Early forecasting of the potential risk zones of COVID-19 in China's megacities

Abstract

Ecological niche model China's megacities Risk zones Early forecasting Recently, the coronavirus disease 2019 (COVID-19) has become a worldwide public health threat. Early and quick identification of the potential risk zones of COVID-19 infection is increasingly vital for the megacities implementing targeted infection prevention and control measures. In this study, the communities with confirmed cases during January 21-February 27 were collected and considered as the specific epidemic data for Beijing, Guangzhou, and Shenzhen. We evaluated the spatiotemporal variations of the epidemics before utilizing the ecological niche models (ENM) to assemble the epidemic data and nine socioeconomic variables for identifying the potential risk zones of this infection in these megacities. Three megacities were differentiated by the spatial patterns and quantities of infected communities, average cases per community, the percentages of imported cases, as well as the potential risks, although their COVID-19 infection situations have been preliminarily contained to date. With higher risks that were predominated by various influencing factors in each megacity, the potential risk zones coverd about 75% to 100% of currently infected communities. Our results demonstrate that the ENM method was capable of being employed as an early forecasting tool for identifying the potential COVID-19 infection risk zones on a fine scale. We suggest that local hygienic authorities should keep their eyes on the epidemic in each megacity for sufficiently implementing and adjusting their interventions in the zones

The COVID-19 pandemic: Impacts on cities and major lessons for urban planning, design, and management

“…They suggested that public health measures and the sharing of inter-city resources are two possible reasons for reducing social interactions and establishing a significant relationship in the second phase. In contrast, Ren et al (2020) observed that the very high-risk zones of COVID-19 infection in Beijing and Guangzhou tend to occur in areas with larger population densities. Similarly, a study of different Italian regions shows higher transmission rates in regions with higher population densities ( Cartenì et al, 2020 ).…”

Epidemia do novo coronavírus (COVID-19): análise dos indicadores nos três primeiros meses, Estado de São Paulo, Brasil

“…Devido à grande concentração populacional e às condições socioeconômicas mais díspares, aliadas ao fato de receberem muitos viajantes de várias partes do país e do mundo, por sua importância econômica, e apresentarem regiões com grande população flutuante, as megacidades como São Paulo foram confrontadas com tensões maiores dos surtos e importância na disseminação da infecção por COVID-19 14 .…”

A Review on COVID-19 Forecasting Models

“…Several approaches have been addressed by researchers to predict the COVID-19 outbreak. Deep Learning LSTM networks (Chimmula and Zhang 2020) Polynomial Neural Network (Fong, Li et al 2020) Neural Network (Moftakhar, Seif et al 2020, Tamang, Singh et al 2020 Ecological niche models (Ren, Zhao et al 2020) Regression Methods (Ji, Zhang et al 2020, Ribeiro, da Iteration method (Perc, Gorišek Miksić et al 2020)…”