Application of artificial neural network for the prediction of biosorption capacity of immobilized Bacillus subtilis for the removal of cadmium ions from aqueous solution

•Immobilized biomass of Bacillus subtilis was used as efficient biosorbent.•Its biosorption capacity is higher as compared to other biosorbents i.e. 251.91 mg/g.•Artificial neural network model was applied to predict the biosorption capacity.•Experimental data was successfully simulated using ANN model.•The biosorbent was successfully regenerated using 0.1 M HCl as desorbing agent.

Artificial neural network (ANN) model was applied for predicting the biosorption capacity of immobilized Bacillus subtilis beads (IBSB) for cadmium ions from aqueous solution. The effect of pH, contact time, biosorbent dosage, temperature and initial cadmium ions concentration was investigated. The equilibrium biosorption capacity of IBSB was found to be 251.91 mg/g at optimum pH of 5.91, temperature of 45 °C and equilibrium time of 3 h for an initial concentration of 496.23 mg/L. The interaction between the biosorbent and cadmium ions was confirmed using FTIR and SEM analysis. The experimental results were simulated using ANN model. Levenberg Marquardt algorithm was used for the training of this network with hyperbolic tangent sigmoid as transfer function. The applied model successfully predicted cadmium biosorption capacity with determination coefficient of 0.997. IBSB can be successfully regenerated using 0.1 M HCl for subsequent cycle use.