Machine learning method for simulation of adsorption separation: Comparisons of model’s performance in predicting equilibrium concentrations

In this work, we implemented different models for predicting adsorption separation of a dye from aqueous solution using porous materials. The equilibrium data solute concentrations were collected resources and used in the training verification purposes to develop models. For prediction (Ce), tree models: Multi-layer Perceptron (MLP), Passive aggressive regression, Decision Tree (DT) Regressor. modeling, considered adsorbent dosage as well pH input parameters model, model was able generate output values, i.e., based on variables. evaluation models’ performances revelated that final R2 scores are 0.99, 0.98, 0.93 DT, MLP Passive-Aggressive, respectively very low RMSE 0.055 decision shows is best among study. Indeed, recommended other three be employed correlation data.