基于MapGIS深度学习的承灾体数据提取工具设计与实践  

Design and Practice of Disaster Bearing Body Data Extraction Tool Based on MAPGIS Deep Learning

作　　者：周丹 张国伟 张凯 潘明敏 范素海 ZHOU Dan;ZHANG Guowei;ZHANG Kai;PAN Mingmin;FAN Suhai(Wuhan Zondy Cyber-Tech Co.,Ltd.,Wuhan 430073,China;Beijing Zondy T&S Cyber-Tech Co.,Ltd.,Beijing 100085,China;Shenzhen Zondy Soft Engineering Co.,Ltd.,Shenzhen 518057,China)

机构地区：[1]武汉中地数码科技有限公司,湖北武汉430073 [2]北京中地时空数码科技有限公司,北京100085 [3]深圳市中地软件工程有限公司,广东深圳518057

出　　处：《测绘地理信息》2024年第3期118-122,共5页Journal of Geomatics

基　　金：国家重点研发计划(2017YFB0503600)。

摘　　要：国务院决定2020—2022年开展第一次全国自然灾害综合风险普查工作。针对普查工作中承灾体数据基数庞大、提取困难等问题,通过以国产MapGIS软件平台为基础,结合大数据、深度学习等技术,探索实践出一套完整的承灾体提取工作流程,形成可应用的深度学习承灾体提取工具,从而进一步加强了空间信息领域对复杂数据的解释与分析能力。为有效开展自然灾害防治和应急管理工作、切实保障社会经济可持续发展提供权威的灾害风险信息和科学决策依据。China's State Council has decided to conduct the first national comprehensive risk survey of natural disasters from 2020 to 2022.In view of the problems such as large data base and extraction difficulty of disaster bearing bodies in the census work,a complete disaster bearing body extraction workflow which combines big data with deep learning technol⁃ogies is explored and practiced based on the Domestic MAP⁃GIS software platform,and an applicable deep learning disas⁃ter bearing body extraction tool is formed.Thus,it further strengthens the interpretation and analysis ability of complex data in spatial information field.To provide authoritative disas⁃ter risk information and scientific decision-making basis for ef⁃fectively carrying out natural disaster prevention and emergen⁃cy management,and ensuring sustainable socio-economic de⁃velopment.

关 键 词：承灾体 MAPGIS平台 深度学习 提取工具 

分 类 号：P208[天文地球—地图制图学与地理信息工程]