基于图注意力网络的城市内涝积水预测与研究  

Prediction and Research of Urban Waterlogging Based on Graph Attention Network

作　　者：胡昊 孙爽[2] 马鑫 李擎[5] 徐鹏 HU Hao;SUN Shuang;MA Xin;LI Qing;XU Peng(Yellow River Conservancy Technical Institute,Kaifeng 475004,China;North China University of Water Resources and Electric Power,Zhengzhou 450045,China;Henan Engineering Research Center of Project Operation and Ecological Security for Inter-Basin Regional Water Diversion Project,Kaifeng 475004,China;China Institute of Water Resources and Hydropower Research,Beijing 100038,China;China Water Resources Beifang Investigation,Design and Research Co.,Ltd.,Tianjin 300222,China)

机构地区：[1]黄河水利职业技术学院,河南开封475004 [2]华北水利水电大学,河南郑州450045 [3]河南省跨流域区域引调水运行与生态安全工程研究中心,河南开封475004 [4]中国水利水电科学研究院,北京100038 [5]中水北方勘测设计研究有限责任公司,天津300222

出　　处：《人民黄河》2024年第4期43-48,共6页Yellow River

基　　金：河南省重大科技专项(221100320200,231100320100);河南省高等学校青年骨干教师培养计划项目(2019GCJS105);开封市重点研发专项(22ZDYF007)。

摘　　要：极端暴雨天气多发频发造成的城市内涝,严重威胁居民的人身财产安全,准确高效的内涝点积水面积预测在提高城市灾害应急处置能力中发挥着至关重要的作用。为了提高城市内涝点积水预测的准确性和直观性,提出一种基于GAT和LSTM网络的GATLSTM组合预测模型,通过GAT提取积水信息局部空间特征,并通过节点分配权重的方式加强对关键信息序列的记忆,随后采用LSTM提取积水面积序列的时间特征,对内涝点积水面积进行预测。以开封市区某内涝点的积水数据建立模型并评估验证,将GATLSTM模型和LSTM、GAT以及GCNLSTM模型进行对比,结果表明:GATLSTM模型的预测精度优于另外3种模型,能够准确地对内涝点积水面积进行预测,可以为防汛工作和应急响应措施的制定提供科学依据。The frequent occurrence of extreme heavy rainfall in cities has posed a severe threat to the personal and property safety of residents due to urban flooding.Accurate and efficient prediction of flooding areas within cities plays a crucial role in enhancing urban disaster emer-gency response capabilities.In order to improve the accuracy and intuitiveness of urban flooding area predictions,this article proposed a com-bination prediction model called GATLSTM,based on GAT(Graph Attention Network)and LSTM(Long Short-Time Memory).The GAT was used to extract local spatial features of flooding information,and it enhanced the memory of key information sequences by assigning weights to nodes.Subsequently,LSTM was employed to extract temporal features of flooding area sequences and predicted the flooding areas at inundation points for the next 10 minutes.The model was built and evaluated by using inundation data from a specific point in Kaifeng City.It was compared with LSTM,GAT and GCNLSTM models.The results indicate that the GATLSTM model outperforms the other three models in terms of prediction accuracy.It can accurately forecast flooding areas at inundation points in the short term,providing a scientific basis for flood prevention efforts and emergency response measures.

关 键 词：积水预测 城市暴雨 图注意力网络 长短期记忆网络 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]