Machine Learning for Advanced Design of Nanocomposite Ultrafiltration Membranes

Abstract

Although the incorporation of nanoparticles into ultrafiltration polymeric membranes has shown promising outcomes, their commercial implementation has yet to be fulfilled due to inconsistency in data, lack of a reliable recipe for the optimum filler content, and reluctance in disrupting the production line which requires significant time and resources. There is a growing demand among membrane communities for a design platform that can accelerate the discovery of new nanocomposite membranes. In this work, a feed-forward ANN (artificial neural network) model that has one hidden layer and the Bayesian regularization training algorithm were chosen for designing a graphical user interface platform to predict the ultrafiltration nanocomposite membrane performance, that is, solute rejection, flux recovery, and pure water flux, thereby saving time and resources used in membrane design. Experimental data (735 samples from 200 reports published between 2006 and 2020) were derived from the literature for training, validation, and testing of the ANN models. The results indicated that the best 30 ANN models produce the most accurate estimation of membrane performance using the seven input variables of polymer concentration, polymer type, filler concentration, average filler size, solvent concentration (in the dope solution), solvent type, and contact angle on the unseen data set. Furthermore, a sensitivity analysis was performed on the achieved models to identify the most effective input variables for each nanocomposite membrane performance. This work has the potential to be extended to other mixed matrix membrane types that are going to be used for microfiltration, nanofiltration, reverse osmosis, and so forth.