通过密度泛函理论和机器学习快速发现材料中的气体反应

IF 13 2区 材料科学 Q1 MATERIALS SCIENCE, MULTIDISCIPLINARY Energy & Environmental Materials Pub Date : 2024-08-02 DOI:10.1002/eem2.12816
Shasha Gao, Yongchao Cheng, Lu Chen, Sheng Huang
{"title":"通过密度泛函理论和机器学习快速发现材料中的气体反应","authors":"Shasha Gao, Yongchao Cheng, Lu Chen, Sheng Huang","doi":"10.1002/eem2.12816","DOIUrl":null,"url":null,"abstract":"In this study, a framework for predicting the gas-sensitive properties of gas-sensitive materials by combining machine learning and density functional theory (DFT) has been proposed. The framework rapidly predicts the gas response of materials by establishing relationships between multisource physical parameters and gas-sensitive properties. In order to prove its effectiveness, the perovskite Cs<sub>3</sub>Cu<sub>2</sub>I<sub>5</sub> has been selected as the representative material. The physical parameters before and after the adsorption of various gases have been calculated using DFT, and then a machine learning model has been trained based on these parameters. Previous studies have shown that a single physical parameter alone is not enough to accurately predict the gas sensitivity of materials. Therefore, a variety of physical parameters have been selected for machine learning, and the final machine learning model achieved 92% accuracy in predicting gas sensitivity. It is important to note that although there have been no previous reports on the response of Cs<sub>3</sub>Cu<sub>2</sub>I<sub>5</sub> to hydrogen sulfide, the resulting model predicts the gas response of H<sub>2</sub>S; it is subsequently confirmed experimentally. This method not only enhances the understanding of the gas sensing mechanism, but also has a universal nature, making it suitable for the development of various new gas-sensitive materials.","PeriodicalId":11554,"journal":{"name":"Energy & Environmental Materials","volume":null,"pages":null},"PeriodicalIF":13.0000,"publicationDate":"2024-08-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Rapid Discovery of Gas Response in Materials Via Density Functional Theory and Machine Learning\",\"authors\":\"Shasha Gao, Yongchao Cheng, Lu Chen, Sheng Huang\",\"doi\":\"10.1002/eem2.12816\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In this study, a framework for predicting the gas-sensitive properties of gas-sensitive materials by combining machine learning and density functional theory (DFT) has been proposed. The framework rapidly predicts the gas response of materials by establishing relationships between multisource physical parameters and gas-sensitive properties. In order to prove its effectiveness, the perovskite Cs<sub>3</sub>Cu<sub>2</sub>I<sub>5</sub> has been selected as the representative material. The physical parameters before and after the adsorption of various gases have been calculated using DFT, and then a machine learning model has been trained based on these parameters. Previous studies have shown that a single physical parameter alone is not enough to accurately predict the gas sensitivity of materials. Therefore, a variety of physical parameters have been selected for machine learning, and the final machine learning model achieved 92% accuracy in predicting gas sensitivity. It is important to note that although there have been no previous reports on the response of Cs<sub>3</sub>Cu<sub>2</sub>I<sub>5</sub> to hydrogen sulfide, the resulting model predicts the gas response of H<sub>2</sub>S; it is subsequently confirmed experimentally. This method not only enhances the understanding of the gas sensing mechanism, but also has a universal nature, making it suitable for the development of various new gas-sensitive materials.\",\"PeriodicalId\":11554,\"journal\":{\"name\":\"Energy & Environmental Materials\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":13.0000,\"publicationDate\":\"2024-08-02\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Energy & Environmental Materials\",\"FirstCategoryId\":\"88\",\"ListUrlMain\":\"https://doi.org/10.1002/eem2.12816\",\"RegionNum\":2,\"RegionCategory\":\"材料科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"MATERIALS SCIENCE, MULTIDISCIPLINARY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Energy & Environmental Materials","FirstCategoryId":"88","ListUrlMain":"https://doi.org/10.1002/eem2.12816","RegionNum":2,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"MATERIALS SCIENCE, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0

摘要

本研究提出了一个结合机器学习和密度泛函理论(DFT)预测气敏材料气敏特性的框架。该框架通过建立多源物理参数与气敏特性之间的关系,快速预测材料的气体响应。为了证明其有效性,我们选择了透辉石 Cs3Cu2I5 作为代表材料。利用 DFT 计算了各种气体吸附前后的物理参数,然后根据这些参数训练了机器学习模型。以往的研究表明,仅凭单一的物理参数不足以准确预测材料的气体敏感性。因此,我们选择了多种物理参数进行机器学习,最终的机器学习模型在预测气体敏感性方面达到了 92% 的准确率。值得注意的是,虽然以前没有关于 Cs3Cu2I5 对硫化氢反应的报道,但所建立的模型预测了 H2S 的气体反应,并随后在实验中得到了证实。这种方法不仅加深了人们对气体传感机理的理解,而且具有通用性,适用于开发各种新型气敏材料。
本文章由计算机程序翻译,如有差异,请以英文原文为准。

摘要图片

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Rapid Discovery of Gas Response in Materials Via Density Functional Theory and Machine Learning
In this study, a framework for predicting the gas-sensitive properties of gas-sensitive materials by combining machine learning and density functional theory (DFT) has been proposed. The framework rapidly predicts the gas response of materials by establishing relationships between multisource physical parameters and gas-sensitive properties. In order to prove its effectiveness, the perovskite Cs3Cu2I5 has been selected as the representative material. The physical parameters before and after the adsorption of various gases have been calculated using DFT, and then a machine learning model has been trained based on these parameters. Previous studies have shown that a single physical parameter alone is not enough to accurately predict the gas sensitivity of materials. Therefore, a variety of physical parameters have been selected for machine learning, and the final machine learning model achieved 92% accuracy in predicting gas sensitivity. It is important to note that although there have been no previous reports on the response of Cs3Cu2I5 to hydrogen sulfide, the resulting model predicts the gas response of H2S; it is subsequently confirmed experimentally. This method not only enhances the understanding of the gas sensing mechanism, but also has a universal nature, making it suitable for the development of various new gas-sensitive materials.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Energy & Environmental Materials
Energy & Environmental Materials MATERIALS SCIENCE, MULTIDISCIPLINARY-
CiteScore
17.60
自引率
6.00%
发文量
66
期刊介绍: Energy & Environmental Materials (EEM) is an international journal published by Zhengzhou University in collaboration with John Wiley & Sons, Inc. The journal aims to publish high quality research related to materials for energy harvesting, conversion, storage, and transport, as well as for creating a cleaner environment. EEM welcomes research work of significant general interest that has a high impact on society-relevant technological advances. The scope of the journal is intentionally broad, recognizing the complexity of issues and challenges related to energy and environmental materials. Therefore, interdisciplinary work across basic science and engineering disciplines is particularly encouraged. The areas covered by the journal include, but are not limited to, materials and composites for photovoltaics and photoelectrochemistry, bioprocessing, batteries, fuel cells, supercapacitors, clean air, and devices with multifunctionality. The readership of the journal includes chemical, physical, biological, materials, and environmental scientists and engineers from academia, industry, and policy-making.
期刊最新文献
Issue Information Unveiling the Role of Electrocatalysts Activation for Iron-Doped Ni Oxyhydroxide in Enhancing the Catalytic Performance of Oxygen Evolution Reaction Unraveling the Morphological and Energetic Properties of 2PACz Self-Assembled Monolayers Fabricated With Upscaling Deposition Methods Covalently Anchoring and In Situ Electrochemical Activation of Conductive Selenophene-Organic Matrix-Driven High-Efficiency Potassium Organic Batteries A Practical Zinc Metal Anode Coating Strategy Utilizing Bulk h-BN and Improved Hydrogen Redox Kinetics
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1