Machine learning driven identification of optimal nanomaterials for efficient pararosaniline dye removal from water using a RFHGB hybrid model | Synapse
March 6, 2026RSC Advances0 citationsOpen Access
Machine learning driven identification of optimal nanomaterials for efficient pararosaniline dye removal from water using a RFHGB hybrid model
The aim is to develop a machine learning model to predict dye degradation and identify effective nanomaterials for purification.
Developed an RFHGB machine learning model.
Used synthetic data augmentation to enhance prediction accuracy.
Evaluated various nanomaterials for efficacy in photocatalytic degradation.
The model accurately predicts the degradation of pararosaniline dye.
ZnO–CuO is identified as the most efficient catalyst for dye removal.
Abstract
An RFHGB machine learning model integrated with synthetic data augmentation accurately predicts photocatalytic degradation of pararosaniline. It also identifies ZnO–CuO as the most efficient catalyst.