刘媛媛,刘业森,刘方华,李梦阳,刘舒,李匡,任汉承

• 1:中国水利水电科学研究院
• 2:水利部防洪抗旱减灾工程技术研究中心
• 3:水利部数字孪生流域重点实验室
• 4:泸州市住房城乡建设局

摘要(Abstract)：

【目的】掌握精细化的降雨时空分布特征，对于城市洪涝风险管理水平的提高具有重要的意义。我国近十几年降雨监测站网密集且数据精细程度高，但时间序列较短；历史降雨资料时间序列长，但是精细程度低。【方法】为了更有效地利用历史降雨资料，将流形学习算法引入到历史降雨资料重构中，从高分辨率降雨资料中，提取降雨的时空分别特征，基于该特征，将历史逐6 h的降雨空间数据重构为逐1 h的降雨数据，以满足城市洪涝风险分析的要求。【结果】结果表明，该方法重构数据高值区与实测值的平均误差在15%以内，低值区在20%以内，比传统插值处理的数据高值区误差降低了45%～85%,低值区降低了10%～40%。【结论】利用流形学习算法重构的历史空间降雨数据符合各地区降雨时空分布特征，可提高降雨空间数据颗粒度，实现降雨时空分布精细化特征的有效、合理的提取和总结。

关键词(KeyWords)： 流形学习;机器学习;暴雨时空分布;特征提取;低分辨率重构;泸州;降水

Abstract:

Keywords:

基金项目(Foundation): 沂沭河流域超标准洪水防控能力提升措施建议(减JZ0145B042024);; 新疆2019—2021年院士工作站合作研究项目(2020,A-001)

作者(Author): 刘媛媛,刘业森,刘方华,李梦阳,刘舒,李匡,任汉承

DOI: 10.13928/j.cnki.wrahe.2024.09.008

参考文献(References)：

• [1] 张建云，王银堂，贺瑞敏，等.中国城市洪涝问题及成因分析[J].水科学进展，2016,27(4):485-491.ZHANG Jianyun,WANG Yintang,HE Ruimin,et al.Discussion on the urban flood and waterlogging and causes analysis in China[J].Advances in Water Science,2016,27(4):485-491.
• [2] 刘波，戎贵文，陈情情，等.基于 SWMM 的 LID 设施分区布局及减排效益[J].南水北调与水利科技(中英文),2023,21(5):930-939.LIU B,RONG G W,CHEN Q Q,et al.Regional distribution and mitigation benefit of LID facility based on SWMM[J].South-to-North Water Transfers and Water Science & Technology,2023,21(5):930-939.
• [3] 周紫蕊，廖卫红，雷晓辉，等.基于 InfoWorks ICM 的城市河网调控与分析：以福州市仓山区龙津阳岐片区为例[J].南水北调与水利科技(中英文),2023,21(4):770-779.ZHOU Z R,LIAO W H,LEI X H,et al.InfoWorks ICM-based urban river network regulation and analysis:A case study of Longjin Yangqi area in Cangshan District,Fuzhou City[J].South-to-North Water Transfers and Water Science & Technology,2023,21(4):770-779.
• [4] 刘登伟，张媛.国外绿色基础设施建设经验对我国“海绵城市”建设的启示[J].水利发展研究，2022,22(2):71-76.LIU Dengwei,ZHANG Yuan.Enlightenment of foreign green infrastructure construction experience on China′s "sponge city" construction [J].Water Resources Development Research,2022,22 (2):71-76.
• [5] 刘业森，刘媛媛，李敏，等.降雨时空不确定性对城市河道洪水的影响[J].南水北调与水利科技(中英文),2022,20(2):317-326.LIU Yesen,LIU Yuanyuan,LI Min,et al.Influence of rainfall spatial and temporal heterogeneity on flooding process in urban rivers[J].South to North Water Transfers and Water Science & Technology,2022,20(2):317-326.
• [6] WANG G Y,SUN G R,LI J K,et al.The experimental study of hydrodynamic characteristics of the overland flow on a slope with three-dimensional Geomat [J].Journal of Hydrodynamics,2018,30(1):153-159.
• [7] 郭良，丁留谦，孙东亚，等.中国山洪灾害防御关键技术[J].水利学报，2018,49(9):1123-1136.GUO Liang,DING Liuqian,SUN Dongya,et al.Key techniques of flash flood disaster prevention in China [J].Journal of Hydraulic Engineering,2018,49(9):1123-1136.
• [8] 程晓陶.城市型水灾害及其综合治水方略[J].灾害学，2010,25(S1):10-15.CHENG Xiaotao.Urban water disasters and strategy of comprehensive control of water disaster [J].Journal of Catastrophology,2010,25(S1):10-15.
• [9] LIU Yuanyuan,LI Lei,LIU Yesen,et al.Dynamic spatial-temporal precipitation distribution models for short-duration rainstorms in Shenzhen,China based on machine learning[J].Atmospheric Research,2020(237):Article 104861.
• [10] LECUN Y,BENGIO Y,HINTON G.Deep learning[J].Nature,2015,521:436-444.
• [11] 刘媛媛，刘洪伟，霍风霖，等.基于机器学习短历时暴雨时空分布规律研究[J].水利学报，2019,50(6):773-779.LIU Yuanyuan,LIU Hongwei,HUO Fenglin,et al.An application of machine learning on examining spatial and temporal distribution of short duration rainstorm[J].Journal of Hydraulic Engineering,2019,50(6):773-779.
• [12] LIU Yuanyuan,LI Lei,ZHANG Wenhai,et al.Rapid identification of rainstorm disaster risks based on an artificial intelligence technology using the 2DPCA method[J].Atmospheric Research,2019,227:157-164.
• [13] 刘媛媛，刘业森，郑敬伟，等.BP神经网络和数值模型相结合的城市内涝预测方法研究[J].水利学报，2022,53(3):284-295.LIU Yuanyuan,LIU Yesen,ZHENG Jingwei,et al.Intelligent rapid prediction method of urban flooding based on BP neural network and numerical simulation model[J].Journal of Hydraulic Engineering,2022,53(3):284-295.
• [14] 彭玲，王世玉.智慧EH供水工程总体设计研究[J].水利水电技术，2020,51(S1):231-236.PENG Ling,WANG Shiyu.Study on general design of intelligent EH Water Supply Project[J].Water Resources and Hydropower Engineering,2020,51(S1):231-236.
• [15] 吴鑫俊，赵晓东，丁茜，等.基于数据驱动的CNN洪水演进预测方法[J].水力发电学报，2021,40(5):79-86.WU Xinjun,ZHAO Xiaodong,DING Xi,et al.CNN flood routing method based on data-driven training[J].Journal of Hydroelectric Engineering,2021,40(5):79-86.
• [16] 白岗岗，侯精明，韩浩，等.基于深度学习的道路积水智能监测方法[J].水资源保护，2021,37(5):75-80.BAI Ganggang,HOU Jingming,HAN Hao,et al.Intelligent monitoring method for road inundation based on deep learning[J].Water Resources Protection,2021,37(5):75-80.
• [17] 鲍振鑫，张建云，王国庆，等.基于水文模型与机器学习集合模拟的水沙变异归因定量识别——以黄河中游窟野河流域为例[J].水科学进展，2021,32(4):485-496.BAO Zhenxin,ZHANG Jianyun,WANG Guoqing,et al.Quantitative assessment of the attribution of runoff and sediment changes based on hydrologic model and machine learning:a case study of the Kuye River in the Middle Yellow River basin[J].Advances in Water Science,2021,32(4):485-496.
• [18] JOSHUA B.TENENBAUM.A global geometric framework for nonlinear dimensionality reduction[J].Science,2000,290(11):2319-2323.
• [19] PAIEMENT A,MIRMEHDI M,XIE X,et al.Integrated segmentation,and interpolation of sparse data [J].IEEE Trans on Image Processing,2014,23(1):10-1025.
• [20] 孔锋，孙劭.1901—2018年“一带一路”陆域地区降雨量时空变化格局[J].水利水电技术(中英文),2021,52(2):1-10.KONG Feng,SUN Shao.Spatiotemporal variation pattern of rainfall in land area of the Belt and Road during 1901—2018[J].Water Resources and Hydropower Engineering,2021,52(2):1-10.