GM(1,n)和BP神经网络在福州市建成区用地预测中的应用比较

Comparison of GM(1,n) and BP neural network model in predicting the construction lands in Fuzhou City

城市规模扩展导致耕地急剧减少，研究城市规模对于保护耕地，提高城市用地集约度有重要意义。本研究分析了1998年～2005年期间福州市城市规模的变化趋势，以福州市建成区为例对GM（1，n）和BP神经网络在此类研究中的应用进行了对比。经检验，BP神经网络比灰色模型拟合良好，这是对建成区面积预测方法有益的探索。

The expand of city occupies lots of cultivate land, the research on construtcion land areapredicting is significant. This paper analyzes the tendency of Fuzhou city scale change be- tween1998 and 2005,comparing the gray model and BP neural network model in predicting the construction land area. The effect has shown BP neural network model is more precision. It hopes that it can contribute to the study on predicting method.