The influence of temperature on the seasonality of historical plague outbreaks

Abstract

Modern plague outbreaks exhibit a distinct seasonal pattern. By contrast, the seasonality of historical outbreaks and its drivers has not been studied systematically. Here, we investigate the seasonal pattern, the epidemic peak timing and growth rates, and the association with latitude, temperature, and precipitation using a large, novel dataset of plague- and all-cause mortality during the Second Pandemic in Europe and the Mediterranean. We show that epidemic peak timing followed a latitudinal gradient, with mean annual temperature negatively associated with peak timing. Based on modern temperature data, the predicted epidemic growth of all outbreaks was positive between 11.7°C and 21.5°C with a maximum around 17.3°C. Hence, our study provides evidence that the growth of plague epidemics across the whole study region depended on similar absolute temperature thresholds. Here, we present a systematic analysis of the seasonality of historical plague in the Northern Hemisphere, and we show consistent evidence for a temperature-related process influencing the epidemic peak timing and growth rates of plague epidemics.

Keywords: Yersinia pestis; climate; epidemic growth; seasonality; second plague pandemic; temperature.

Figure 1.

The distribution of plague deaths by months from all recorded plague years shows a distinct seasonality pattern for all five places ((a) Alexandria, (b) Algiers, (c) Barcelona, (d) London, and (e) Vienna) with multiple outbreaks. The boxes encompass the 25th to 75th percentiles, the whiskers extend to the maximum or to maximally 1.5 times the interquartile range. The vertical lines denote the medians. Few outliers (dots) have been omitted from the plot for clarity.

Figure 2.

The AAP of monthly plague deaths suggests a latitudinal gradient with a shift of epidemic activity towards the end of the year for increasing latitude. (Online version in colour.)

Figure 3.

Association of annual mean temperature (a) and annual mean precipitation (b) with epidemic peak week. The bands show the 95% CIs for the fit from a univariable, linear GEE model.

Figure 4.

Distribution of predicted time-varying growth rates by temperature. (a) Histogram of positive (green) and zero or negative growth (red) and (b) scatter plot of time-varying growth rates for the full dataset. The red line and ribbon indicate the fit and 95% CI from a univariable GAMM model. The maximum growth was predicted at 17.3°C. (Online version in colour.)