Hongling Qin, Ke Wang, Xifei Ma, Fangfang Li, Yanrong Liu, Xiaoyan Ji
{"title":"Predicting the solubility of CO<sub>2</sub> and N<sub>2</sub> in ionic liquids based on COSMO-RS and machine learning.","authors":"Hongling Qin, Ke Wang, Xifei Ma, Fangfang Li, Yanrong Liu, Xiaoyan Ji","doi":"10.3389/fchem.2024.1480468","DOIUrl":null,"url":null,"abstract":"<p><p>As ionic liquids (ILs) continue to be prepared, there is a growing need to develop theoretical methods for predicting the properties of ILs, such as gas solubility. In this work, different strategies were employed to obtain the solubility of CO<sub>2</sub> and N<sub>2</sub>, where a conductor-like screening model for real solvents (COSMO-RS) was used as the basis. First, experimental data on the solubility of CO<sub>2</sub> and N<sub>2</sub> in ILs were collected. Then, the solubility of CO<sub>2</sub> and N<sub>2</sub> in ILs was predicted using COSMO-RS based on the structures of cations, anions, and gases. To further improve the performance of COSMO-RS, two options were used, i.e., the polynomial expression to correct the COSMO-RS results and the combination of COSMO-RS and machine learning algorithms (eXtreme Gradient Boosting, XGBoost) to develop a hybrid model. The results show that the COSMO-RS with correction can significantly improve the prediction of CO<sub>2</sub> solubility, and the corresponding average absolute relative deviation (AARD) is decreased from 43.4% to 11.9%. In contrast, such an option cannot improve that of the N<sub>2</sub> dataset. Instead, the results obtained from coupling machine learning algorithms with the COSMO-RS model agree well with the experimental results, with an AARD of 0.94% for the solubility of CO<sub>2</sub> and an average absolute deviation (AAD) of 0.15% for the solubility of N<sub>2</sub>.</p>","PeriodicalId":12421,"journal":{"name":"Frontiers in Chemistry","volume":"12 ","pages":"1480468"},"PeriodicalIF":3.8000,"publicationDate":"2024-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11560425/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Frontiers in Chemistry","FirstCategoryId":"92","ListUrlMain":"https://doi.org/10.3389/fchem.2024.1480468","RegionNum":3,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/1/1 0:00:00","PubModel":"eCollection","JCR":"Q2","JCRName":"CHEMISTRY, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0
Abstract
As ionic liquids (ILs) continue to be prepared, there is a growing need to develop theoretical methods for predicting the properties of ILs, such as gas solubility. In this work, different strategies were employed to obtain the solubility of CO2 and N2, where a conductor-like screening model for real solvents (COSMO-RS) was used as the basis. First, experimental data on the solubility of CO2 and N2 in ILs were collected. Then, the solubility of CO2 and N2 in ILs was predicted using COSMO-RS based on the structures of cations, anions, and gases. To further improve the performance of COSMO-RS, two options were used, i.e., the polynomial expression to correct the COSMO-RS results and the combination of COSMO-RS and machine learning algorithms (eXtreme Gradient Boosting, XGBoost) to develop a hybrid model. The results show that the COSMO-RS with correction can significantly improve the prediction of CO2 solubility, and the corresponding average absolute relative deviation (AARD) is decreased from 43.4% to 11.9%. In contrast, such an option cannot improve that of the N2 dataset. Instead, the results obtained from coupling machine learning algorithms with the COSMO-RS model agree well with the experimental results, with an AARD of 0.94% for the solubility of CO2 and an average absolute deviation (AAD) of 0.15% for the solubility of N2.
期刊介绍：
Frontiers in Chemistry is a high visiblity and quality journal, publishing rigorously peer-reviewed research across the chemical sciences. Field Chief Editor Steve Suib at the University of Connecticut is supported by an outstanding Editorial Board of international researchers. This multidisciplinary open-access journal is at the forefront of disseminating and communicating scientific knowledge and impactful discoveries to academics, industry leaders and the public worldwide.
Chemistry is a branch of science that is linked to all other main fields of research. The omnipresence of Chemistry is apparent in our everyday lives from the electronic devices that we all use to communicate, to foods we eat, to our health and well-being, to the different forms of energy that we use. While there are many subtopics and specialties of Chemistry, the fundamental link in all these areas is how atoms, ions, and molecules come together and come apart in what some have come to call the “dance of life”.
All specialty sections of Frontiers in Chemistry are open-access with the goal of publishing outstanding research publications, review articles, commentaries, and ideas about various aspects of Chemistry. The past forms of publication often have specific subdisciplines, most commonly of analytical, inorganic, organic and physical chemistries, but these days those lines and boxes are quite blurry and the silos of those disciplines appear to be eroding. Chemistry is important to both fundamental and applied areas of research and manufacturing, and indeed the outlines of academic versus industrial research are also often artificial. Collaborative research across all specialty areas of Chemistry is highly encouraged and supported as we move forward. These are exciting times and the field of Chemistry is an important and significant contributor to our collective knowledge.
京公网安备 11010802042870号
京ICP备2023020795号-1
分享
求助内容：
应助结果提醒方式：
扫码关注我们
