.png){kind=icon}
返回
Rationally design the ionic liquid-based absorbents for CO2 absorption using machine learning
.png){kind=icon}
PRE
AI
DOI：10.1016/j.seppur.2025.132613.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Ionic liquids (ILs) have shown great potential as CO2 absorbents, but traditional experimental methods for screening ILs are both time-consuming and labor-intensive. To identify the most effective ILs with desirable properties, the computer-aided design approaches are essential. This study manifested a rapid screening method for ILs using graph neural network (GNN). Approximate 40,000 experimental data points were collected, including CO2 solubility, viscosity, melting point, and toxicity, to train high-precision GNN regression models and XGBoost classification models. Various strategies were examined for constructing molecular graphs based on IL structures and several GNN models were compared, ultimately proposing an effective GNN architecture that enhances prediction accuracy. To realize high-throughput screening, a database containing 200,000 IL structures was built. The screening criteria included the melting point below 298.15 K, viscosity under 100 MPa & sdot;s, and the toxicity with log10EC50 greater than 3.4 mu M. Through this screening process, 12 ILs were successfully identified that showed the highest CO2 solubility. Density functional theory (DFT) calculations indicated that the main interaction mechanism between CO2 and ILs involves the C atom of CO2 being attracted by the O atom of the anion, while the O atom of CO2 is attracted by the H atom of the cation. This data-driven approach simplifies the selection and design of IL absorbents, thereby accelerating the development of CO2 capture technologies.
Keyword:
Machine learning
Ionic liquids
High-through screening
CO2 absorption
期刊
IF:
9
论文数:
3.0W
被引数:
12.1W
机构
引用论文
暂无论文信息