SatNet: A Low-Cost, Neural-Network based Algorithm Utilizing Publicly
Available Data for Disease Hotspot Detection
Abstract
The rapid spread of infectious diseases poses a significant global
health challenge, requiring timely and accurate detection for effective
intervention. Traditional disease detection services, such as the
Centers for Disease Control and Prevention (CDC) and the World Health
Organization (WHO), play a crucial role in monitoring and responding to
outbreaks. However, these services are largely inaccessible to people
around the world due to their high costs and resource-intensive
processes because they often rely on expensive sources of data.
Fortunately, satellite images are a great alternative source of data as
modern satellites can provide detailed images which clearly display a
region’s financial status and pollution levels: two key metrics in
potential disease outbreaks. Therefore, this study aimed on developing a
more affordable algorithm (SatNet) that utilizes publicly available
satellite imagery to perform disease hotspot detection. The algorithm
works by retrieving zoomed-in satellite images of the city inputted by
the user and feeding these images into a novel, hybrid recursive
convolutional neural network. This model, designed to classify regions
within the images as low income, high-income, or industrial areas, was
trained and tested on a custom data set consisting of 7,448 images and
was able to achieve a 94.872 training accuracy and 84.183 testing
accuracy. The output of this model is then used to create a detailed
heatmap for the city which clearly indicates the specific regions in
most danger of disease outbreaks. Overall, the affordability and
accessibility of SatNet will allow governments/organizations around the
world to provide their people with the healthcare they need and
significantly reduce the spread of diseases in an increasingly
interconnected world.