Ensemble forecast of human West Nile virus cases and mosquito infection rates

Abstract

West Nile virus (WNV) is now endemic in the continental United States; however, our ability to predict spillover transmission risk and human WNV cases remains limited. Here we develop a model depicting WNV transmission dynamics, which we optimize using a data assimilation method and two observed data streams, mosquito infection rates and reported human WNV cases. The coupled model-inference framework is then used to generate retrospective ensemble forecasts of historical WNV outbreaks in Long Island, New York for 2001-2014. Accurate forecasts of mosquito infection rates are generated before peak infection, and >65% of forecasts accurately predict seasonal total human WNV cases up to 9 weeks before the past reported case. This work provides the foundation for implementation of a statistically rigorous system for real-time forecast of seasonal outbreaks of WNV.

Figure 1. Scatterplot of the annual total number of human WNV cases in Suffolk County, NY, USA as a function of the annual sum of weekly observed mosquito WNV infection rates.

The two quantities are highly linearly correlated (r=0.76, P=0.002).

Figure 2. Average weekly observations and free model simulation of infectious mosquito rates and human WNV cases.

Only 25% of human cases had been reported by week 33, the week that average observations of infectious mosquitoes peaked. Average weekly observations (2001-2014, red *) and free model simulation (cyan o).

Figure 3. Ten bi-weekly forecasts of infectious mosquitoes and human WNV cases for 2010.

The magenta lines are the ensemble mean forecasts, the grey area is the spread of the ensemble forecast (light grey represents area between the 10th and 90th percentile and the darker grey area represents the spread between the 25th and 75th percentile), blue lines are the ensemble mean posterior distribution, black x's are data points assimilated into the model and red * are future observations.

Figure 4. Results for 2001–2014 retrospective forecasts.

Shown are the fraction of forecasts accurate as a function of lead week for the metrics human WNV cases (blue), peak timing (week of peak mosquito infection rates, orange), peak infection rate (yellow) and total infectious mosquitoes (purple). A forecast was deemed accurate if: (1) peak timing was within ±1 week of the observed peak of infectious mosquitoes; (2) peak infection rate was within ±25% of the observed peak infection rate; (3) total infectious mosquitoes were within ±25% of the observed; and (4) human WNV cases were within ±25% or ±1 case of the total number of reported cases, whichever was larger. Note that for all metrics lead week is shown with respect to the week of peak mosquito infection.