Mathematical model is a good approach to deal with the coupling effects of governing parameters in algal bloom growth. Amongmanymodels to deal with combining factors and data-based supervised learning classifiers, the Artificial Neural Network (ANN) has the most significant impact on the development of bloom pattern.
In previous work (Hushchyna and Nguyen-Quang, 2017), we have introduced the Modified Redfield Ratio (MRR) to estimate algal blooms occurring in Mattatall Lake, Nova Scotia (Canada). The goals of this paper are to test this modified index based on nutrient level to estimate bloom patterns via field experimental data and by the mathematical simulation with a supervised learning model Artificial Neural Network.
Many waterbodies across Nova Scotia (Canada) have been experiencing algal blooms occurring in large numbers and diversity, without knowledge or understanding about their causes and effects. Algal blooms have appeared in Mattatall Lake (ML) and other lakes of the province in recent years. ML experienced severe algal blooms in 2013. During the fall of 2014, massive algal blooms appeared in ML, and persisted until late December 2014. The blooms have a pattern of being nontoxic in the summer and potentially toxic in the fall-winter season, with nutrients increasing on a monthly basis.