Prediction of copper ions adsorption by attapulgite adsorbent using tuned-artificial intelligence model

• Published in: Chemosphere (Oxford) 2021-08, Vol.276, p.130162-130162, Article 130162
• Main Authors: Bhagat, Suraj Kumar, Pyrgaki, Konstantina, Salih, Sinan Q., Tiyasha, Tiyasha, Beyaztas, Ufuk, Shahid, Shamsuddin, Yaseen, Zaher Mundher
• Format: Article
• Language: English
• Subjects: Artificial intelligence; Attapulgite clay; Copper adsorption; Heavy metal
• ISSN: 0045-6535; 1879-1298
• DOI: 10.1016/j.chemosphere.2021.130162

Copper (Cu) ion in wastewater is considered as one of the crucial hazardous elements to be quantified. This research is established to predict copper ions adsorption (Ad) by Attapulgite clay from aqueous solutions using computer-aided models. Three artificial intelligent (AI) models are developed for this purpose including Grid optimization-based random forest (Grid-RF), artificial neural network (ANN) and support vector machine (SVM). Principal component analysis (PCA) is used to select model inputs from different variables including the initial concentration of Cu (IC), the dosage of Attapulgite clay (Dose), contact time (CT), pH, and addition of NaNO3 (SN). The ANN model is found to predict Ad with minimum root mean square error (RMSE = 0.9283) and maximum coefficient of determination (R2 = 0.9974) when all the variables (i.e., IC, Dose, CT, pH, SN) were considered as input. The prediction accuracy of Grid-RF model is found similar to ANN model when a few numbers of predictors are used. According to prediction accuracy, the models can be arranged as ANN-M5> Grid-RF-M5> Grid-RF-M4> ANN-M4> SVM-M4> SVM-M5. Overall, the applied statistical analysis of the results indicates that ANN and Grid-RF models can be employed as a computer-aided model for monitoring and simulating the adsorption from aqueous solutions by Attapulgite clay. [Display omitted] •Aqueous solutions percentage copper (Cu) ions adsorption is predicted.•The feasibility of the artificial intelligence (AI) models is adopted in this study.•Five different modeling scenarios based on the related parameters are investigated.•Uncertainty analysis using bootstrap method is applied.•Results are evidence the potential of the AI models for the Cu prediction.