The Application of an Adaptive Neuro-Fuzzy Inference System for the Removal of Cadmium (II) from Acid Mine Drainage onto Modified Cellulose Nanocrystals

This research uses a modified cellulose nanocrystal composite, a green and biodegradable adsorbent, to remove cobalt (II) using a column study. Fourier transform infrared spectroscopy, scanning electron microscopy, and thermogravimetric analysis were used to characterise the adsorbent. The fixed-bed column was used to remove cadmium (II) at room temperature with process factors, such as pH (4−8), bed height (3–9 cm), flow rate (3–7 mL/min), and concentration (10−20 mg/L). According to the findings, the cobalt (II) breakthrough occurred quicker for a lower bed height, greater flow rate, and higher cadmium(II) concentration. The Yoon–Nelson model is the most appropriate kinetic model. Deep learning models, such as the adaptive neuro-fuzzy inference model with two algorithms (Backpropagation and Least Squares Estimation), were effectively used to model the effectiveness of cadmium (II) removal in aqueous solution using modified cellulose nanocrystals. To compare the model's predicted results with experimental data, statistical approaches were used, including Marquardt's percentage standard deviation (MPSD), the coefficient of determination (R²), and Mean Square Error (MSE). The ANFIS model used to predict cadmium (II) adsorption using modified cellulose nanocrystals had a strong correlation value of 0.997 for the Least Squares Estimation (LSE) and 0.999 for the Gradient Descent (Backpropagation), indicating how effectively the trained model predicted the cadmium(II) adsorption process.