Prediction of Algal Blooms in the Great Lakes through a Convolution Neural Network of Remote Sensing Data

Harmful algal blooms (HABs) are the proliferation of algae due to eutrophication and have severe repercussions to the ecological balance in many water bodies, due to the toxins the algae produce. Additionally, the identification and prediction of these HABs has been a challenge in the scientific community due to the interactions between both biological and physical processes that cause the HABs. Here, we used remote sensing data to bypass these issues; remote sensing data provides significant information about the coverage of chlorophyll which can be used to locate HABs. Using this indicator of HABs, we trained a Convolution Neural Network (CNN) to identify nine types of algal blooms, using 25 epochs of 900 images, which can predict algal bloom shapes with an 80 percent accuracy. This approach of HAB identification can easily be applied to other aquatic ecosystems where remote sensing data is present.