Application of different mathematical models based on artificial intelligence technique to predict the concentration distribution of solute through a polymeric membrane

Jowaher Alanazi; Mohammad M Algahtani; Muteb Alanazi; Tareq Nafea Alharby

doi:10.1016/j.ecoenv.2023.115183

Application of different mathematical models based on artificial intelligence technique to predict the concentration distribution of solute through a polymeric membrane

Ecotoxicol Environ Saf. 2023 Jun 24:262:115183. doi: 10.1016/j.ecoenv.2023.115183. Online ahead of print.

Authors

Jowaher Alanazi¹, Mohammad M Algahtani², Muteb Alanazi³, Tareq Nafea Alharby³

Affiliations

¹ Department of Pharmacology and Toxicology, College of Pharmacy, University of Ha'il, Ha'il 81442, Saudi Arabia. Electronic address: Js.alanzi@uoh.edu.sa.
² Department of Pharmacology and Toxicology, College of Pharmacy, King Saudi University, Riyadh, Saudi Arabia.
³ Department of Clinical Pharmacy, College of Pharmacy, University of Ha'il, Ha'il 81442, Saudi Arabia.

PMID: 37364398
DOI: 10.1016/j.ecoenv.2023.115183

Abstract

Membrane-based purification of therapeutic agents has recently attracted global attention as a promising replacement for conventional techniques like distillation and pervaporation. Despite the conduction of different investigations, development of more research about the operational feasibility of using polymeric membranes to separate the detrimental impurities of molecular entities is of great importance. The focus of this paper is to develop a numerical strategy based on multiple machine learning methods to predict the concentration distribution of solute through a membrane-based separation process. Two inputs are being analyzed in this study, specifically r and z. Furthermore, the single target output is C, and the number of data points exceeds 8000. To analyze and model the data for this study, we used the Adaboost (Adaptive Boosting) model over three different base learners (K-Nearest Neighbors (KNN), Linear Regression (LR), and Gaussian Process Regression (GPR)). In the process of hyper-parameter optimization for models, the BA optimization algorithm applied on the adaptive boosted models. Finally, Boosted KNN, Boosted LR, and Boosted GPR have scores of 0.9853, 0.8751, and 0.9793 in terms of R² metric. Based on the recent fact and other analyses, boosted KNN model is introduced as the most appropriate model of this research. The error rates for this model are 2.073 × 10¹ and 1.06 × 10^-2 in terms of MAE and MAPE metrics.

Keywords: Artificial intelligence; CFD; Mass transfer; Membrane; Separation.