Early Detection of Blue Green Algae Blooms Using Artificial Intelligence
University
Shawnee State University
Major
Digital Simulation and Gaming Engineering Technology
Presentation Types
Oral Group Presentation
Abstract
Chronic blue-green algae blooms in drinking water and ecosystems consume oxygen and produce nitrogen at levels toxic to the environment and its inhabitants, including humans who rely on clean drinking water. We describe a neural network-based artificial intelligence which aims to find the algae blooms early enough to prevent or mitigate the effects of such blooms. We further discuss the training procedure of the neural network used to detect algae blooms as early as possible. As an added benefit for remote or economically distressed regions, the detection equipment needed for implementation is simple to use and extremely cost effective.
We conclude with further potential applications of the technique to a variety of problems related to water testing.
Human Subjects
no
Faculty Mentor Name
R. Duane Skaggs
Faculty Mentor Title
Associate Professor
Faculty Mentor Academic Department
Engineering Technologies
Recommended Citation
Ludowese, Nicholas; Reynolds, Demetrius; Knauff, Lane; and Adams, Chase, "Early Detection of Blue Green Algae Blooms Using Artificial Intelligence" (2021). Celebration of Scholarship. 3.
https://digitalcommons.shawnee.edu/cos/2021/trustees/3
Early Detection of Blue Green Algae Blooms Using Artificial Intelligence
Chronic blue-green algae blooms in drinking water and ecosystems consume oxygen and produce nitrogen at levels toxic to the environment and its inhabitants, including humans who rely on clean drinking water. We describe a neural network-based artificial intelligence which aims to find the algae blooms early enough to prevent or mitigate the effects of such blooms. We further discuss the training procedure of the neural network used to detect algae blooms as early as possible. As an added benefit for remote or economically distressed regions, the detection equipment needed for implementation is simple to use and extremely cost effective.
We conclude with further potential applications of the technique to a variety of problems related to water testing.