2] Cheng QL, Lou GY, Huang WH, et al. Assessment and potential sources of metals in the surface sediments of the Yellow River Delta, Eastern China. Environmental Science and Pollution Research, 2017, 24: 17446-17454
[3] 廖华军, 李国胜, 王少华, 等. 近30年苏北滨海滩涂湿地演变特征与空间格局. 地理科学进展, 2014, 33(9): 1209-1217 [Liao H-J, Li G-S, Wang S-H, et al. Evolution and spatial patterns of tidal wetland in North Jiangsu Province in the past 30 years. Progress in Geo-graphy, 2014, 33(9): 1209-1217]
[4] 柳海鹰, 高吉喜, 李政海. 土地覆盖及土地利用遥感研究进展. 国土资源遥感, 2001, 13(4): 7-12 [Liu H-Y, Gao J-X, Li Z-H. The advances in the application of remote sensing technology to the study of land covering and land utilization. Remote Sensing for Land & Resources, 2001, 13(4): 7-12]
[5] Noam L, Cheristopher CMK, Zhang QL, et al. Remote sensing of night Lights: A review and an outlook for the future. Remote Sensing of Environment, 2020, 237: 111443
[6] 王圆圆, 李京. 遥感影像土地利用/覆盖分类方法研究综述. 遥感信息, 2004(1): 53-59 [Wang Y-Y, Li J. Classification methods of land use/cover based on remote sensing technology. Remote Sensing Information, 2004(1): 53-59]
[7] 李爽, 丁圣彦, 钱乐祥. 决策树分类法及其在土地覆盖分类中的应用. 遥感技术与应用, 2002, 17(1): 6-11 [Li S, Ding S-Y, Qian L-X. The decision tree classification and its application research in land cover. Remote Sensing Technology and Application, 2002, 17(1): 6-11]
[8] 李彤, 吴骅. 采用决策树分类技术对北京市土地覆盖现状进行研究. 遥感技术与应用, 2004, 19(6): 485-487 [Li T, Wu Y. Application of decision tree classification to Peking land cover. Remote Sensing Technology and Application, 2004, 19(6): 485-487]
[9] Torbick N, Ledoux L, Salas W, et al. Regional mapping of plantation extent using multisensor imagery. Remote Sensing, 2016, 8: 236
[10] 赵萍, 傅云飞, 郑刘根, 等. 基于分类回归树分析的遥感影像土地利用/覆被分类研究. 遥感学报, 2005, 9(6): 708-716 [Zhao P, Fu Y-F, Zheng L-G, et al. Cart-based land use/cover classification of remote sen-sing images. Journal of Remote Sensing, 2005, 9(6): 708-716]
[11] 娄佩卿, 付波霖, 林星辰, 等. 基于GEE的1998—2018年京津冀土地利用变化对生态系统服务价值的影响. 环境科学, 2019, 40(12): 291-298 [Lou P-Q, Fu B-L, Lin X-C, et al. Influence of land use change on ecosystem service value based on GEE in the Beijing-Tianjin-Hebei Region from 1998 to 2018. Environmental Science, 2019, 40(12): 291-298]
[12] Pekel JF, Cottam A, Gorelick N, et al. High-resolution mapping of global surface water and its long-term changes. Nature, 2016, 540: 418-422
[13] Yamazaki D, Trigg MA. The dynamics of earth's surface water. Nature, 2016, 540: 348-349
[14] DeLancey ER, Kariyeva J, Cranston J, et al. Monitoring hydro temporal variability in Alberta, Canada with multi-temporal Sentinel-1 SAR Data. Canadian Journal of Remote Sensing, 2017, 44: 1-10
[15] 罗丽艳, 张甜甜. 环渤海区域环境与可持续发展. 城市, 2010(3): 31-35 [Luo L-Y, Zhang T-T. The regional environment around Bohai Rim and the sustaina-ble development. City, 2010(3): 31-35]
[16] 朱会义, 李秀彬, 何书金, 等. 环渤海地区土地利用的时空变化分析. 地理学报, 2001, 56(3): 253-260 [Zhu H-Y, Li X-B, He S-J, et al. Spatio-temporal change of land use in Bohai Rim. Acta Geographica Sinica, 2001, 56(3): 253-260]
[17] 王丰, 刘书明, 卢文虎, 等. 基于遥感的天津滨海新区土地利用/覆盖变化分析. 海洋通报, 2014, 33(6): 683-690 [Wang F, Liu S-M, Lu W-H, et al. Analysis on the land use and cover change in Tianjin Binhai new area based on the remote sensing. Marine Science Bulletin, 2014, 33(6): 683-690]
[18] Nirav NP, Emanuele A, Paolo G, et al. Multitemporal settlement and population mapping from Landsat using Google Earth Engine. International Journal of Applied Earth Observation and Geoinformation, 2015, 35: 199-208
[19] 王献溥. 《1∶1000000中国植被图集》问世 [EB/OL]. (2019-12-12) [2020-01-03]. https://xueshu.baidu.com/usercenter/paper/show?paperid=797e26-cd932d9b1ad669d121f382ae89&site=xueshu_se [Wang X-B. The 1:1000000 Vegetation Atlas of China was Published [EB/OL]. (2019-12-12) [2020-01-03]. https://xueshu.baidu.com/usercenter/paper/show?paperid=797e26cd932d9b1ad669d121f382ae89&site=xueshu_se]
[20] 陈百明, 周小萍. 《土地利用现状分类》国家标准的解读. 自然资源学报, 2007, 22(6): 994-1003 [Chen B-M, Zhou X-P. Explanation of current land use condition classification for national standard of the People's Republic of China. Journal of Natural Resources, 2007, 22(6): 994-1003]
[21] Wang XX , Xiao XM, Zou ZH, et al. Tracking annual changes of coastal tidal flats in China during 1986-2016 through analyses of Landsat images with Google Earth Engine. Remote Sensing of Environment, 2020, 238: 110987
[22] Xiao XM, Zhang QY, Bobby B, et al. Modeling gross primary production of temperate deciduous broadleaf forest using satellite images and climate data. Remote Sensing of Environment, 2004, 91: 256-270
[23] 胡云锋, 商令杰, 王召海, 等. GEE平台和CART方法的北京市土地解译. 测绘科学, 2018, 43(4): 87-93 [Hu Y-F, Shang L-J, Wang Z-H, et al. Land-cover and land-use classification in Beijing based in CART and GEE. Science of Surveying and Mapping, 2018, 43(4): 87-93]
[24] 陈炜, 黄慧萍, 田亦陈, 等. 基于Google Earth Engine平台的三江源地区生态环境质量动态监测与分析. 地球信息科学学报, 2019, 21(9): 1382-1391 [Chen W, Huang H-P, Tian Y-C, et al. Monitoring and assessment of the eco-environment quality in the Sanjiangyuan region based on Google Earth Engine. Journal of Geo-information Science, 2019, 21(9): 1382-1391]
[25] 张滔, 唐宏. 基于Google earth engine的京津冀2001—2015年植被覆盖变化与城镇扩张研究. 遥感技术与应用, 2018, 33(4): 593-599 [Zhang T, Tang H. Vegetation cover change and urban expansion in Beijing-Tianjin-Hebei during 2001-2015 based on Google Earth Engine. Remote Sensing Technology and Application, 2018, 33(4): 593-599]
[26] 温庆可, 张增祥, 徐进勇, 等. 环渤海滨海湿地时空格局变化遥感监测与分析. 遥感学报, 2011, 15(1): 183-200 [Wen Q-K, Zhang Z-X, Xu J-Y, et al. Spatial and temporal change of wetlands in Bohai Rim during 2000-2008: An analysis based on satellite images. Journal of Remote Sensing, 2011, 15(1): 183-200]
[27] 韩忠亮, 朱敏. 中国区域经济发展战略研究——环渤海经济圈发展研究报告. 新经济导刊, 2009(7): 87-95 [Han Z-L, Zhu M. Research on China's Regional economic development strategy: Report on the development of Bohai Rim economic Circle. New Economy Weekly, 2009(7): 87-95]
[28] 魏帆, 韩广轩, 韩美, 等. 1980—2017年环渤海海岸线和围填海时空演变及其影响机制. 地理科学, 2019, 39(6): 997-1007 [Wei F, Han G-X, Han M, et al. Temporal-spatial dynamic evolution and mechanism of shoreline and the sea reclamation in the Bohai Rim during 1980-2017. Scientia Geographica Sinica, 2019, 39(6): 997-1007]
[29] 常雄凯, 刘淼, 李春林, 等. 辽宁沿海土地利用变化的图谱特征. 生态学杂志, 2015, 34(12):3459-3465 [Chang X-K, Liu M, Li C-L, et al. Geo-spectrum cha-racteristics of land use change in Liaoning coastal areas. Chinese Journal of Ecology, 2015, 34(12): 3459-3465]
[30] 陈耀, 叶振宇, 郑鑫. 我国环渤海地区的人口流动关于协调经济发展. 当代经济管理, 2010, 32(5): 53-57 [Chen Y, Ye Z-Y, Zheng X. On Harmonious deve-lopment between regional floating population and social economy. Contemporary Economy & Management, 2010, 32(5): 53-57]
[31] Emanuele M, Gabriele B. Preliminary comparison of Sentinel-2 and Landsat 8 imagery for a combined use. Remote Sensing, 2016, 8: 1014
[32] Liu XP, Hu GH, Chen YM. High-resolution multi-temporal mapping of global urban land using Landsat images based on the Google Earth Engine platform. Remote Sen-sing of Environment, 2018, 209: 227-239
[33] 申丹, 常禹, 胡远满, 等. 辽宁沿海地区景观格局变化及驱动力分析. 江西农业大学学报, 2015, 37(5): 874-884 [Shen D, Chang Y, Hu Y-M, et al. Landscape pattern change and its driving forces in Liaoning coastal areas. Acta Agriculturae Universitatis Jiangxiensis, 2015, 37(5): 874-884]
[34] 孟梦, 田海峰, 邬明权, 等. 基于Google Earth Engine平台的湿地景观空间格局演变分析: 以白洋淀为例. 云南大学学报:自然科学版, 2019, 41(2): 416-424 [Meng M, Tian H-F, Wu M-Q, et al. Evolution characteristics analysis of wetland landscape pattern based on Google Earth Engine platform: A case study on Baiyangdian. Journal of Yunnan University: Natural Sciences, 2019, 41(2): 416-424]