This study empirically investigates the complex interplay between the severity of the coronavirus pandemic, mobility changes in retail and recreation, transit stations, workplaces, and residential areas, and lockdown measures in 88 countries around the world during the early phase of the pandemic. To conduct the study, data on mobility patterns, socioeconomic and demographic characteristics of people, lockdown measures, and coronavirus pandemic were collected from multiple sources (e.g., Google, UNDP, UN, BBC, Oxford University, Worldometer). A Structural Equation Modeling (SEM) framework is used to investigate the direct and indirect effects of independent variables on dependent variables considering the intervening effects of mediators. Results show that lockdown measures have significant effects to encourage people to maintain social distancing so as to reduce the risk of infection. However, pandemic severity and socioeconomic and institutional factors have limited effects to sustain social distancing practice. The results also explain that socioeconomic and institutional factors of urbanity and modernity have significant effects on pandemic severity. Countries with a higher number of elderly people, employment in the service sector, and higher globalization trend are the worst victims of the coronavirus pandemic (e.g., USA, UK, Italy, and Spain). Social distancing measures are reasonably effective at tempering the severity of the pandemic.
On the premise that knowledge creation defines contemporary metropolitan regions, we profile them by their inventive networks, as measured by a variety of complementary social network, technology, and patenting metrics that distinguish scalar and structural aspects. Using a comprehensive, multiyear database of patent applications, we investigate whether the knowledge creation network profiles are discriminating characteristics of metropolitan regions by establishing a new urban taxonomy for metropolitan areas in the United States. The four-class taxonomy is not only statistically significant, but it is also economically meaningful in terms of economic performance of metropolitan areas. We find that metropolitan areas benefit from a higher density of inventors in the population, and that there is a positive correlation between economic performance and metropolitan areas with inventor teams working in similar or complementary areas of technology. In fact, the structure of knowledge creation networks are fundamental to economic performance and extends to metropolitan growth rates in jobs and income.
Prediction of complex epidemiological systems such as COVID-19 is challenging on many grounds. Commonly used compartmental models struggle to handle an epidemiological process that evolves rapidly and is spatially heterogeneous. On the other hand, machine learning methods are limited at the beginning of the pandemics due to small data size for training. We propose a deep learning approach to predict future COVID-19 infection cases and deaths 1 to 4 weeks ahead at the fine granularity of US counties. The multi-variate Long Short-term Memory (LSTM) recurrent neural network is trained on multiple time series samples at the same time, including a mobility series. Results show that adding mobility as a variable and using multiple samples to train the network improve predictive performance both in terms of bias and of variance of the forecasts. We also show that the predicted results have similar accuracy and spatial patterns with a standard ensemble model used as benchmark. The model is attractive in many respects, including the fine geographic granularity of predictions and great predictive performance several weeks ahead. Furthermore, data requirement and computational intensity are reduced by substituting a single model to multiple models folded in an ensemble model.
The ongoing COVID-19 global pandemic is touching every facet of human lives (e.g., public health, education, economy, transportation, and the environment). This novel pandemic and nonpharmaceutical interventions of lockdown and confinement implemented citywide, regionally or nationally are affecting virus transmission, people's travel patterns, and air quality. Many studies have been conducted to predict the diffusion of the COVID-19 disease, assess the impacts of the pandemic on human mobility and on air quality, and assess the impacts of lockdown measures on viral spread with a range of Machine Learning (ML) techniques. This literature review aims to analyze the results from past research to understand the interactions among the COVID-19 pandemic, lockdown measures, human mobility, and air quality. The critical review of prior studies indicates that urban form, people's socioeconomic and physical conditions, social cohesion, and social distancing measures significantly affect human mobility and COVID-19 viral transmission. During the COVID-19 pandemic, many people are inclined to use private transportation for necessary travel to mitigate coronavirus-related health problems. This review study also noticed that COVID-19 related lockdown measures significantly improve air quality by reducing the concentration of air pollutants, which in turn improves the COVID-19 situation by reducing respiratoryrelated sickness and deaths. It is argued that ML is a powerful, effective, and robust analytic paradigm to handle complex and wicked problems such as a global pandemic. This study also explores the spatiotemporal aspects of lockdown and confinement measures on coronavirus diffusion, human mobility, and air quality. Additionally, we discuss policy implications, which will be helpful for policy makers to take prompt actions to moderate the severity of the pandemic and improve urban environments by adopting data-driven analytic methods.
We introduce network science methods to uncover inherent characteristics of functional regions. An aggregate spatial interaction network is constructed based on a large mobile phone data set including 431 million mobile calls made by 10 million anonymous customers over one month and the geographic locations of the mobile base towers involved in each call. We use Thiessen polygons (termed ‘cells’) as the unit of analysis to approximate the service area of each mobile base tower. Major findings encompass the following three aspects. First, cells with high betweenness centrality are linearly distributed in space, which closely aligns with major transportation corridors. We find that this pattern can be explained by analysing the characteristics of calling activities on transportation networks. Second, we detect a two‐level hierarchy of communities that correspond well to county and prefecture‐level administrative unit boundaries. Lastly, almost every community identified at the two hierarchical levels contains a cell with high betweenness. These cells are located near the political and economic centres and play the role of hubs in the regional socio‐economic system. This research demonstrates that networks built from mobile phone data provide new understandings of spatial interactions and regional structures.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.