Personalized machine learning models of terminal olefin hydroformylation for regioselectivity prediction

IF 11.5 Q1 CHEMISTRY, PHYSICAL Chem Catalysis Pub Date : 2024-08-20 DOI:10.1016/j.checat.2024.101079
Hao Wang, Yuzhuo Chen, Hang Yu, Menghui Qi, De Xia, Minkai Qin, XuCheng Lv, Bing Lu, Ruiliang Gao, Yong Wang, Shanjun Mao
{"title":"Personalized machine learning models of terminal olefin hydroformylation for regioselectivity prediction","authors":"Hao Wang, Yuzhuo Chen, Hang Yu, Menghui Qi, De Xia, Minkai Qin, XuCheng Lv, Bing Lu, Ruiliang Gao, Yong Wang, Shanjun Mao","doi":"10.1016/j.checat.2024.101079","DOIUrl":null,"url":null,"abstract":"<p>The integration of machine learning into hydroformylation processes represents a pivotal advancement in high-throughput screening within the chemical industry. This study employs a data-driven approach to develop predictive models for terminal olefin reactions. Using a database of 1,167 entries, we merged reaction embeddings with corresponding labels. The well-trained extreme gradient boosting model achieves a test set coefficient of determination (R<sup>2</sup>) score of 0.897. However, when applied to specific-olefin tasks, the model shows suboptimal performance. Therefore, tailored models for specific olefins like 1-octene and styrene are developed, achieving improved test set R<sup>2</sup> scores of 0.850 and 0.789, respectively, compared to the general-olefin task. Interpretability findings highlight the significance of high-temperature, low-pressure, and low-concentration metals in enhancing linear regioselectivity and providing chemical insights. This study underscores the transformative potential of machine learning as a surrogate model in advancing high-throughput screening and optimizing chemical processes in the industry.</p>","PeriodicalId":53121,"journal":{"name":"Chem Catalysis","volume":"1 1","pages":""},"PeriodicalIF":11.5000,"publicationDate":"2024-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Chem Catalysis","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1016/j.checat.2024.101079","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"CHEMISTRY, PHYSICAL","Score":null,"Total":0}
引用次数: 0

Abstract

The integration of machine learning into hydroformylation processes represents a pivotal advancement in high-throughput screening within the chemical industry. This study employs a data-driven approach to develop predictive models for terminal olefin reactions. Using a database of 1,167 entries, we merged reaction embeddings with corresponding labels. The well-trained extreme gradient boosting model achieves a test set coefficient of determination (R2) score of 0.897. However, when applied to specific-olefin tasks, the model shows suboptimal performance. Therefore, tailored models for specific olefins like 1-octene and styrene are developed, achieving improved test set R2 scores of 0.850 and 0.789, respectively, compared to the general-olefin task. Interpretability findings highlight the significance of high-temperature, low-pressure, and low-concentration metals in enhancing linear regioselectivity and providing chemical insights. This study underscores the transformative potential of machine learning as a surrogate model in advancing high-throughput screening and optimizing chemical processes in the industry.

Abstract Image

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
用于区域选择性预测的末端烯烃加氢甲酰化个性化机器学习模型
将机器学习融入加氢甲酰化过程代表了化学工业在高通量筛选方面的重要进步。本研究采用数据驱动方法,为末端烯烃反应开发预测模型。我们使用一个包含 1,167 个条目的数据库,将反应嵌入与相应的标签合并。训练有素的极梯度提升模型的测试集判定系数 (R2) 得分为 0.897。然而,当应用于特定烯烃任务时,该模型显示出不理想的性能。因此,我们开发了针对特定烯烃(如 1-辛烯和苯乙烯)的定制模型,与一般烯烃任务相比,测试集 R2 分数分别提高到 0.850 和 0.789。可解释性研究结果凸显了高温、低压和低浓度金属在提高线性区域选择性和提供化学见解方面的重要性。这项研究强调了机器学习作为一种替代模型在推进高通量筛选和优化工业化学过程方面的变革潜力。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
CiteScore
10.50
自引率
6.40%
发文量
0
期刊介绍: Chem Catalysis is a monthly journal that publishes innovative research on fundamental and applied catalysis, providing a platform for researchers across chemistry, chemical engineering, and related fields. It serves as a premier resource for scientists and engineers in academia and industry, covering heterogeneous, homogeneous, and biocatalysis. Emphasizing transformative methods and technologies, the journal aims to advance understanding, introduce novel catalysts, and connect fundamental insights to real-world applications for societal benefit.
期刊最新文献
Reverse effect of metal-support interaction on platinum and iridium catalysts in ammonia selective oxidation Visualizing active species in CO2 electroreduction Key role of precatalyst composition and iron impurities in oxygen evolution reaction Enzymatic azide synthesis by ATP-dependent synthetase Visualizing the step bunching on Pt surfaces and its effect in electrocatalysis with EC-STM
×
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