Population spatialization method based on AWA-DRCN

Abstract

The invention relates to a population spatialization method based on AWA-DRCN, and belongs to the technical field of Internet and computers. The method comprises the following steps: S1, acquiring a population data set and driving factor data, and preprocessing the population data set and the driving factor data; s2, a de-coarsening process: adopting an AWA model to achieve global feature learning, and completing regional and county-level population general survey data rasterization; and S3, a'refining'process: constructing a high-efficiency sub-pixel convolutional neural network DRCN model, taking the rasterized population data and the driving factor data in the step S2 as features, taking the processed grid population raster data as labels, inputting the processed grid population rasterdata into the DRCN model for hybrid learning to achieve global and local features, and obtaining a population spatialization result in spatial distribution. The AWA + DRCN model adopted in the methodis high in simulation precision, and the space residual value interval error is minimum.

Description

technical field [0001] The invention belongs to the technical field of Internet and computer, and relates to a population spatialization method based on AWA-DRCN. Background technique [0002] Population spatialization is similar to the downscaling process of early climate data. It is a downscaling space that converts the statistical population with low spatial resolution at a certain point in the study area into a high-resolution population distribution that is close to the real population distribution. technology. Since population spatialization data solves the spatial limitation of census data to a certain extent, it is widely used in disease and disaster management, urban planning and other aspects. To sum up, the current population spatial modeling technology can be roughly divided into two major trends: global model building and local model building. [0003] The construction of the global model has gone through the calculation of the average population in the region...

AI Technical Summary

Problems solved by technology

However, the SRCNN model has the problem of too many parameters in the nonlinear mapping step and a certain amount of information loss caused by a large filter. Trying to improve the convolution structure or use sub-pixel convolution can better learn local features.

[0004] A single model can only extract global or local features alone, and cannot get rid of the influence of complex terrain. Therefore, a method for high-resolution population spatialization is urgently needed

Images