欢迎访问中国科学院大学学报,今天是

中国科学院大学学报 ›› 2009, Vol. 26 ›› Issue (4): 451-457.DOI: 10.7523/j.issn.2095-6134.2009.4.004

• 论文 • 上一篇    下一篇

基于BP神经网络模型的新疆建设用地分析

段祖亮1,2, 张小雷1, 权晓燕1,2   

  1. 1. 中国科学院新疆生态与地理研究所, 乌鲁木齐 830011;
    2. 中国科学院研究生院, 北京 100049
  • 收稿日期:2009-02-05 修回日期:2009-03-11 发布日期:2009-07-15
  • 通讯作者: 段祖亮
  • 基金资助:

    中国科学院知识创新工程重要方向项目(KZCX2-YW-321-03)和中国科学院知识创新重大项目(KZCX2-XB2-03-03)资助 

Analysis of construction land by back-propagation neural network model with Xinjiang as a case

DUAN Zu-Liang1,2, ZHANG Xiao-Lei1, QUAN Xiao-Yan1,2   

  1. 1. Xinjiang Institute of Ecology and Geography, Chinese Academy of Sciences, Urumqi 830011, China;
    2. Graduate University of the Chinese Academy of Sciences, Beijing 100049, China
  • Received:2009-02-05 Revised:2009-03-11 Published:2009-07-15

摘要:

鉴于BP神经网络在非线性领域预测中的应用,以新疆建设用地为研究对象,构建BP神经网络预测模型,选取1996~2006年总人口、城市化水平、GDP等10个因子,反映新疆人口状况、经济发展水平、产业结构及投资水平作为网络的仿真输入,对2007年新疆建设用地进行模拟预测,预测结果与实际面积的相对误差仅为0.06%.最后针对新疆建设用地中存在的问题,提出了保障经济与社会协调可持续发展的土地利用策略.

关键词: BP神经网络模型, 建设用地, 影响因素, 预测, 新疆

Abstract:

Taking Xinjiang as an example, we establish a predicting model by using BP neural network, and make a prediction of construction land in 2007. The model learning samples are from the social-economic statistical data between 1996 and 2006. The results show that the relative error between the predicted and actual value is only 0.06%, and the BP neural network has higher precision and better effectiveness than traditional methods. Some strategic countermeasures are put forward for sustainable land use in Xinjiang.

Key words: BP neural network model, construction land, influencing factor, prediction, Xinjiang

中图分类号: