WASD neuronet prediction for China´s population

As one of the most important factors influencing the development potential of the country, China´s population attracts considerable attention. Some official organizations regularly publish the predictions of China´s population every calendar year. However, most of the predictions use the standard cohort-component method, which does not allow for all relevant impact factors and may lose sight of some important uncertainty factors. To overcome the aforementioned limitations, in this paper, we present a 3-layer feedforward neuronet (i.e., neural network) approach equipped with a weights-and-structuredetermination (WASD) algorithm for the population prediction of China. Numerical experiments further substantiate the feasibility of such an approach and indicate that there are three kinds of possibilities for the progress of China´s population in the next decade. With the highest possibility, China´s population will keep continual increase with a gentle growth rate.