欢迎访问《中国农学通报》，
中国农学通报

中国农学通报 ›› 2017, Vol. 33 ›› Issue (21): 82-88.doi: 10.11924/j.issn.1000-6850.casb16090040

• 资源 环境 生态 土壤 气象 • 上一篇    下一篇

基于主成分-BP神经网络的建设用地规模预测

王 丹1,杨小艳1,2,郑 剑3,陈龙高1,高卫东1   

  1. (1江苏师范大学土地资源研究所,江苏徐州 221116；2中国矿业大学环境与测绘学院,江苏徐州221116；3连云港市国土资源局,江苏连云港 222001）
  • 收稿日期:2016-09-07 修回日期:2016-10-24 接受日期:2016-11-08 出版日期:2017-07-27 发布日期:2017-07-27
  • 通讯作者: 王 丹
  • 基金资助:
    国家自然科学基金项目“基于情景模拟的土地利用规划环境影响动态基底评价模型研究” (41601087)；国家自然科学基金项目“县级土地利用规划环境影响多时态评价模型研究”(41271121)；江苏省普通高校研究生科研创新计划项目“基于土地利用情景模拟的环境影响预测与评价研究”(KYZZ_0388)。

Construction Land Scale Prediction Based on Principal Component-BP Neural Network:A Case Study of Lianyungang

Wang Dan1, Yang Xiaoyan1,2, Zheng Jian3, Chen Longgao1, Gao Weidong1   

  1. (1Institute of Land Resources, Jiangsu Normal University, Xuzhou Jiangsu 221116;2School of Environment and Spatial Informatics, China University of Mining & Technology, Xuzhou Jiangsu 221116;3Land and Resources Bureau of Lianyungang City, Lianyungang Jiangsu 222001)
  • Received:2016-09-07 Revised:2016-10-24 Accepted:2016-11-08 Online:2017-07-27 Published:2017-07-27

PDF (PC)

403

摘要： 建设用地是城市发展的重要因素，对建设用地规模的预测可以为土地利用总体规划提供参考数据和技术支持。笔者以连云港市为例，收集了2004—2013年有关建设用地规模的社会经济统计数据，采用主成分-BP神经网络模型对连云港市2014—2020年建设用地规模进行预测，得出7年连云港市建设用地规模的预测结果。本研究得出主要结论：（1）主成分分析结果显示社会经济的发展、人口和基础设施的变化以及环境的改善从不同方面影响着建设用地的规模；（2）笔者构建的BP神经网络模型误差率较低、拟合效果较好且对于训练集以外的新样本数据具有较好的泛化能力，说明所建模型具有可靠性,可以进行预测；（3）连云港市2014—2020年的建设用地规模呈现逐年扩张的趋势，年均增长率为0.97%，连云港市应采取有效措施控制建设用地规模并且合理保护耕地，使得建设用地面积的增长控制在合理的范围之内。主成分-BP神经网络模型不仅能够对影响建设用地规模的因素进行全面分析，同时可以得到精度较高的建设用地规模预测数据，因此能够较好地应用于建设用地规模预测。

关键词: 花针期灌水, 花针期灌水, 主茎高, 基部茎粗, 干物质积累量, 高效节水栽培

Abstract: Construction land is an important factor in the process of the urban development. Prediction of the construction land scale can provide reference data and technical support for general land use planning. This research collected the sociol and economic data from 2004 to 2013 which influenced the construction land scale of Lianyungang, and applied the principal component-BP neural network model to predict the scale of construction land in Lianyungang from 2014 to 2020, then obtained seven years’ prediction results of the scale of construction land in Lianyungang city. The following results can be concluded from the research: (1) The principal component analysis results show that the development of social economy, the changes of population and infrastructure, the improvement of the environment mainly contributed to influencing the scale of Lianyungang construction land from different aspects. (2) The error rate of the BP neural network model built in this research was low and its imitative effect was good, in addition, the model also had good generalization ability to the new sample data from outside of the training sets, which illustrated that the model was credible, so it could be applied to predict the construction land of the future. (3) The construction land scale of Lianyungang showed expansion trend from 2014 to 2020, the average annual growth rate was zero point seven nine percent, the growth rate was relatively fast, which may lead to many social problems. So effective measures should be taken to control the scale of the construction land of Lianyungang and protect arable land legitimately, making the growth of construction land area controlled in a reasonable range. Principal component-BP neural network model can not only comprehensively analyse the influencing factors of the construction land scale, it also can get high precision prediction data of construction land scale. As a result, this model should be well applied to construction land scale prediction.

中图分类号: