Temperature Decreases Spread Parameters of the New Covid-19 Case Dynamics

Abstract

(1) Background: The virulence of coronavirus diseases due to viruses like SARS-CoV or MERS-CoV decreases in humid and hot weather. The putative temperature dependence of infectivity by the new coronavirus SARS-CoV-2 or covid-19 has a high predictive medical interest. (2) Methods: External temperature and new covid-19 cases in 21 countries and in the French administrative regions were collected from public data. Associations between epidemiological parameters of the new case dynamics and temperature were examined using an ARIMA model. (3) Results: We show that, in the first stages of the epidemic, the velocity of contagion decreases with country- or region-wise temperature. (4) Conclusions: Results indicate that high temperatures diminish initial contagion rates, but seasonal temperature effects at later stages of the epidemy remain questionable. Confinement policies and other eviction rules should account for climatological heterogeneities, in order to adapt the public health decisions to possible geographic or seasonal gradients.

Keywords: covid-19; heat inhibition; temperature sensitivity; weather-dependent virulence.

Figure 1

Left: Start of covid-19 epidemic in countries with various climates. Right: Daily number of new cases from 25 January until 14 March 2020 in France.

Figure 2

(a) Virulence of covid-19 in liquids and secretions (from [27]); (b) Linear regression of negative initial autocorrelation slope on mean weather temperature of six countries, France, UK, Spain, Italy, China and Chile (Pearson correlation coefficient R = 0.97, one-tailed p = 0.001). (c) Autocorrelation function A for three countries, France, Spain and Chile showing during February until 14 March 2020 a decrease in the positive correlation duration and the negative initial slope of the auto-correlation curve when the mean temperature of the country increases.

Figure 3

Daily increase in confirmed COVID-19 cases for administrative regions of France on 6 March 2020 (filled symbols, dotted line, log regression model) and on 15 March 2020 (circles, interrupted line, exponential regression model).

Figure 4

Slope of exponential model fitted to data in Table 3 as a function of mean annual temperature in that country. The Pearson correlation coefficient is R = −0.568, one-tailed p = 0.0036.