Using machine learning to understand microgeographic determinants of the Zika vector, Aedes aegypti

Abstract

There are limited data on why the 2016 Zika outbreak in Miami-Dade County, Florida was confined to certain neighborhoods. In this research, Aedes aegypti, the primary vector of Zika virus, are studied to examine neighborhood-level differences in their population dynamics and underlying processes. Weekly mosquito data were acquired from the Miami-Dade County Mosquito Control Division from 2016 to 2020 from 172 traps deployed around Miami-Dade County. Using Random Forest, a machine learning method, predictive models of spatiotemporal dynamics of Ae. aegypti in response to meteorological conditions and neighborhood-specific socio-demographic and physical characteristics, such as land-use and land-cover type and income level, were created. The study area was divided into two groups: areas affected by local transmission of Zika during the 2016 outbreak and unaffected areas. Aedes aegypti populations in areas affected by Zika were more strongly influenced by 14- and 21-day lagged weather conditions. In the unaffected areas, mosquito populations were more strongly influenced by land-use and day-of-collection weather conditions. There are neighborhood-scale differences in Ae. aegypti population dynamics. These differences in turn influence vector-borne disease diffusion in a region. These results have implications for vector control experts to lead neighborhood-specific vector control strategies and for epidemiologists to guide vector-borne disease risk preparations, especially for containing the spread of vector-borne disease in response to ongoing climate change.