土地利用规划中建设用地预测方法比较

Comparison of Construction Land Prediction Methods in Land Use Planning

为探索提高建设用地预测精度和预测方法比较,该文运用多元线性回归模型、GM(1,1)模型和BP神经网络模型对晋城市建设用地进行预测,预测结果说明三种模型的平均相对误差和预测精度均存在一定差异。研究表明:建设用地预测中应结合数据本身的特点和数据收集的难易程度选择不同模型;多角度多方法进行预测比较,可得到预测精度较高的预测结果;对于建设用地预测方法比较,可以从模型本质特性、数据采用形式和数据获取难易程度等7个方面进行综合比较。该研究为科学选择建设用地预测方法、探索预测方法比较提供一种思路,为土地利用规划修编和土地资源可持续利用提供科学依据。

In order to improve the prediction accuracy of construction land and compare prediction methods,multiple linear regression model,GM( 1,1) model and BP neural network model are used to predict construction land in Jincheng. The result of the research indicates that both the relative error and average prediction accuracy of three models have some differences to a certain extent. It is concluded that we should choose different prediction models according to the difficulty of data collection and the characteristics of the data itself; A higher prediction accuracy can be obtained by different aspects and methods comparison. We can compare construction land prediction methods from the aspects of essential characteristics of the model,the forms of the data,the difficulty in data collection and etc. This study provides a new idea for selecting construction land prediction methods and comparing the prediction methods. Otherwise,it could offer the reference for land use planning and sustainable land use.