Next generation mosquito control through technology-driven trap development and artificial intelligence guided detection of mosquito breeding habitats

Project Summary Each year, approximately 400 million people are infected with an arboviral disease from the bite of an Aedes spp mosquito. Aedes spp. mosquitoes are a leading public health threat due to their high competency to vector multiple pathogens, their preference to bite humans, and their ability to adapt to new domestic environments. In the US, reintroduction and establishment of Aedes aegypti and Aedes albopictus mosquito populations has resulted in local epidemics of Zika, dengue and chikungunya in the past decade. Unfortunately, mosquito control programs in the US generally operate with limited budgets, forcing the majority of insecticide spraying to be conducted in reaction to population exposure instead of targeted prevention, which has also contributed to considerable growth of insecticide resistant populations, yielding a widening gap of infrastructure vulnerability. Our current proposal aims to leverage existing technologies from non-health disciplines to advance mosquito detection and abatement. We propose to validate the use of technology-driven mosquito traps that allow for high- throughput identification and counting of Aedes mosquitos at various life stages to inform decision making when selecting areas for insecticide spraying and abatement. Additionally, we propose to develop rigorous remote sensing workflows for identification of neighborhood-level Aedes abundance risk and rapid detection of individual Aedes mosquito breeding habitats on a household-level. This innovative proposal uses multi-year and real-world mosquito data from two different metropolitan areas to statistically adjust for variances in geographic ecologies, urban microclimates, seasonal climate patterns, and annual weather events. Our study will result in low-cost tools immediately ready for broad distribution and integration by vector control agencies nationally. The outcomes of our study have promise to directly impact vector control agency's decision-making processes for mosquito trapping site selection, inform preventative abetment protocols, and shorten the time required for mosquito collection and identification. Further, integration of our proposed technology traps and informed site selection maps will increase overall collection volumes while preserving scarce resources for local vector control agencies. This proposal has the potential to create a paradigm shift in how we approach vector control globally, with a targeted intervention resulting in significant economic, environmental, and clinical benefits.