基于深度学习的城市内涝积水水深预测模型

doi:10.3880/j.issn.10046933.2025.01.008

首页 > 过刊浏览>2025年第41卷第1期 >56-63. DOI:10.3880/j.issn.10046933.2025.01.008

PDF HTML阅读 XML下载导出引用引用提醒

基于深度学习的城市内涝积水水深预测模型

DOI:

10.3880/j.issn.10046933.2025.01.008

作者:

林凯荣 ^{^1,2,3}
林凯荣
中山大学土木工程学院,广东广州 510275;广东省海洋土木工程重点实验室,广东广州 510275;广东省华南地区水安全调控工程技术研究中心,广东广州 510275
在知网中查找
在百度中查找
在本站中查找
欧阳佳娜 ^¹
欧阳佳娜
中山大学土木工程学院,广东广州 510275
在知网中查找
在百度中查找
在本站中查找
马旭民 ^¹
马旭民
中山大学土木工程学院,广东广州 510275
在知网中查找
在百度中查找
在本站中查找
肖名忠 ^¹
肖名忠
中山大学土木工程学院,广东广州 510275
在知网中查找
在百度中查找
在本站中查找
冯星昱 ^¹
冯星昱
中山大学土木工程学院,广东广州 510275
在知网中查找
在百度中查找
在本站中查找

作者单位:

(1.中山大学土木工程学院,广东广州 510275;2.广东省海洋土木工程重点实验室,广东广州 510275;3.广东省华南地区水安全调控工程技术研究中心,广东广州 510275 )

作者简介:

林凯荣(1980—),男,教授,博士,主要从事水文水资源研究。E-mail:linkr@mail.sysu.edu.cn

通讯作者:

中图分类号:

基金项目:

国家优秀青年科学基金项目(51822908)；广东省基础与应用基础研究基金项目(2023B1515040028)；广东省水文局专项资金项目(440001-2023-10716)

Prediction model of urban waterlogging water depth based on deep learning//

Author:

LIN Kairong ^{^1,2,3}
LIN Kairong
School of Civil Engineering,Sun Yat-Sen University, Guangzhou 510275, China;Guangdong Key Laboratory of Marine Civil Engineering, Guangzhou 510275, China;Guangdong Engineering Technology Research Center of Water Security Regulation and Control for Southern China, Guangzhou 510275, China
在知网中查找
在百度中查找
在本站中查找
OUYANG Jiana ^¹
OUYANG Jiana
School of Civil Engineering,Sun Yat-Sen University, Guangzhou 510275, China
在知网中查找
在百度中查找
在本站中查找
MA Xumin ^¹
MA Xumin
School of Civil Engineering,Sun Yat-Sen University, Guangzhou 510275, China
在知网中查找
在百度中查找
在本站中查找
XIAO Mingzhong ^¹
XIAO Mingzhong
School of Civil Engineering,Sun Yat-Sen University, Guangzhou 510275, China
在知网中查找
在百度中查找
在本站中查找
FENG Xingyu ^¹
FENG Xingyu
School of Civil Engineering,Sun Yat-Sen University, Guangzhou 510275, China
在知网中查找
在百度中查找
在本站中查找

Affiliation:

(1.School of Civil Engineering,Sun Yat-Sen University, Guangzhou 510275, China;2.Guangdong Key Laboratory of Marine Civil Engineering, Guangzhou 510275, China;3.Guangdong Engineering Technology Research Center of Water Security Regulation and Control for Southern China, Guangzhou 510275, China)

Fund Project:

摘要

图/表

访问统计

参考文献

相似文献

引证文献

文章评论

摘要:

为提高城市内涝模拟计算效率,满足城市内涝预警时效性的要求,利用深度学习方法优势,基于传统水文水动力学模型的模拟结果,以坡度、高程、降水量等城市暴雨内涝致灾链条发展的关键驱动因子作为输入,结合卷积神经网络(CNN)和长短期记忆网络(LSTM),引入注意力机制(ATT),并使用麻雀搜索优化算法进行超参数优选,构建了城市内涝积水水深预测的CNN-LSTM-ATT模型。利用该模型对深圳市大空港新城区内涝积水水深进行预测,结果表明:CNN-LSTM-ATT模型能有效预测暴雨引起的城市内涝积水水深,其在未来30min内的预测水深与水文水动力学模型模拟结果相近,模型精度在延长预见期后略有下降；与水文水动力学模型相比,CNN-LSTM-ATT模型模拟效率提高近200倍。

关键词:城市内涝;水文水动力学模型;深度学习方法;水深预测;深圳市中图分类号:TP183;TV124 文献标志码:A 文章编号:10046933

Abstract:

In order to improve the computational efficiency of urban waterlogging simulation and meet the requirement of timeliness of urban flooding warning, the advantage of deep learning method and simulation results of the traditional hydrological-hydrodynamic model were utilized, and the key driving factors for the development of urban rainstorm waterlogging disaster chain, including slope, elevation, and precipitation, were used as inputs. In combination with the convolutional neural network

Key words:urban waterlogging; hydrological-hydrodynamic model; deep learning method; water depth prediction; Shenzhen City 〖FL

参考文献

[1] 张金良,罗秋实,王冰洁,等.城市极端暴雨洪涝灾害成因及对策研究进展[J].水资源保护,2024,40(1):6-15.(ZHANG Jinliang,LUO Qiushi,WANG Bingjie,et al.Research progress on causes and countermeasures for extreme rainstorm-induced urban flood disasters[J].Water Resources Protection,2024,40(1):6-15.(in Chinese)

[2] 徐宗学,陈浩,任梅芳,等.中国城市洪涝致灾机理与风险评估研究进展[J].水科学进展,2020,31(5):713-724.(XU Zongxue,CHEN Hao,REN Meifang,et al.Progress on disaster mechanism and risk assessment of urban flood/waterlogging disasters in China[J].Advances in Water Science,2020,31(5):713-724.(in Chinese)

[3] 李超超,程晓陶,申若竹,等.城市化背景下洪涝灾害新特点及其形成机理[J].灾害学,2019,34(2):57-62.(LI Chaochao,CHENG Xiaotao,SHEN Ruozhu,et al.New characteristics and formation mechanism of flood and waterlogging disasters in the context of rapid urbanization[J].Journal of Catastrophology,2019,34(2):57-62.(in Chinese)

[4] 卢兴超,徐宗学,李永坤,等.基于SWMM与LISFLOOD-FP耦合模型的城市街区内涝模拟研究[J].水资源保护,2024,40(3):98-105.(LU Xingchao,XU Zongxue,LI Yongkun,et al.Research on urban block waterlogging simulation based on coupling model of SWMM and LISFLOOD-FP[J].Water Resources Protection,2024,40(3):98-105,124.(in Chinese)

[5] CRED, UNDRR.The human cost of disasters:an overview of the last 20 years (2000-2019)[EB/OL].(2020-10-16) [2024-06-10].https://www.undrr.org/publication/human-cost-disasters-overview-last-20-years-2000-2019.

[6] ANDIMUTHU R,YANDASAM P,MUDGAL B V,et al.Performance of urban storm drainage network under changing climate scenarios:flood mitigation in Indian coastal city[J].Scientific Reports,2019,9(1):7783.

[7] PANDA R K,PRAMANIK N,BALA B.Simulation of river stage using artificial neural network and MIKE 11 hydrodynamic model[J].Computers & Geosciences,2010,36(6):735-745.

[8] CHANG F J,CHEN P A,LU Y R,et al.Real-time multi-step-ahead water level forecasting by recurrent neural networks for urban flood control[J].Journal of Hydrology,2014,517:836-846.

[9] CHEN Jian,LI Yaowei,ZHANG Changhui,et al.Urban flooding prediction method based on the combination of LSTM neural network and numerical model[J].International Journal of Environmental Research and Public Health,2023,20(2):1043.

[10] 周聂,侯精明,陈光照,等.基于机器学习的山洪灾害快速预报方法[J].水资源保护,2022,38(2):32-40.(ZHOU Nie,HOU Jingming,CHEN Guangzhao,et al.A rapid forecasting method for mountain flood disaster based on machine learning algorithms[J].Water Resources Protection,2022,38(2):32-40.(in Chinese)

[11] 苑希民,黄玉啟,田福昌,等.基于LSTM-GM神经网络模型的风暴潮增水预报方法[J].水资源保护,2023,39(6):8-15.(YUAN Ximin,HUANG Yuqi,TIAN Fuchang,et al.Research on forecasting method of storm surge based on LSTM-GM neural network model[J].Water Resources Protection,2023,39(6):8-15.(in Chinese)

[12] PATRO S,CHATTERJEE C,MOHANTY S,et al.Flood inundation modeling using MIKE FLOOD and remote sensing data[J].Journal of the Indian Society of Remote Sensing,2009,37(1):107-118.

[13] LECUN Y,BOTTOU L,BENGIO Y,et al.Gradient-based learning applied to document recognition[J].Proceedings of the IEEE,1998,86(11):2278-2324.

[14] HOCHREITER S,SCHMIDHUBER J.Long short-term memory[J].Neural Computation,1997,9(8):1735-1780.

[15] 宋天宇.基于长短时记忆网络的山丘区洪水预报研究[D].大连:大连理工大学,2020.

[16] 张荣,李伟平,莫同.深度学习研究综述[J].信息与控制,2018,47(4):385-397.(ZHANG Rong,LI Weiping,MO Tong.Review of deep learning[J].Information and Control,2018,47(4):385-397.(in Chinese)

[17] 石卓,史东华,姚成,等.基于径流模数的LSTM模型在无资料嵌套流域的应用[J].河海大学学报(自然科学版),2024,52(3):51-57.(SHI Zhuo,SHI Donghua,YAO Cheng,et al.Application of runoff modulus-based LSTM in ungauged nested watersheds[J].Journal of Hohai University(Natural Sciences),2024,52(3):51-57.(in Chinese)

[18] TREISMAN A M,GELADE G.A feature-integration theory of attention[J].Cognitive Psychology,1980,12(1):97-136.

[19] MIORELLI R,KULAKOVSKYI A,CHAPUIS B,et al.Supervised learning strategy for classification and regression tasks applied to aeronautical structural health monitoring problems[J].Ultrasonics,2021,113:106372.

[20] FLETCHER T D,ANDRIEU H,HAMEL P.Understanding, management and modelling of urban hydrology and its consequences for receiving waters:a state of the art[J].Advances in Water Resources,2013,51:261-279.

[21] XUE Jiankai,SHEN Bo.A novel swarm intelligence optimization approach:sparrow search algorithm[J].Systems Science & Control Engineering,2020,8(1):22-34.

[22] 成霄楠.基于改进麻雀搜索算法及组合模型的光伏发电功率超短期预测研究[D].保定:河北大学,2023.

[23] 谭雨欣,吴端炜.基于MIKE URBAN的大亚湾澳头圆盘区域内涝模拟及排涝对策[J].人民珠江,2023,44(5):18-25.(TAN Yuxin,WU Duanwei.Waterlogging simulation and drainage countermeasures of Aotou Yuanpan area in Daya Bay based on MIKE URBAN[J].Pearl River,2023,44(5):18-25.(in Chinese)

[24] 卓小燕,孙翔.基于MIKE模型的城市内涝风险评估与整治方案效果研究[J].水利规划与设计,2023(10):34-40.(ZHUO Xiaoyan,SUN Xiang.Risk assessment of urban waterlogging based on MIKE model and study on the effect of remediation scheme[J].Water Resources Planning and Design,2023(10):34-40.(in Chinese)

[25] 侯俊,陈诚,郑玉磊,等.基于MIKE FLOOD模型的平原水网地区内涝治理效果模拟研究[J].水利水电科技进展,2024,44(6):41-47.(HOU Jun, CHEN Cheng, ZHENG Yulei, et al.Simulation study on effectiveness of waterlogging control in plain water network areas based on MIKE FLOOD model[J].Advances in Science and Technology of Water Resources,2024,44(6):41-47.(in Chinese)

[26] 方煜铭,马旭民,林凯荣,等.基于MIKE FLOOD的深圳市大空港片区暴雨内涝模拟分析[J].人民珠江,2024,45(5):88-95.(FANG Yuming,MA Xumin,LIN Kairong,et al.Simulation analysis of rainstorm waterlogging in Shenzhen Dakonggang area based on MIKE FLOOD[J].Pearl River,2024,45(5):88-95.(in Chinese)

引用本文

林凯荣,欧阳佳娜,马旭民,等.基于深度学习的城市内涝积水水深预测模型[J].水资源保护,2025,41(1):56-63.(LIN Kairong, OUYANG Jiana, MA Xumin, et al. Prediction model of urban waterlogging water depth based on deep learning//[J]. Water Resources Protection,2025,41(1):56-63.(in Chinese))

复制

文章指标

点击次数:183
下载次数: 91
HTML阅读次数: 0
引用次数: 0

历史

收稿日期:
最后修改日期:
录用日期:
在线发布日期: 2025-03-04
出版日期:

引用本文

分享

文章指标

历史