Abstract
China’s transportation industry has been experiencing huge changes and the travelling frequency of citizens becomes higher and higher and more and more diversified in a short time period. The analysis and deep research on the short-term change of population density in the city-level spatial resolution are worthy of further exploration. In this study, we first used two linear regression models to build relationships between the 2010 census density, predicted 2020 census density and the Tencent density respectively to test the usability of Tencent positioning data. The Pearson’s correlation coefficients r 0.58 (p $50\times 50$ km of spatial resolution. The total average of the ConvLSTM model’s Root Mean Square Error (RMSE) is 139.0, while the SARIMA’s one is three times greater than the value. And the coefficient of determination (R2) values of ConvLSTM model is higher than 0.9, while the other ones are about 0.78. Comparing the two results in both time and space concludes that: the evaluation results reflected by RMSE and R2 showed that the two models are both suitable for the prediction of Tencent density distribution in finely-grained time and space. Nevertheless, the predicted density correlated much better with the tested data at temporal and spatial scales when using ConvLSTM compared to SARIMA, and the capability of prediction in space by ConvLSTM model is more stable.
Highlights
Before the end of the human population growth in the foreseeable future is likely to come [1], the future development of population size and structure is of importance since planning in many areas of politics and business is conducted based on expectations about the future makeup of the population [2]
We visualize the distribution of Average Tencent Density (ATD) by 32 classifications natural break method that has been mentioned in section II.B., while the 2010 census density is classified and visualized by the same method, shown as figure 4(a), and the same output of predicted 2020 census density is shown in figure 4(b)
While we use ConvLSTM to predict the Tencent density distribution, because the convolution is used when we train the models, which can consider the surrounded cells’ values, there is not the situation like the seasonal autoregressive-integrated-moving-average (SARIMA). It is precisely because the ConvLSTM model considers the spatial autocorrelation that it is more suitable for prediction of Tencent density distribution, which proves that ConvLSTM model is much more accurate than the SARIMA model in this study
Summary
Before the end of the human population growth in the foreseeable future is likely to come [1], the future development of population size and structure is of importance since planning in many areas of politics and business is conducted based on expectations about the future makeup of the population [2]. Predicting the population size or density distribution in both finely-grained spatial and temporal scales in a large area, such as China, with a land area of about 9.6 million square kilometres, had not received much attention because the related data in a large area over a dynamic time period was hard to obtain in the past several years until the geographic spatiotemporal big data [9] appeared recently. 2) We first predict the human population distribution in a finely-grained spatial and temporal resolutions for the whole of China by a traditional model SARIMA and a novel deep learning model ConvLSTM, and to compare the results to conclude the most accurate one.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
