摘要
依据乌鲁木齐市2000~2015年社会经济发展数据,通过构建城市建成区规模扩张与社会经济发展的协调性分析模型,计算市辖区建成区规模扩张与社会经济发展的协调性系数;构建预测模型,分析乌鲁木齐市辖区建成区规模与其他社会经济发展指标的关系,进而对其市辖区到2020年建成区规模进行预测。主要结论有:乌鲁木齐市辖区的建成区的单位土地经济效益逐年增加,GDP的增长速度明显要高于建成区规模的扩张,说明其建设用地的土地报酬正处于递增的第一阶段,总体上土地投入较合理;乌鲁木齐市辖区建成区规模扩张与人口增长的协调度较弱,其建成区规模正处于快速扩张阶段;通过分析两个不同预测模型的实际应用效果,显示通过BP神经网络模型能够获得更加有效的预测,最终预测到2020年乌鲁木齐市辖区建成区规模将达到523.8287km2。
Through the construction of coordination area expansion and the development of society and economy analysis model of the city was built,based on the2000data of social economic development in2015,calculate the area of Urumqi city built area coordination coefficient of scale expansion and the economic and social development;build multivariate linear regression model,analysis of the relationship between Urumqi city and other built-up area scale social and economic index,and the city built in2020to forecast the size.The main conclusions are:The unit of land economic benefit in Urumqi City,the area of built-up area increased year by year,the growth rate of GDP was significantly higher than that of built-up area expansion,its development is in the stage of increasing returns of land,land investment is generally more reasonable;The Urumqi area of built-up area expansion and population growth the coordination degree is weak,the built-up area scale is in a phase of rapid expansion;Through the analysis of two different prediction models of the practical application results show that the BP neural network model to predict the more effective,the final forecast to2020Urumqi City area of built-up area will reach523.8287km2.
作者
穆飞翔
蒲春玲
刘祥鑫
MU Fei-Xiang;PU Chun-Ling;LIU Xiang-Xin(School of Management, Xinjiang Agricultural University, Xinjiang Urumqi 830052, China;Center for Economic and Social Development, Xinjiang Agricultural University, Xinjiang Urumqi 830052, China)
出处
《上海国土资源》
2017年第3期30-35,共6页
Shanghai Land & Resources
基金
国家社会科学基金项目"西部‘矿农复合区’非自愿移民搬迁安置及管控机制研究"(14XGL005)
关键词
建成区
规模扩张
经济社会发展
协调性分析
建设用地
效益分析
多元线性回归
BP神经网络
built-up area
scale expansion
economic social development
harmony analysis
construction land
benefit evaluation
multiple regression
BP neural network
