Comparison Study of ANFIS, ANN, and RSM and Mechanistic Modeling for Chromium(VI) Removal Using Modified Cellulose Nanocrystals–Sodium Alginate (CNC–Alg)

Abstract The adsorption process was investigated using the ANFIS, ANN, and RSM models. adaptive neuro-fuzzy inference system (ANFIS), artificial neural network (ANN), response surface methodology (RSM) were used to develop an approach for assessing Cr(VI) from wastewater cellulose nanocrystals sodium alginate. adsorbent characterized Fourier transform infrared spectroscopy thermogravimetric analysis. Initial pH of 6, contact time 100 min, initial concentration 175 mg/L, sorbent dose 6 mg, capacity 350.23 mg/g optimal condition. mechanism described via four mechanistic models (film diffusion, Weber Morris, Bangham, Dumwald-Wagner models), with correlation values 0.997, 0.990, 0.989 RSM, respectively, predicted incredible accuracy. Statistical error tasks additionally applied relate adequacy Using central composite design (CCD), significance operating factors such as time, dose, pH, investigated. same concept create a training set ANN where Levenberg–Marquardt, variable learning rate, Polak Ribiere conjugate algorithms used. Further statistical indices supported ANFIS best prediction model compared RSM. efficient algorithm optimize process, which resulted in 350 capacity. Film diffusion identified rate-limiting modeling.