Original scientific paper
https://doi.org/10.15255/KUI.2022.085
Machine Learning and Neural Networks for Modelling the Retention of PPhACs by NF/RO
Yamina Ammi
; Laboratory of Biomaterials and Transport Phenomena (LBMPT), University of Médéa, 26 000 Médéa, Algeria
*
Cherif Si-Moussa
orcid.org/0000-0001-5727-2742
; Laboratory of Biomaterials and Transport Phenomena (LBMPT), University of Médéa, 26 000 Médéa, Algeria
Salah Hanini
; Laboratory of Biomaterials and Transport Phenomena (LBMPT), University of Médéa, 26 000 Médéa, Algeria
* Corresponding author.
Abstract
The retention of polar pharmaceutical active compounds (PPhACs) by nanofiltration and reverse osmosis (NF/RO) membranes is of paramount importance in membrane separation processes. The retention of 21 PPhACs was correlated using artificial intelligence techniques: multi-layer perceptron (MLP), feedforward neural network with radial basis function (RBF), and support vector machine (SVM). A database of 541 retention values has been collected from the literature. The results showed a high predictive capacity of the MLP model for the retention of PPhACs by NF/RO with a very high correlation coefficient (R = 0.9714) and a very low root mean squared error (RMSE = 3.9139 %) for the entire data set. The comparison between the three models showed the superiority of the MLP model. The sensitivity analysis emphasised that the retention of PPhACs is governed by three interactions arranged in descending order: polarity interactions (hydrophobicity/hydrophilicity), electrostatic repulsion, and steric hindrance. This research suggests that the PPhACs retention on the NF/RO membrane strongly depends on the topological polar surface area.
Keywords
machine learning; neural networks; modelling; retention; PPhACs; nanofiltration; reverse osmosis
Hrčak ID:
309800
URI
Publication date:
11.11.2023.
Visits: 649 *