Plant Phenology Supports the Multi-emergence Hypothesis for Ebola Spillover Events

Abstract

Ebola virus disease outbreaks in animals (including humans and great apes) start with sporadic host switches from unknown reservoir species. The factors leading to such spillover events are little explored. Filoviridae viruses have a wide range of natural hosts and are unstable once outside hosts. Spillover events, which involve the physical transfer of viral particles across species, could therefore be directly promoted by conditions of host ecology and environment. In this report, we outline a proof of concept that temporal fluctuations of a set of ecological and environmental variables describing the dynamics of the host ecosystem are able to predict such events of Ebola virus spillover to humans and animals. We compiled a data set of climate and plant phenology variables and Ebola virus disease spillovers in humans and animals. We identified critical biotic and abiotic conditions for spillovers via multiple regression and neural network-based time series regression. Phenology variables proved to be overall better predictors than climate variables. African phenology variables are not yet available as a comprehensive online resource. Given the likely importance of phenology for forecasting the likelihood of future Ebola spillover events, our results highlight the need for cost-effective transect surveys to supply phenology data for predictive modelling efforts.

Keywords: Climate; Climate change; Emerging infectious disease; Normalized Difference Vegetation Index; Phenology; Spillover.

Figure 1

a Map of localities of Ebola virus disease outbreaks (where exact coordinates could be obtained, small squares), climate data (large squares) and phenology data (circles). b Box plots for climate and phenology variables with significant inter-annual variation (see Table 1 for statistical results) between years with recorded Ebola human  + animal spillover events and years without known Ebola virus spillover events spanning the period of 1953–2016. Boxes represent 25–75% interval, whiskers represent non-outlier range, circles represent outliers, and stars represent extreme values. Lines connect medians of the same variables between years with spillover events and years without spillover events. Climate variables are shown in filled boxes, and phenology variable is shown in open boxes. (a) 10-Year average rainfall in Kibale National Park, (b) number of days with ≥ 0.254-mm rainfall per month (DP01), (c) number of days with ≥ 12.7-mm rainfall per month (DP05), (d) number of days with ≥ 25.4-mm rainfall per month (DP10), (e) highest daily total of precipitation per month in mm (EMXP), (f) lowest daily minimum temperature for the month in °C (EMNT), (g) monthly mean minimum temperature in °C (MMNT), (h) total precipitation, in mm/10, for the month (TPCP), (i) second independent component of Normalized Difference Vegetation Index (IC2 NDVI) anomaly between July and December.

Figure 2

Performance for annual time series regression of animal/human spillover events from neural network modelling (SANN) using only climate PCs, only phenology PCs and climate and phenology PCs combined as sets of input variables. a Time series predictions for the observed number of human and animal spillover (closed large circles/red) versus the predicted numbers from best retained models (500 network iterations) of climate variables only (small closed circles/blue), phenology variables only (open squares/green) and climate/phenology combined as input data sets (open circles/grey). b Correlation scatter plots between observed spillovers and predicted spillovers using models with inputs: climate variables only (small closed circles/blue), phenology variables only (open squares/green) and climate/phenology combined as input data sets (open circles/grey). correlation with climate + phenology model r = 0.7663, P = 0.00008; correlation with only climate model r = 0.6254, P = 0.0032; correlation with only phenology r = 0.8860, P ≤ 0.000001 (Color figure online).

Figure 3

Seasonality of Ebola virus spillover events (humans + animals, standardised values, closed circles), the standardised average of climate PCs 1-3 (open circles) and the standardised average of phenology PCs 1–6 (closed squares). Standardised values for single phenology PCs 1–6 are shown as background lines (no symbols). Both September and December spikes in recorded human + animal Ebola virus spillover events (virus symbols) are associated with lower values of the average of phenology PCs 1–6 (fruit/leaf symbols), but only for the September spike with average climate variable changes (weather symbols). Curves are spline-fitted.

Figure 4

Changes in the proportion of plants bearing fruits between months with no recorded spillovers (open bars) and months with recorded spillovers (closed bars). Dots represent raw data points, column height means, bars represent errors. Plant species shown here were significant predictors in the regression model for number of spillovers per month for the period 1993–2002 in Kahuzi-Biega National Park. Original data from Yamagiwa et al. (2008).