Legionnaires’ disease is a severe pneumonia with a 1 in 10 fatality rate, and cooling towers containing Legionella bacteria are a common source of community outbreaks. Outbreak investigators need to find and test cooling towers to stop the outbreak and prevent more illnesses and deaths. Manual visual scanning of aerial imagery for cooling towers during investigations requires expertise, is labor-intensive, and can be error-prone.
We developed TowerScout, a tool that uses machine learning to automatically detects cooling towers visible from aerial imagery across the United States.
The Legionella team is excited about the TowerScout resource for identifying visible cooling towers using aerial satellite imagery. During outbreak investigations, TowerScout enables us to quickly identify visible cooling towers using this automated tool rather than manually searching across images, which is a time- and personnel-intensive process. Additionally, TowerScout may enable public health to prospectively identify cooling towers for building a registry or conducting outreach. By sharing water management program and Legionella control resources with cooling tower owners, public health can work towards preventing future outbreaks of Legionnaires’ disease.
— Legionella team, Centers for Disease Control and Prevention