Student Research Reports

View Research Report

Culex mosquitoes pose a large threat to humans and other species due to their ability to carry deadly viruses such as the West Nile and Zika Viruses. Washington D.C. in particular has a humid subtropical climate that is ideal as habitats for mosquito breeding. Thus, tracking the habitats and breeding patterns of mosquitos in Washington D.C. is crucial towards addressing local public health concerns. Although fieldwork techniques have improved over the years, tracking and analyzing mosquitos is difficult, dangerous, and time-consuming. In this work, we propose a solution to this issue by creating a Culex mosquito abundance predictor using machine learning techniques to determine under which conditions Culex mosquitoes thrive and reproduce. We used four environmental variables to conduct this experiment: precipitation, specific humidity, enhanced vegetation index (EVI), and surface skin temperature. We obtained sample data of these variables in the Washington D.C. areas from the NASA Giovanni Earth Science Data system, as well as mosquito abundance data collected by the D.C. government. Using these data, we created and compared four different machine learning regression models: Random Forest, Decision Tree, Support Vector Machine, and Multi-Layer Perceptron. For each model, we searched for the optimal configurations to get the best fitting possible. It was discovered that the Random Forest Regressor produced the most accurate prediction of mosquito abundance in an area with the four environment variables, with a mean average error of 3.3. It was also found that EVI was the most significant factor in determining the mosquito abundance. Models and findings from this research are going to be utilized by public health programs for mosquito related disease observations and predictions. Keywords: mosquito breeding patterns, machine learning techniques, Culex mosquitoes, ecological variables