experimental investigation and modelling of total chlorophyll extraction from mixed microalgae using neural network

Algae represent a diverse group of photosynthetic and microscopic entities that are recognized as significant contributors to biomass generation and the synthesis of valuable biological compounds. chlorophyll, which is the principal pigment present within these organisms, is integral in the process of light absorption and its subsequent transformation into chemical energy, thereby playing a crucial role in the metabolic pathways that result in the production of oxygen and organic matter. in the present study, a neural network model was created to determine the best chlorophyll extraction method, incorporating factors like initial algae concentration (2, 4, and 6 g/l), temperature (30, 40, and 50 °c), and time. by training the model on a substantial portion of the dataset (70%) and configuring it with 8 hidden neurons, significant results were obtained correlation coefficient of 0.9942 and a minimal error of 0.0178, showcasing the model’s effectiveness. among the various factors investigated, the duration of extraction was recognized as the preeminent factor influencing the efficacy of chlorophyll extraction, as corroborated by the results of the model. therefore, the neural network model created in this study will facilitate the discovery of more efficient techniques for extracting chlorophyll from microalgae in the future.