Artificial Neural Network (ANN)

A method for optimal structure selection of hidden layers of the artificial neural network (ANN) is proposed. Its main idea is the practical application of several internal structures of ANN and further calculation of the error of each hidden layer structure using identical data sets for ANN training. The method is based on the alternate comparison of the expected result values and the actual results of the feedforward artificial neural networks with a different number of inner layers and a different number of neurons on each layer.

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.