基于GIS和BP神经网络的区域农村贫困空间模拟分析——一种区域贫困程度测度新方法

Spatial Simulating in Regional Rural Poverty Based on GIS and BP Neural Network:A New Appraisement Method on Regional Rural Poverty

基于区域农村贫困程度测定方式不完善及缺乏地理视角的现状,选取四川省36个国家级扶贫县为实证对象,构建自然社会经济全面耦合的农村贫困测度指标体系,分析区域农村贫困的影响机制,并运用GIS与BP神经网络模拟区域自然致贫指数、社会致贫指数和经济消贫指数的空间分布格局。在此基础上,提出了全面表征区域农村贫困程度的区域扶贫压力指数——一种新的区域农村贫困测度方法,为国家扶贫政策文件《财政扶贫资金管理办法》中关于财政扶贫资金基于区域农村贫困程度分配提供实践基础。

Based on the status that appraisement method on regional rural poverty is not perfect and is lacking geographical factor, the national poverty alleviation counties in Sichuan Province were taken as an example to construct index system of regional rural poverty which includes physical, social and economic factors, and the infecting mechanism of regional rural poverty was an- alyzed. The regional Natural Impoverishing Index, Social Impoverishing Index and Economic Poverty Alleviation Index were simulated companying with their spatial distribution pattern with tools of GIS and BP Neural Network. Then, the regional Pres- sure of Poverty Alleviation Index was discussed, which can represent extent of regional rural poverty perfectly. It provided a new method of appraisement on regional rural poverty, and could give a realistic way about distribution of financial anti-poverty fund basically for the regional rural poverty. The method would comply with the country anti poverty policy laying on 《 Management Method of Financial Anti Poverty Fund》.