基于GIS和BP神经网络的生态疗养中心选址研究

Research on site selection of eco-recuperation center based on GIS and BP neural network

为了科学合理地选择生态疗养中心建筑地址,提出了一种将GIS(地理信息系统)与BP神经网络技术相结合的选址方法.该方法首先选取高程、坡度、坡向、水文、交通、土壤、土地利用、人口密度、地质灾害等9个指标作为评价指标,并利用GIS技术对这9个指标进行栅格化、量化和归一化处理;然后利用训练所得的BP神经网络模型计算出评价指标的权重值,并利用GIS的权重叠加方法最终确定生态疗养中心位置.研究结果显示,利用BP神经网络方法选取合理的学习速率与动量值可以有效地计算出评价因子的权重大小,进而可合理地选取生态疗养中心的建设位置.该方法对其他建筑或场所的选址也具有良好的参考价值.

In order to choose the location of eco-recuperation center scientifically and rationally,a site selection method combining GIS and BP neural network technology was proposed.Firstly,nine indexes,including elevation,slope,aspect,river,road,soil,land use,population density and geological hazard,were selected as evaluation indexes,and the nine indexes were rasterized,quantified and normalized by GIS technology.Then the BP neural network model was used to calculate the weight value of the evaluation index,and the weight superposition method of GIS was used to determine the site selection of eco-recuperation center.The results show that BP neural network method can effectively calculate the weight of evaluation factors by selecting a reasonable learning rate and momentum value,and then rationally select the construction location of ecorecuperation center.This method also has good reference value for other buildings or sites.