Poverty-Returning Risk Monitoring and Analysis of the Registered Poor Households Based on BP Neural Network and Natural Breaks: A Case Study of Yunyang District, Hubei Province

To address the problem of subjectivity in determining poverty-returning risk among registered poor households, a method monitoring and analyzing households based on BP neural network natural breaks was constructed. In case Yunyang District, Hubei Province, data poverty alleviation development system, we constructed system for households. The spatial distribution pattern under analyzed from two scales district township, respectively, by combining Geographic Information Science, influence degree indicators using mean impact value (MIV). results show that: (1) study area basically coincides with local poverty-causing factors social economic development. (2) Poverty-Returning Risk Index each township represents globally strong dependence Moran’s I coefficient 0.352. (3) past identification status is main factor to reduce risk, policy should remain unchanged period time. (4) Improving quality education within focusing helping older average age can further risk.