Random forest regression on joint role of meteorological variables, demographic factors, and policy response measures in COVID-19 daily cases: global analysis in different climate zones.

Different sources of factors in environment can affect the spread of COVID-19 by influencing the diffusion of the virus transmission, but the collective influence of which has hardly been considered. This study aimed to utilize a machine learning algorithm to assess the joint effects of meteorological variables, demographic factors, and government response measures on COVID-19 daily cases globally at city level. Random forest regression models showed that population density was the most crucial determinant for COVID-19 transmission, followed by meteorological variables and response measures. Ultraviolet radiation and temperature dominated meteorological factors, but the associations with daily cases varied across different climate zones. Policy response measures have lag effect in containing the epidemic development, and the pandemic was more effectively contained with stricter response measures implemented, but the generalized measures might not be applicable to all climate conditions. This study explored the roles of demographic factors, meteorological variables, and policy response measures in the transmission of COVID-19, and provided evidence for policymakers that the design of appropriate policies for prevention and preparedness of future pandemics should be based on local climate conditions, population characteristics, and social activity characteristics. Future work should focus on discerning the interactions between numerous factors affecting COVID-19 transmission.

Association between meteorological factors and COVID-19 transmission in low- and middle-income countries: A time-stratified case-crossover study.

BACKGROUND: Evidence is limited regarding the association between meteorological factors and COVID-19 transmission in low- and middle-income countries (LMICs). OBJECTIVE: To investigate the independent and interactive effects of temperature, relative humidity (RH), and ultraviolet (UV) radiation on the spread of COVID-19 in LMICs. METHODS: We collected daily data on COVID-19 confirmed cases, meteorological factors and non-pharmaceutical interventions (NPIs) in 2143 city- and district-level sites from 6 LMICs during 2020. We applied a time-stratified case-crossover design with distributed lag nonlinear model to evaluate the independent and interactive effects of meteorological factors on COVID-19 transmission after controlling NPIs. We generated an overall estimate through pooling site-specific relative risks (RR) using a multivariate meta-regression model. RESULTS: There was a positive, non-linear, association between temperature and COVID-19 confirmed cases in all study sites, while RH and UV showed negative non-linear associations. RR of the 90th percentile temperature (28.1 °C) was 1.14 [95% confidence interval (CI): 1.02, 1.28] compared with the 50th percentile temperature (24.4 °C). RR of the10th percentile UV was 1.41 (95% CI: 1.29, 1.54). High temperature and high RH were associated with increased risks in temperate climate but decreased risks in tropical climate, while UV exhibited a consistent, negative association across climate zones. Temperature, RH, and UV interacted to affect COVID-19 transmission. Temperature and RH also showed higher risks in low NPIs sites. CONCLUSION: Temperature, RH, and UV appeared to independently and interactively affect the transmission of COVID-19 in LMICs but such associations varied with climate zones. Our results suggest that more attention should be paid to meteorological variation when the transmission of COVID-19 is still rampant in LMICs.