Impact analysis of environmental and social factors on early-stage COVID-19 transmission in China by machine learning

Confounding amplifies the effect of environmental factors on COVID-19

The global COVID-19 pandemic has severely impacted human health and socioeconomic development, posing an enormous public health challenge. Extensive research has been conducted into the relationship between environmental factors and the transmission of COVID-19. However, numerous factors influence the development of pandemic outbreaks, and the presence of confounding effects on the mechanism of action complicates the assessment of the role of environmental factors in the spread of COVID-19. Direct estimation of the role of environmental factors without removing the confounding effects will be biased. To overcome this critical problem, we developed a Double Machine Learning (DML) causal model to estimate the debiased causal effects of the influencing factors in the COVID-19 outbreaks in Chinese cities. Comparative experiments revealed that the traditional multiple linear regression model overestimated the impact of environmental factors. Environmental factors are not the dominant cause of widespread outbreaks in China in 2022. In addition, by further analyzing the causal effects of environmental factors, it was verified that there is significant heterogeneity in the role of environmental factors. The causal effect of environmental factors on COVID-19 changes with the regional environment. It is therefore recommended that when exploring the mechanisms by which environmental factors influence the spread of epidemics, confounding factors must be handled carefully in order to obtain clean quantitative results. This study offers a more precise representation of the impact of environmental factors on the spread of the COVID-19 pandemic, as well as a framework for more accurately quantifying the factors influencing the outbreak.

Street-level built environment on SARS-CoV-2 transmission: A study of Hong Kong

Understanding the association between SARS-CoV-2 Spatial Transmission Risk (SSTR) and Built Environments (BE) is crucial for implementing effective pandemic prevention measures. Massive efforts have been made to examine the macro-built environment at the regional level, which has neglected the living service areas at the residential scale. Therefore, this study aims to explore the association between Street-level Built Environments (SLBE) and SSTR in Hong Kong from the 1st to the early 5th waves of the pandemic to address this gap. A total of 3693 visited/resided buildings were collected and clustered by spatial autocorrelation, and then Google Street View (GSV) was employed to obtain SLBE features around the buildings. Eventually, the interpretable machine learning framework based on the random forest algorithm (RFA)-based SHapley Additive exPlanations (SHAP) model was proposed to reveal the hidden non-linear association between SSTR and SLBE. The results indicated that in the high-risk cluster area, street sidewalks, street sanitation facilities, and artificial structures were the primary risk factors positively associated with SSTR, in low-risk cluster areas with a significant positive association with traffic control facilities. Our study elucidates the role of SLBE in COVID-19 transmission, facilitates strategic resource allocation, and guides the optimization of outdoor behavior during pandemics for urban policymakers.

High-resolution short-term prediction of the COVID-19 epidemic based on spatial-temporal model modified by historical meteorological data

In the global challenge of Coronavirus disease 2019 (COVID-19) pandemic, accurate prediction of daily new cases is crucial for epidemic prevention and socioeconomic planning. In contrast to traditional local, one-dimensional time-series data-based infection models, the study introduces an innovative approach by formulating the short-term prediction problem of new cases in a region as multidimensional, gridded time series for both input and prediction targets. A spatial-temporal depth prediction model for COVID-19 (ConvLSTM) is presented, and further ConvLSTM by integrating historical meteorological factors (Meteor-ConvLSTM) is refined, considering the influence of meteorological factors on the propagation of COVID-19. The correlation between 10 meteorological factors and the dynamic progression of COVID-19 was evaluated, employing spatial analysis techniques (spatial autocorrelation analysis, trend surface analysis, etc.) to describe the spatial and temporal characteristics of the epidemic. Leveraging the original ConvLSTM, an artificial neural network layer is introduced to learn how meteorological factors impact the infection spread, providing a 5-day forecast at a 0.01° × 0.01° pixel resolution. Simulation results using real dataset from the 3.15 outbreak in Shanghai demonstrate the efficacy of Meteor-ConvLSTM, with reduced RMSE of 0.110 and increased R 2 of 0.125 (original ConvLSTM: RMSE = 0.702, R 2 = 0.567; Meteor-ConvLSTM: RMSE = 0.592, R 2 = 0.692), showcasing its utility for investigating the epidemiological characteristics, transmission dynamics, and epidemic development.

Conditioning factors in the spreading of Covid-19 - Does geography matter?

There is evidence in literature that the spread of COVID-19 can be influenced by various geographic factors, including territorial features, climate, population density, socioeconomic conditions, and mobility. The objective of the paper is to provide an updated literature review on geographical studies analysing the factors which influenced COVID-19 spreading. This literature review took into account not only the geographical aspects but also the COVID-19-related outcomes (infections and deaths) allowing to discern the potential influencing role of the geographic factors per type of outcome. A total of 112 scientific articles were selected, reviewed and categorized according to subject area, aim, country/region of study, considered geographic and COVID-19 variables, spatial and temporal units of analysis, methodologies, and main findings. Our literature review showed that territorial features may have played a role in determining the uneven geography of COVID-19; for instance, a certain agreement was found regarding the direct relationship between urbanization degree and COVID-19 infections. For what concerns climatic factors, temperature was the variable that correlated the best with COVID-19 infections. Together with climatic factors, socio-demographic ones were extensively taken into account. Most of the analysed studies agreed that population density and human mobility had a significant and direct relationship with COVID-19 infections and deaths. The analysis of the different approaches used to investigate the role of geographic factors in the spreading of the COVID-19 pandemic revealed that the significance/representativeness of the outputs is influenced by the scale considered due to the great spatial variability of geographic aspects. In fact, a more robust and significant association between geographic factors and COVID-19 was found by studies conducted at subnational or local scale rather than at country scale.

Analysis of the influence of the stay-at-home order on the electricity consumption in Chinese university dormitory buildings during the COVID-19 pandemic

During the COVID-19 pandemic, strict stay-at-home orders have been implemented in many Chinese universities in virus-hit regions. While changes in electricity consumption in the residential sector caused by COVID-19 have been thoroughly analysed, there is a lack of insight into the impact of the stay-at-home order on electricity consumption in university dormitory buildings. Based on questionnaire survey results, this study adopted the statistical Kaplan-Meier survival analysis to analyse the energy-use behaviours of university students in dormitories during the COVID-19 pandemic. The electricity load profiles of the dormitory buildings before and during the implementation of the stay-at-home order were generated and compared to quantitatively analyse the influence of COVID-19 pandemic on the energy-use behaviours of university students, and the proposed load forecasting method was validated by comparing the forecasting results with monitoring data on electricity consumption. The results showed that: 1) during the implementation of the stay-at-home order, electricity consumption in the university dormitory buildings increased by 41.05%; 2) due to the increased use of illuminating lamps, laptops, and public direct drinking machines, the daily electricity consumption increased most significantly from 13:00 to 18:00, with an increase rate of 97.15%; and 3) the morning peak shifted backward and the evening peak shifted forward, demonstrating the effect of implementing the stay-at-home order on reshaping load profiles.

The environment, epidemics, and human health

In this editorial piece, the Editors of the Virtual Special Issue (VSI) "The environment, epidemics, and human health" comment on the papers accepted for publication, which were selected after peer-reviewing among all those manuscripts submitted to the Special Issue. In view of the title of the VSI, it is clear that its aim goes beyond the COVID-19 pandemic, trying to explore relations among environmental aspects, any kind of epidemics, and human health. However, COVID-19 is still hitting as a global and current main issue, causing that manuscripts dealing with this disease and the SARS-CoV-2 virus are of high relevance in the whole set of research papers published.

Study of the Economic, Environmental, and Social Factors Affecting Chinese Residents' Health Based on Machine Learning

The Healthy China Strategy puts realistic demands for residents' health levels, but the reality is that various factors can affect health. In order to clarify which factors have a great impact on residents' health, based on China's provincial panel data from 2011 to 2018, this paper selects 17 characteristic variables from the three levels of economy, environment, and society and uses the XG boost algorithm and Random forest algorithm based on recursive feature elimination to determine the influencing variables. The results show that at the economic level, the number of industrial enterprises above designated size, industrial added value, population density, and per capita GDP have a greater impact on the health of residents. At the environmental level, coal consumption, energy consumption, total wastewater discharge, and solid waste discharge have a greater impact on the health level of residents. Therefore, the Chinese government should formulate targeted measures at both economic and environmental levels, which is of great significance to realizing the Healthy China strategy.