Integrated CO2 Capture and Nutrient Removal by Microalgae Chlorella vulgaris and Optimization Using Neural Network and Support Vector Regression

Microalgae are useful for the mitigation of carbon from point source CO 2 emission flue gases. The main aim of this work was to maximize the growth of microalgae Chlorella vulgaris in a pilot scale photobioreactor as well as CO2 and nutrient removal. Chlorella vulgaris was cultured in three bubble column photobioreactors with the working volumes of 4, 9.6 and 16 L and CO2 concentration of power plant flue gas (ranging from 0.04 to 15%), flow rate from 50 to 150 mL min(-1) and the diameter of the photobioreactors were considered as study parameters. Optimal condition observed was for the reactor with the diameter of 10.5 cm, CO2 concentration of 7.5% and flowrate of 100 mL min(-1) with the maximum cell concentration and average CO2 removal of 3.63 g. L-1 and 91.7%, respectively. Besides, total phosphorus removal of 100% and total nitrogen removal efficiency in the range of 81.5-94.1% observed for all the experiments which demonstrated a desirable design of bioreactors with high mixing efficiency. Finally, the effects of different studied parameters on the biomass concentration were predicted by Artificial Neural Network (ANN) and Support Vector Regression (SVR) methods. The Levenberg-Marquardt algorithm and Gaussian kernel with correlation coefficient values of 0.9937 and 0.9964 were selected as the optimal network. [GRAPHICS] .