基于多源数据的重庆市产业功能区识别及变迁分析  

Identification and Change Analysis of Industrial Functional Area in Chongqing City Based on Multi-source Data

作　　者：沈祺林 牟凤云[1,2] 邵志豪 SHEN Qilin;MOU Fengyun;SHAO Zhihao(School of Smart City,Chongqing Jiaotong University,Chongqing 400000,China;The Project Supported by the Open Fund of Key Laboratory of Urban Resources Monitoring and Simulation,Ministry of Natural Resources,Shenzhen 518038,China;208 Hydrogeology and Engineering Geology Team,Chongqing Bureau of Geology and Mineral Exploration and Development,Chongqing 401121)

机构地区：[1]重庆交通大学智慧城市学院,重庆400074 [2]自然资源部城市国土资源监测与仿真重点实验室,广东深圳5180381 [3]重庆市地质矿产勘查开发局208水文地质工程地质队,重庆401121

出　　处：《地域研究与开发》2024年第5期47-53,共7页Areal Research and Development

基　　金：2024年度教育部人文社会科学研究规划基金项目(24YJAZH107)重庆市教委科学技术研究计划项目(KJZD-K202300707);自然资源部城市国土资源监测与仿真重点实验室开放基金课题(KF-2021-06-102);重庆交通大学研究生科技创新项目(2024S0158);重庆市研究生导师团队建设项目(JDDSTD2022002)。

摘　　要：基于POI数据,通过TF-IDF算法、K-means聚类算法精确识别产业功能区,深入探究重庆市中心城区2014—2021年产业功能区时空演化。结果表明:(1)重庆市中心城区休闲娱乐产业区与生活服务产业区呈集中分布;商业产业区与公共服务产业区由离散分布变为集中分布;其余产业功能区呈零散分布。(2)2014—2021年,重庆市中心城区休闲娱乐产业区、商业产业区、科教文化产业区、生活服务产业区、公共服务产业区变化较明显;房地产业区变化较小;医疗产业区变化呈先增加后减少趋势;商务服务产业区无明显变化。(3)运用混淆矩阵法对产业功能区识别结果进行精度评价,得到重庆市中心城区产业功能区总体分类精度为82.50%,Kappa系数为0.80。总体上,TF-IDF算法能够较精确地识别出产业功能区,识别结果可为研究产业功能区空间演化提供参考。Based on POI data,the TF-IDF algorithm and K-means clustering algorithm were used to accurately identify the industrial functional areas,and the spatio-temporal evolution of the industrial functional areas in the central urban area of Chongqing City from 2014 to 2021 was deeply explored.The results showed that:(1)The leisure and entertainment industry area and the life service industry area in the central urban area of Chongqing were centrally distributed;The commercial industrial area and the public service industrial area had changed from discrete distribution to centralized distribution;The rest of the industrial functional areas were scattered.(2)From 2014 to 2021,the leisure and entertainment industry zone,commercial industry zone,science,education and cultural industry zone,life service industry zone and public service industry zone in the central urban area of Chongqing changed significantly.The real estate industry area had changed less;The change trend of medical industry zones was first increasing and then decreasing;There was no significant change in the business service industrial zone.(3)The confusion matrix method was used to evaluate the accuracy of the identification results of industrial functional zones,and the overall classification accuracy of industrial functional zones in the central urban area of Chongqing was 82.50%,and the Kappa coefficient was 0.80.In general,the TF-IDF algorithm could accurately identify industrial functional areas,and its recognition results could provide a reference for the study of the spatial evolution of industrial functional areas.

关 键 词：产业功能区 TF-IDF算法 POI数据 K-MEANS聚类算法 时空演化 重庆市 

分 类 号：TU984.11[建筑科学—城市规划与设计] F293.1[经济管理—国民经济]