Date Thesis Awarded


Access Type

Honors Thesis -- Open Access

Degree Name

Bachelors of Science (BS)


Data Science


Dan Runfola

Committee Members

Carrie Dolan

Anthony Stefanidis


Monitoring the spread of an outbreak of disease (such as COVID-19) is an important component of any coordinated pandemic response. Across the globe, our ability to conduct such monitoring - especially at early stages of the COVID- 19 pandemic - was highly limited due to a lack of public reporting mechanisms. Today, the process of case data collection remains expensive and, in some regions, is subject to political considerations. Researchers have turned to some techniques leveraging Google Trends and Twitter data to overcome limitations in public data sources. Here, we provide another approach which leverages satellite information to provide estimates of case counts. Visible features in imagery - such as vehicles in parking lots, or temporary structures at hospitals - should convey some information about underlying disease spreads. We explore the use of a ResNet50V2-LSTM hybrid model that is trained on satellite information, seeking to predict case counts across counties in the USA using imagery alone. Using solely this imagery, this model produced an overall rate of error of 4.55%. We discuss advantages and drawbacks of this approach, and how some future directions may aid us in overcoming contemporary limits.