A Hybrid Population Distribution Prediction Approach Integrating LSTM and CA Models with Micro-Spatiotemporal Granularity: A Case Study of Chongming District, Shanghai

Pengyuan Wang,Dong Xu,Di Zhang,Xiao Huang,Joseph Mango,Xiang Li

doi:10.3390/ijgi10080544

Abstract

Studying population prediction under micro-spatiotemporal granularity is of great significance for modern and refined urban traffic management and emergency response to disasters. Existing population studies are mostly based on census and statistical yearbook data due to the limitation of data collecting methods. However, with the advent of techniques in this information age, new emerging data sources with fine granularity and large sample sizes have provided rich materials and unique venues for population research. This article presents a new population prediction model with micro-spatiotemporal granularity based on the long short-term memory (LSTM) and cellular automata (CA) models. We aim at designing a hybrid data-driven model with good adaptability and scalability, which can be used in more refined population prediction. We not only try to integrate these two models, aiming to fully mine the spatiotemporal characteristics, but also propose a method that fuses multi-source geographic data. We tested its functionality using the data from Chongming District, Shanghai, China. The results demonstrated that, among all scenarios, the model trained by three consecutive days (ordinary dates), with the granularity of one hour, incorporated with road networks, achieves the best performance (0.905 as the mean absolute error) and generalization capability.

Highlights

Population distribution prediction refers to estimating the population of a specific geographic unit, taking into account the impact of natural geography and the socioeconomic environment and applying scientific methods to estimate population development in another temporal period [1]
As for neighboring scenarios, we notice that models that consider spatial information outperform models that do not, which proves the important role of spatial dependency in population distribution prediction
Taking mobile phone signaling data as input and Chongming District of China as the study case, we proposed a model that integrates long short-term memory (LSTM) and cellular automata (CA) to extract population dynamics from spatiotemporal dimensions

Summary

Introduction

Population distribution prediction refers to estimating the population of a specific geographic unit, taking into account the impact of natural geography and the socioeconomic environment and applying scientific methods (predictive models) to estimate population development in another temporal period [1]. Traditional population prediction generally has extremely coarse spatiotemporal granularity. With the advent of information handling techniques, new data collection methods, data processing algorithms, and improvements in computing power have made population prediction with micro-spatiotemporal granularity possible. Population estimation and prediction have been essential in human society for policymaking and socioeconomic planning, such as urban and health care planning at different administration levels. Studies on population prediction can be traced back to the United Kingdom in 1695 [2]. After years of exploration and efforts by mathematicians, statisticians, demographers, geographers, and other scholars, a series of models for population prediction is proposed

Objectives

Findings

Discussion

Conclusion