Predictive modelling and optimization of an airlift bioreactor for selenite removal from wastewater using artificial neural networks and particle swarm optimization.

Selenite (Se4+) is the most toxic of all the oxyanion forms of selenium. In this study, a feed forward back propagation (BP) based artificial neural network (ANN) model was developed for a fungal pelleted airlift bioreactor (ALR) system treating selenite-laden wastewater. The performance of the bioreactor, i.e., selenite removal efficiency (REselenite) (%) was predicted through two input parameters, namely, the influent selenite concentration (ICselenite) (10 mg/L - 60 mg/L) and hydraulic retention time (HRT) (24 h - 72 h). After training and testing with 96 sets of data points using the Levenberg-Marquardt algorithm, a multi-layer perceptron model (2-10-1) was established. High values of the correlation coefficient (0.96 ≤ R ≤ 0.98), along with low root mean square error (1.72 ≤ RMSE ≤ 2.81) and mean absolute percentage error (1.67 ≤ MAPE ≤ 2.67), clearly demonstrate the accuracy of the ANN model (> 96%) when compared to the experimental data. To ensure an efficient and economically feasible operation of the ALR, the process parameters were optimized using the particle swarm optimization (PSO) algorithm coupled with the neural model. The REselenite was maximized while minimizing the HRT for a preferably higher range of ICselenite. Thus, the most favourable optimum conditions were suggested as: ICselenite - 50.45 mg/L and HRT - 24 h, resulting in REselenite of 69.4%. Overall, it can be inferred that ANN models can successfully substitute knowledge-based models to predict the REselenite in an ALR, and the process parameters can be effectively optimized using PSO.

Selenite removal from wastewater using fungal pelleted airlift bioreactor.

This study investigated the removal of selenite from wastewater using the fungus Asergillus niger KP isolated from a laboratory scale inverse fluidized bed bioreactor. The effect of different carbon sources and initial selenite concentration on fungal growth, pellet formation and selenite removal was first examined in a batch system. The fungal strain showed a maximum selenite removal efficiency of 86% in the batch system. Analysis of the fungal pellets by field-emission scanning electron microscopy, field-emission transmission electron microscopy and energy-dispersive X-ray spectroscopy revealed the formation of spherical-shaped elemental selenium nanoparticles of size 65-100 nm. An increase in the initial selenite concentration in the media resulted in compact pellets with smooth hyphae structure, whereas the fungal pellets contained hair like hyphae structure when grown in the absence of selenite. Besides, a high initial selenite concentration reduced biomass growth and selenite removal from solution. Using an airlift reactor with fungal pellets, operated under continuous mode, a maximum selenite removal of 94.3% was achieved at 10 mg L-1 of influent selenite concentration and 72 h HRT (hydraulic retention time). Overall, this study demonstrated very good potential of the fungal-pelleted airlift bioreactor system for removal of selenite from wastewater. Graphical abstract.