利用深度学习模型进行城市内涝影响分析  

Analysis of Urban Waterlogging Influence Based on Deep Learning Model

作　　者：潘银 邵振峰[1] 程涛[1] 贺蔚 PAN Yin;SHAO Zhenfeng;CHENG Tao;HE Wei(State Key Laboratory of Information Engineering in .Surveying,Mapping and Remote Sensing, Wuhan University,Wuhan 430079,China;Wuhan Municipal Engineering Design and Research Institute Co.,Ltd.,Wuhan 430015,China)

机构地区：[1]武汉大学测绘遥感信息工程国家重点实验室,湖北武汉430079 [2]武汉市政工程设计研究院有限责任公司,湖北武汉430015

出　　处：《武汉大学学报（信息科学版）》2019年第1期132-138,共7页Geomatics and Information Science of Wuhan University

基　　金：国家重点研发计划战略性国际科技创新合作重点专项(2016YFE0202300);广州市科技计划(201604020070);武汉市晨光计划(2016070204010114);湖北省重点研发计划(2016AAA018);国家自然科学基金(51508422,41771454)~~

摘　　要：城市内涝是当前典型的一类城市自然灾害,影响着居民的生活质量。以城市内涝点作为研究对象,综合考虑内涝对城市居民工作和生活等方面造成的影响,筛选出与影响程度相关的21类空间数据。同时,基于深度学习原理构建栈式自编码神经网络模型,结合层次分析法获取的内涝点影响程度标签,剖析21类空间数据与内涝点对居民工作生活影响程度的关系,实现城市内涝对居民工作和生活影响的定量分析。实验表明,栈式自编码神经网络模型能准确地描述内涝点周围的系列空间数据与内涝影响程度之间的关系,可有效预测潜在内涝点对居民工作和生活的影响程度大小,可用于城市防洪排涝方案的制定和排水管网的优化设计。Urban waterlogging is a typical kind of urban natural disasters, which affecting the quality of residents’ life.This paper takes a series of waterlogging points produced by urban rainstorm as the research objects, comprehensively considering the influence of urban waterlogging on the work and life of residents, and screens out 21 kinds of data related to the influence degree.At the same time, based on the principle of deep learning, we construct a stacked autoencoder neural network model. With the influence degree labels of urban waterlogging points obtained by analytic hierarchy process method, the relationship between the 21 types of data and the influence degree of waterlogging points is analyzed, which will be applied to the quantitative analysis of the influence of urban waterlogging points.The experimental results show that the proposed model in this paper can describe the relationship between the spatial data and the influence degree accurately. In addition, this model can effectively predict the influence degree of potential waterlogging points, which is not only beneficial to the formulation of the urban waterlogging prevention scheme, but also provides a reference for the design of urban drainage pipe network.

关 键 词：深度学习 城市内涝 栈式自编码神经网络 层次分析法 

分 类 号：P208[天文地球—地图制图学与地理信息工程]