Machine learning insight into inhibition efficiency modelling based on modified graphene oxide of diaminohexane (DAH-GO) and diaminooctane (DAO-GO)

IF 3.1 Q2 MATERIALS SCIENCE, MULTIDISCIPLINARY Carbon Trends Pub Date : 2024-06-11 DOI:10.1016/j.cartre.2024.100373
Kabiru Haruna , Sani I. Abba , Jamil Usman , A.G. Usman , Abdulrahman Musa , Tawfik A. Saleh , Isam H. Aljundi
{"title":"Machine learning insight into inhibition efficiency modelling based on modified graphene oxide of diaminohexane (DAH-GO) and diaminooctane (DAO-GO)","authors":"Kabiru Haruna ,&nbsp;Sani I. Abba ,&nbsp;Jamil Usman ,&nbsp;A.G. Usman ,&nbsp;Abdulrahman Musa ,&nbsp;Tawfik A. Saleh ,&nbsp;Isam H. Aljundi","doi":"10.1016/j.cartre.2024.100373","DOIUrl":null,"url":null,"abstract":"<div><p>The effective prediction of corrosion inhibition efficiency (%IE) of modified graphene oxides (GOs); diaminohexane-modified graphene oxide (DAH-GO) and diaminooctane-modified graphene oxide (DAO-GO) is vital for advanced material applications. This study employs a dual-modelling scheme to predict the %IE, for this purpose, four stand-alone machine learning (ML) models (Multivariate Regression (MVR), Gaussian Process Regression (GPR), Adaptive Neuro-Fuzzy Inference System (ANFIS), and Neural Network (NN)), and five simple averaging (SA) ensemble paradigms (MVR-SA, GPR-SA, ANFIS-SA, NN-SA, and Decision Tree-SA (DT-SA)). Feature selection processes were carried out to develop three distinct models, leading to a comprehensive comparative analysis. The results demonstrated that the non-linear stand-alone models (GPR, ANFIS, NN) significantly outperform the linear MVR model, with the M2 model configuration yielding the highest performance across all models. Remarkably, GPR-M2 achieved perfect model tuning with zero error rates, indicating its superior predictive capabilities. Ensemble techniques further improved performance, reflecting the experimental data's complexities in %IE modelling. The hierarchical order of performance in the training phase in the testing phase is DT-SA &lt; MVR-SA &lt; ANFIS-SA &lt; NN-SA &lt; GPR-SA. The GPR-SA ensemble emerged as the most accurate technique, substantially enhancing the predictive accuracy of the ensemble models by up to 67.73% in the training phase and 50.71% in the testing phase. These findings suggest the potential of GPR-SA in boosting the performance of ensemble approaches in material science applications. The study recommended a promising future for ML in the development and application of corrosion-inhibitors.</p></div>","PeriodicalId":52629,"journal":{"name":"Carbon Trends","volume":"16 ","pages":"Article 100373"},"PeriodicalIF":3.1000,"publicationDate":"2024-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2667056924000543/pdfft?md5=a20d8003d5b921de8be788888ef22dda&pid=1-s2.0-S2667056924000543-main.pdf","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Carbon Trends","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2667056924000543","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"MATERIALS SCIENCE, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0

Abstract

The effective prediction of corrosion inhibition efficiency (%IE) of modified graphene oxides (GOs); diaminohexane-modified graphene oxide (DAH-GO) and diaminooctane-modified graphene oxide (DAO-GO) is vital for advanced material applications. This study employs a dual-modelling scheme to predict the %IE, for this purpose, four stand-alone machine learning (ML) models (Multivariate Regression (MVR), Gaussian Process Regression (GPR), Adaptive Neuro-Fuzzy Inference System (ANFIS), and Neural Network (NN)), and five simple averaging (SA) ensemble paradigms (MVR-SA, GPR-SA, ANFIS-SA, NN-SA, and Decision Tree-SA (DT-SA)). Feature selection processes were carried out to develop three distinct models, leading to a comprehensive comparative analysis. The results demonstrated that the non-linear stand-alone models (GPR, ANFIS, NN) significantly outperform the linear MVR model, with the M2 model configuration yielding the highest performance across all models. Remarkably, GPR-M2 achieved perfect model tuning with zero error rates, indicating its superior predictive capabilities. Ensemble techniques further improved performance, reflecting the experimental data's complexities in %IE modelling. The hierarchical order of performance in the training phase in the testing phase is DT-SA < MVR-SA < ANFIS-SA < NN-SA < GPR-SA. The GPR-SA ensemble emerged as the most accurate technique, substantially enhancing the predictive accuracy of the ensemble models by up to 67.73% in the training phase and 50.71% in the testing phase. These findings suggest the potential of GPR-SA in boosting the performance of ensemble approaches in material science applications. The study recommended a promising future for ML in the development and application of corrosion-inhibitors.

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
基于二氨基己烷(DAH-GO)和二氨基辛烷(DAO-GO)的改性氧化石墨烯的机器学习对抑制效率建模的启示
有效预测改性石墨烯氧化物(GOs)、二氨基己烷改性氧化石墨烯(DAH-GO)和二氨基辛烷改性氧化石墨烯(DAO-GO)的缓蚀效率(%IE)对于先进材料的应用至关重要。本研究采用了双重建模方案来预测 IE%,为此采用了四种独立的机器学习(ML)模型(多元回归(MVR)、高斯过程回归(GPR)、自适应神经模糊推理系统(ANFIS)和神经网络(NN))以及五种简单平均(SA)集合范例(MVR-SA、GPR-SA、ANFIS-SA、NN-SA 和决策树-SA(DT-SA))。通过特征选择过程开发了三种不同的模型,从而进行了全面的比较分析。结果表明,非线性独立模型(GPR、ANFIS、NN)明显优于线性 MVR 模型,其中 M2 模型配置在所有模型中性能最高。值得注意的是,GPR-M2 实现了完美的模型调整,错误率为零,这表明它具有卓越的预测能力。集合技术进一步提高了性能,反映了 %IE 建模中实验数据的复杂性。在测试阶段,训练阶段的性能等级顺序为 DT-SA < MVR-SA < ANFIS-SA < NN-SA < GPR-SA。GPR-SA 组合是最准确的技术,在训练阶段大大提高了组合模型的预测准确性,高达 67.73%,在测试阶段提高了 50.71%。这些发现表明,GPR-SA 在提高材料科学应用中的集合方法性能方面具有潜力。该研究为 ML 在腐蚀抑制剂的开发和应用中的发展前景提出了建议。
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
Carbon Trends
Carbon Trends Materials Science-Materials Science (miscellaneous)
CiteScore
4.60
自引率
0.00%
发文量
88
审稿时长
77 days
期刊最新文献
Mechanistic insight into the catalytic activities of metallic sites on nitrogen-doped graphene quantum dots for CO2 hydrogenation Fe-based catalytic modification of a birch sawdust-based carbon structure: The effect of process parameters on the final product using an experimental design Evaluation of morphological, structural, thermal, electrical, and chemical composition properties of graphene oxide, and reduced graphene oxide obtained by sequential reduction methods Eco and user–friendly curcumin based nanocomposite forensic powder from coal fly ash for latent fingerprint detection in crime scenes Reduced thermal conductivity of constricted graphene nanoribbons for thermoelectric applications
×
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