Predicting rejection of emerging contaminants through RO membrane filtration based on ANN-QSAR modeling approach: trends in molecular descriptors and structures towards rejections

Abstract

QSAR-ANN modelling was applied on ECs to predict the rejection of ECs by RO membrane and conduct explanatory study based the importance of selected descriptors.

Predicting micropollutant removal through nanopore-sized membranes using several machine-learning approaches based on feature engineering

“…Mousavi and Sajjadi compared the ANN-quantitative structure–activity relationship (QSAR) model strategy for the prediction of 72 micropollutant removal rate in RO membranes. 46 The ANN-QSAR model outperformed the MLR model, achieving higher accuracy with a R 2 of 0.95 and a lower RMSE of 6.4224. Teychene et al , conducted research using a decision tree model to assess the performance of reverse osmosis (RO) and nanofiltration (NF) membranes in removing 22 different polar micropollutants, focusing on the removal rate (%).…”