PS 82-218
High-frequency fluctuations in mosquito populations: Dynamical and observational implications

Friday, August 15, 2014
Exhibit Hall, Sacramento Convention Center
Yun Jian, Nicholas School of the Environment, Duke University, Durham, NC
Background/Question/Methods

Our understanding of mosquito population dynamics is still quite incomplete. In particular, we lack a quantitative description, and even adequate observations, of the full range of temporal scales over which mosquito abundance fluctuates in natural conditions.  In this study, we address the problem of identifying the variability scales of mosquito populations, the processes generating them, and the representativeness of observations at different sampling scales. We analyzed a 9-year daily abundance data for Aedes vexans and Culiseta melanura in North Carolina. We explored the population fluctuations of these two species over periods between 2 days and 9 years using Discrete Fourier Transform (DFT). We resampled the daily observation at a 7-day frequency and computed the AutoCorrelation Function (ACF) and the Partial AutoCorrelation Function (PACF) for the original dataset and for the sub-sampled ones to evaluate how a degraded temporal resolution affects the fluctuation captured by the time series. Furthermore, an Individual-Based life cycle Simulation model (IBS) was constructed and its result was compared to density-dependent population models to identify the statistical properties in the observed mosquito abundance associated with distinct population dynamical mechanisms and to investigate the potential ecological processes generating the observed fluctuations in the abundance time series. 

Results/Conclusions

Both Aedes vexans and Culiseta melanura exhibit fast abundance fluctuations. Significant cycles with periods shorter than 2 weeks are found in the daily observation. We argue that such short time scale fluctuations, rather than to birth/death processes, are likely due to varying mosquito activity in response to rapid changes in meteorological conditions, a process, we suggest, neglected or misunderstood in existing conceptual and predictive representations  mosquito population dynamics. We find that the range of time scales over which mosquito population variability takes place can be divided into three main parts: at small time scales (the microscale, indicatively 1 day-2 weeks) apparent population fluctuations are driven by behavioral responses to rapid changes in weather conditions, at intermediate scales (2 weeks-1 month) endogenous dynamics dominate, fingerprinted by distinct peaks in the power spectrum, at longer scales (1 month-several years) mosquito populations respond to seasonal and inter-annual environmental changes. We conclude that observations of mosquito populations should be based on a sub-weekly sampling frequency and that predictive models of mosquito population abundance must include behavioral dynamics to separate the effects of a varying mosquito activity from actual changes in the number of mosquito individuals.