| 机器学习探究电子气体在沸石分子筛上的吸附 | |
| Machine learning exploring the adsorption of electronic gases on zeolite molecular sieves | |
| 摘要: 使用机器学习进行高通量筛选是一种新的材料筛选方法，我们结合巨正则蒙特卡罗(GCMC)模拟和机器学习方法研究了沸石分子筛对气体的吸附。使用GCMC模拟方法，计算了12种电子气体在240种纯硅沸石分子筛上的绝对吸附量，并通过Zeo++程序分析了沸石分子筛的17种结构特征。在此基础上，建立了2种机器学习模型：多元线性回归模型和随机森林回归模型，旨在预测沸石分子筛对各类电子气体的吸附能力。同时，通过相关性分析和模型性能评估，揭示了不同结构特征对气体吸附容量的影响程度，并对模型的稳定性和预测精度进行了讨论。 | |
| 关键词: 电子特种气体 沸石分子筛 机器学习 巨正则蒙特卡罗模拟 | |
| 基金项目: 国家重点研发计划(No.2021YFA1501500)资助。 | |
| Abstract: Using machine learning for high - throughput screening is a new material screening method. The gas adsorption on zeolite molecular sieves was studied using the grand canonical Monte Carlo (GCMC) simulation and machine learning methods. The GCMC simulation method was used to calculate the absolute adsorption capacity of 12 types of electron gases on 240 varieties of silica zeolite molecular sieves. In comparison, the Zeo++ program was employed to analyze 17 types of structural characteristics of these zeolite molecular sieves. On this basis, multiple linear regression and random forest regression were established to predict the adsorption capacity of zeolite molecular sieves for electronic gases. Through correlation analysis and model performance evaluation, the impact degree of different structural characteristics on gas adsorption capacity was revealed, and the stability and prediction accuracy of the model were discussed. | |
| Keywords: electronic specialty gas zeolite molecular sieve machine learning grand canonical Monte Carlo simulation | |
| 投稿时间：2024-11-14 修订日期：2024-12-23 | |
| 摘要点击次数: 693 | |
| 全文下载次数: 353 | |
| 陈佳丽,赵国祥,颜亚玉,夏万厅,李巧红,张健.机器学习探究电子气体在沸石分子筛上的吸附[J].无机化学学报,2025,41(1):155-164. | |
| 查看全文 查看/发表评论 下载PDF阅读器 | |
| Support information: 相关附件： 20240408_SI.doc | |
|
| |
|
| |
|
| |