Our paper titled “Machine Learning Based Screening of Organic Frameworks for Separation of CF4/N2, C2F6/N2, and SF6/N2” has been published online in the journal “Chemical Engineering Science”, accessible at https://doi.org/10.1016/j.ces.2024.120280.
Using molecular simulations and machine learning, we developed regression models for high-throughput screening of organic frameworks for CF4/N2, C2F6/N2, and SF6/N2 separation. The Grand Canonical Ensemble Monte Carlo method simulated adsorption in 603 materials, analyzing six structural features and introducing two descriptors (AVG_SIG, AVG_SQRT_EPS). Eight ML models were applied, with XGBoost and GN showing the most promise after hyperparameter optimization with Harris Hawks Optimization, enhancing prediction accuracy.
Since 1951, Chemical Engineering Science (CES) has been a leading journal for fundamental research in the field, publishing significant advances and supporting the growth of chemical engineering into a diverse and robust scientific area.
CES is recognized internationally as a top-tier journal, indexed in the Science Citation Index (SCI). In the Web of Science (WOS) 2022-2023 rankings, it is rated Q2, reflecting its quality and reputation. With an impact factor of 4.7 in 2023 and a CiteScore of 7.9, CES is also ranked in Zone 2 of the Chinese Academy of Sciences (CAS) SCI Journal Ranking under Chemical Engineering.