Spatialization modeling of rural socio-economic data based on neural network: A case study of Fangshan District in Beijing, China

Obtaining the quantitative positioning space-based demographic and socio-economic information has the significance on assessing resources, environment and disaster. This paper presents a dynamic modeling method for rural GDP statistics data spatialization based on neural network Selecting Fangshan District in Beijing, China as the study area and taking villages as studying unit, this paper analyzes spatial correlation between the rural GDP and different geographic elements, establishes the assessment system of key factors which influence the economic development, and uses BP neural network to simulate the spatial interaction between the rural GDP and the factors and build the rural GDP spatial quantitative distribution of 500m × 500m grids. The result shows that the result of simulation and distribution are approximately consistent. The results also indicate that, the spatialization method of socio-economic statistic data using neural network has advantages of intelligent modeling and automation, wide adaptability and high precision spatialization.