佟金萍,张涵玥,刘辉,黄晶,郝亚

• 1:常州大学商学院
• 2:河海大学管理科学研究所
• 3:河海大学商学院

摘要(Abstract)：

随着全球变暖日益严重,极端气候现象频发。面对内涝灾害,城市社会经济呈现高脆弱性,有效评估城市内涝风险成为城市建设和区域可持续发展的迫切要求。以三座长三角核心城市,即上海市、南京市和杭州市为研究区,通过社交媒体数据获取积水样本数据,从气象、地形和社会经济三方面选取评价指标,构建基于极端梯度提升(XGBoost)的城市内涝风险评估模型,在评估长三角核心城市内涝风险等级的基础上分析影响城市内涝的主要因素。结果表明:(1)运用XGBoost进行城市内涝灾害风险研究,其预测性能和预测精度优于其他常用机器学习模型;(2)从城市内涝风险分布来看,三个城市的内涝风险均呈现较高的空间异质性,主城区多为内涝高风险,周边新城区多为内涝低风险区,城市内涝风险等级呈现由中心城区向周围扩散的趋势,靠近河流、长江入海口处以及河网高密度区内涝风险也较高;(3)就影响因素而言,高程是影响研究区内涝风险的首要因素,道路分布和强降雨为影响上海城市内涝高风险地区的次级因素,受人为影响的地表覆盖是导致南京和杭州城市内涝高风险地区的次级因素。

关键词(KeyWords)： 城市内涝;机器学习模型;XGBoost模型;风险评估;降雨

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金重点项目(91846203);; 2020年江苏省研究生科研与实践创新计划项目(KYCX20_2619,KYCX20_2620);; 2018年高校“青蓝工程”中青年学术带头人培养资助项目(苏教师[2018] 12号);; 2020年江苏省“紫金文化人才工程”项目(苏宣干[2020] 96号)

作者(Author): 佟金萍,张涵玥,刘辉,黄晶,郝亚

DOI: 10.13928/j.cnki.wrahe.2021.10.001

参考文献(References)：

• [1] 上海市统计局.上海统计年鉴[M].北京：中国统计出版社，2020.Shanghai Municipal Bureau of Statistics.Shanghai Statistical Yearbook[M].Beijing:China Statistics Press,2020.
• [2] 江苏省统计局.江苏统计年鉴[M].北京：中国统计出版社，2020.Jiangsu Municipal Bureau of Statistics.Jiangsu Statistical Yearbook[M].Beijing:China Statistics Press,2020.
• [3] 浙江省统计局.浙江统计年鉴[M].北京：中国统计出版社，2020.Zhejiang Municipal Bureau of Statistics.Zhejiang Statistical Yearbook[M].Beijing:China Statistics Press,2020.
• [4] 张建云，王银堂，贺瑞敏，等.中国城市内涝问题及成因分析[J].水科学进展，2016,27(4):485-491.ZHANG J Y,WANG Y T,HE R M,et al.Discussion on the urban flood and waterlogging and causes analysis in China[J].Advances in Water Science,2016,27(4):485-491.
• [5] 高峰，刘鹏，黄超然.基于系统思考的武汉市内涝成因分析及对策[J].灾害学，2017,32(3):101-106.GAO F,LIU P,HUANG C R.Analysis and responses of the waterlogging in Wuhan City based on system thinking[J].Journal of Catastrophology,2017,32(3):101-106.
• [6] 杨佩国，靳京，赵东升，等.基于历史暴雨洪涝灾情数据的城市脆弱性定量研究：以北京市为例[J].地理科学，2016,36(5):733-741.YANG P G,JIN J,ZHAO D S,et al.An urban vulnerability study based on historical flood data:a case study of Beijing[J].Scientia Geographica Sinica,2016,36(5):733-741.
• [7] 陆海明，邹鹰，孙金华，等.基于SWMM的铁心桥实验基地内涝防治效果模拟[J].水资源保护，2020,36(1):58-65.LU H M,ZHOU Y,SUN J H,et al.Simulation of waterlogging control effect in Tiexinqiao experimental base based on SWMM[J].Water Resources Protection,2020,36(1):58-65.
• [8] 权瑞松.多情景视角的上海中心城区地铁暴雨内涝暴露性分析[J].地理科学，2015,35(4):471-475.QUAN R S.Exposure analysis of rainstorm waterlogging on subway in central urban area of Shanghai based on multiple scenario perspective[J].Scientia Geographica Sinica,2015,35(4):471-475.
• [9] 陈军飞，李倩，邓梦华，等.基于随机森林与可变模糊集的城市洪涝脆弱性评估[J].长江流域资源与环境，2020,29(11):2551-2562.CHEN J F,LI Q,DENG M H,et al.Urban flood vulnerability assessment based on random forests and variable fuzzy sets[J].Resources and Environment in the Yangtze Basin,2020,29(11):2551-2562.
• [10] 黄国如，罗海婉，卢鑫祥，等.城市洪涝灾害风险分析与区划方法综述[J].水资源保护，2020,36(6):1-6.HUANG G R,LUO H W,LU X X,et al.Study on risk analysis and zoning method of urban flood disaster[J].Water Resources Protection,2020,36(6):1-6.
• [11] MILAD J,ELHAM K L,SOBRI H,et al.Application of SVM and SWAT models for monthly streamflow prediction,a case study in South of Iran[J].KSCE Journal of Civil Engineering,2014,19:345-357.
• [12] HAMID D,BAHRAM C,OMID R,et al.Urban flood risk mapping using the GARP and QUEST models:a comparative study of machine learning techniques[J].Journal of Hydrology,2019,569:142-154.
• [13] ZHAO G,PANG B,XU Z,et al.Mapping flood susceptibility in mountainous areas on a national scale in China[J].Science of the Total Environment,2018,615(15):1133-1142.
• [14] 黄华兵，王先伟，柳林.城市暴雨内涝综述：特征、机理、数据与方法[J].地理科学进展，2021,40(6):1048-1059.HUANG H B,WANG X W,LIU L.A review on urban pluvial floods:characteristics,mechanisms,data,and research methods[J].Progress in Geography,2021,40(6):1048-1059.
• [15] JI S W,WANG X J,ZHAO W P,et al.An application of a three-stage XGBoost-based model to sales forecasting of a cross-border e-commerce enterprise[J].Mathematical Problems in Engineering,2019.
• [16] 中华人民共和国水利部.2016年中国水旱灾害公报[M].北京：中国水利水电出版社，2016.Ministry of Water Resources of the People′s Republic of China.Bulletin of Flood and Drought Disasters in Chins[M].Beijing:China Water Resources and Hydropower Press,2016.
• [17] YU H,ZHAO Y,FU Y,et al.Spatiotemporal variance assessment of urban rainstorm waterlogging affected by impervious surface expansion:a case study of Guangzhou,China[J].Sustainability,2018,10(10):3761.
• [18] ZHANG H,WU C,CHEN W,et al.Assessing the impact of climate change on the waterlogging risk in coastal cities:a case study of Guangzhou,South China[J].Journal of Hydrometeorology,2017,18(6):1549-1562.
• [19] 尹占娥，许世远，殷杰，等.基于小尺度的城市暴雨内涝灾害情景模拟与风险评估[J].地理学报，2010,65(5):553-562.YIN Z E,XU S Y,YIN J.Small-scale based scenario modeling and disaster risk assessment of urban rainstorm water-logging[J].Acta Geographica Sinica,2010,65(5):553-562.
• [20] 王玉鑫，曾燕，邱新法，等.土地利用变化对城市积涝的影响研究：以南京市浦口区为例[J].气象科学，2017,37(2):231-238.WANG Y X,ZENG Y,QIU X F,et al.Impact of land use change on urban waterlogging:case of Nanjing Pukou[J].Journal of the Meteorological Sciences,2017,37(2):231-238.
• [21] 王光朋，刘连友，胡子瑛.京津冀都市圈格网尺度洪涝灾害风险评价研究[J].灾害学，2020,35(3):186-193.WANG G M,LIU L Y,HU Z Y.Risk assessment of rainstorm and flood disasters at grid-scale in Beijing-Tianjin-Hebei metropolitan area[J].Journal of Catastrophology,2020,35(3):186-193.
• [22] CHEN T,GUESTRIN C.XGBoost:a scalable tree boosting system[C]//Association for Computing Machinery.Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.New York:Association for Computing Machinery,2016:785-794.
• [23] SCHUMANN J P,VERNIEUWE H,DE BAETS B,et al.ROC-based calibration of flood inundation models[J].Hydrological Processes,2015,28(22):5495-5502.
• [24] 权瑞松.典型沿海城市暴雨内涝灾害风险评估研究[D].上海：华东师范大学，2012.QUAN R S.Research on risk assessment of rainstorm waterlogging disaster in typical coastal city[D].Shanghai:East China Normal University,2012.
• [25] CHEN Junfei,LI Juan,WANG Huimin,et al.Risk assessment of urban rainstorm disaster based on multi-layer weighted principal component analysis:a case study of Nanjing,China[J].International Journal of Environmental Research and Public Health.2020,17(15):5523.
• [26] 雷享勇，陈燕，潘骁骏，等.杭州市主城区暴雨内涝灾害风险区划[J].杭州师范大学学报(自然科学版),2019,18(1):105-112.LEI X Y,CHEN Y,PAN X J,et al.Risk zonation of rainstorm flooding disaster in Hangzhou Main City Zone[J].Journal of Hangzhou Normal University(Natural Science Edition),2019,18(1):105-112.
• [27] MAHYAT S T,SIMON J,FARZIN S.Identifying the essential flood conditioning factors for flood prone area mapping using machine learning techniques[J].CATENA,2019,175:174-192.
• [28] 住房和城乡建设部城市交通工程技术中心.中国主要城市道路网密度监测报告[R].北京：住房和城乡建设部城市交通工程技术中心，中国城市规划设计研究院，北京四维图新科技股份有限公司，2020.Urban Traffic Engineering Technology Center of the Ministry of Housing and Urban Rural Development.Annual Report on Road Network Density in Major Chinese Cities[R].Beijing:Urban Traffic Engineering Technology Center of Ministry of Housing and Urban-Rural Development,China Academy of Urban Planning and Design,NavInfo Co.,Ltd.,2020.
• [29] 梁春阳，林广发，张明锋，等.社交媒体数据对反映台风灾害时空分布的有效性研究[J].地球信息科学学报，2018,20(6):807-816.LIANG C Y,LIN G F,ZHANG M F,et al.Assessing the effectiveness of social media data in mapping the distribution of typhoon disasters[J].Journal of Geo-information Scienc,2018,20(6):807-816.