Machine learning-assisted screening of copper-cerium bimetallic catalysts for tetracycline degradation

Abstract

Bimetallic catalysts have shown significant potential for the removal of refractory organic pollutants due to their high catalytic activity, strong stability, and low cost. However, the individual preparation and testing of candidate materials are both time-consuming and impractical. In this study, a d-band center guided machine learning (ML) approach is proposed for screening the copper-cerium (Cu1Ce3) bimetallic catalyst for hydrogen peroxide activation. A total of 2000 bimetallic combinations with varying composition ratios were screened using the d-band center shift as the key descriptor by integrating density functional theory (DFT) with ML models. The DFT results corroborated the ML predictions and elucidated the enhanced charge transfer characteristics of the Cu1Ce3 bimetallic catalyst. Under optimal conditions, more than 99.4% of tetracycline was degraded using the Cu1Ce3/H2O2 system. This study provides novel insights and a practical strategy for the development of bimetallic catalysts, thereby enhancing the applicability of ML-assisted material screening in advanced oxidation processes.