Hi! My name is Om, and I'm a high school junior. This summer, I participated in the SEES Internship Program a partnership with UT Austin and NASA, and worked with the Mosquito Mapper cohort. The goal of the Mosquito Mappers is to collect mosquito larva, analyze this data, and draw conclusions about mosquitoes and their land cover habitats.
I started the internship in early June with an introductory webinar where I met scientists, mentors, peer mentors, and more. I gained an overview of the expectations and outcomes that I would strive for during the following months. The goal of the Mosquito Mapper team was to study vector-borne diseases through environmental factors that affect the behaviors of those vectors. As our cohort's name suggests, we focused primarily on mosquitoes!
Every Tuesday morning and each Wednesday during this eight-week internship, I learned how to use satellite data, create a UI to display data, and other current mosquito vector research alongside our mentors or a guest scientist. To enhance the skills taught in these webinars, we worked on 2-3 assignments weekly. The assignments were based on reading research papers on mosquito analysis and then posting our thoughts in discussions with other interns, which took place via Canvas. We built mosquito traps and identified mosquito larval specimens using a clip-on microscope for our mobile phones, provided by the SEES program. In addition, I utilized the GLOBE Observer app to make land cover observations and mosquito observations through the traps I built alongside my peers. After collecting data, developing our skills, and hearing from amazing speakers through the cohort and NASA SEES speaker series, I was ready to begin my project!
My team's project was based on the premise that species distribution models (SDMs) that use climate variables to make binary predictions are effective for niche prediction in current and future climate scenarios. Our study defined a Hutchinson hypervolume with temperature, humidity, air pressure, precipitation, and cloud cover climate vectors collected from the National Oceanic and Atmospheric Administration that we matched to mosquito presence and absence points extracted from GLOBE Observer and the National Ecological Observatory Network. We then trained an 86% accurate Random Forest model that operates on binary classification. Given a location and date input, the model produces a threat level based on the number of decision trees that vote for a presence label. The feature importance chart and regression show a positive, linear correlation between humidity and mosquito threat and between temperature and threat below a threshold of 28°C. We then visualized the results in an interactive ArcGIS Dashboard. In accordance with the statistical analysis, we found high threat clusters in warm, humid regions. We also built a device leveraging GPS smartphone technology and the IoT to collect and analyze data on the edge. Users can see, in real-time, a mosquito threat level index without cloud connectivity with application uses in remote areas.
Overall, I had a great experience with the NASA SEES program and found a research project and group that will help counter some of the worldwide health problems regarding mosquitoes. I would like to thank all the mentors, speakers, and teammates that allowed me to have a wonderful experience and project.
Om is a high school junior from California working on a research project this summer using the GLOBE Observer Mosquito Habitat Mapper. His virtual internship is part of a collaboration between the Institute for Global Environmental Strategies (IGES) and the NASA Texas Space Grant Consortium (TSGC) to extend the TSGC Summer Enhancement in Earth Science (SEES) internship for US high school (http://www.tsgc.utexas.edu/sees-internship/). He shares his experience this summer in this guest blog post.
