Machine learning in laser-induced breakdown spectroscopy: A review

IF 6.5 2区 物理与天体物理 Q1 PHYSICS, MULTIDISCIPLINARY
Zhongqi Hao, Ke Liu, Qianlin Lian, Weiran Song, Zongyu Hou, Rui Zhang, Qianqian Wang, Chen Sun, Xiangyou Li, Zhe Wang
{"title":"Machine learning in laser-induced breakdown spectroscopy: A review","authors":"Zhongqi Hao,&nbsp;Ke Liu,&nbsp;Qianlin Lian,&nbsp;Weiran Song,&nbsp;Zongyu Hou,&nbsp;Rui Zhang,&nbsp;Qianqian Wang,&nbsp;Chen Sun,&nbsp;Xiangyou Li,&nbsp;Zhe Wang","doi":"10.1007/s11467-024-1427-2","DOIUrl":null,"url":null,"abstract":"<div><p>Laser-induced breakdown spectroscopy (LIBS) is a spectroscopic analytic technique with great application potential because of its unique advantages for online/in-situ detection. However, due to the spatially inhomogeneity and drastically temporal varying nature of its emission source, the laser-induced plasma, it is difficult to find or hard to generate an appropriate spatiotemporal window for high repeatable signal collection with lower matrix effects. The quantification results of traditional physical principle based calibration model are unsatisfactory since these models were not able to compensate for complicate matrix effects as well as signal fluctuation. Machine learning is an emerging approach, which can intelligently correlated the complex LIBS spectral data with its qualitative or/and quantitative composition by establishing multivariate regression models with greater potential to reduce the impacts of signal fluctuation and matrix effects, therefore achieving relatively better qualitative and quantitative performance. In this review, the progress of machine learning application in LIBS is summarized from two main aspects: i) Pre-processing data for machine learning model, including spectral selection, variable reconstruction, and denoising to improve qualitative/quantitative performance; ii) Machine learning methods for better quantification performance with reduction of the impact of matrix effect as well as LIBS spectra fluctuations. The review also points out the issues that researchers need to address in their future research on improving the performance of LIBS analysis using machine learning algorithms, such as restrictions on training data, the disconnect between physical principles and algorithms, the low generalization ability and massive data processing ability of the model.</p><div><figure><div><div><picture><source><img></source></picture></div></div></figure></div></div>","PeriodicalId":573,"journal":{"name":"Frontiers of Physics","volume":"19 6","pages":""},"PeriodicalIF":6.5000,"publicationDate":"2024-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Frontiers of Physics","FirstCategoryId":"101","ListUrlMain":"https://link.springer.com/article/10.1007/s11467-024-1427-2","RegionNum":2,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"PHYSICS, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0

Abstract

Laser-induced breakdown spectroscopy (LIBS) is a spectroscopic analytic technique with great application potential because of its unique advantages for online/in-situ detection. However, due to the spatially inhomogeneity and drastically temporal varying nature of its emission source, the laser-induced plasma, it is difficult to find or hard to generate an appropriate spatiotemporal window for high repeatable signal collection with lower matrix effects. The quantification results of traditional physical principle based calibration model are unsatisfactory since these models were not able to compensate for complicate matrix effects as well as signal fluctuation. Machine learning is an emerging approach, which can intelligently correlated the complex LIBS spectral data with its qualitative or/and quantitative composition by establishing multivariate regression models with greater potential to reduce the impacts of signal fluctuation and matrix effects, therefore achieving relatively better qualitative and quantitative performance. In this review, the progress of machine learning application in LIBS is summarized from two main aspects: i) Pre-processing data for machine learning model, including spectral selection, variable reconstruction, and denoising to improve qualitative/quantitative performance; ii) Machine learning methods for better quantification performance with reduction of the impact of matrix effect as well as LIBS spectra fluctuations. The review also points out the issues that researchers need to address in their future research on improving the performance of LIBS analysis using machine learning algorithms, such as restrictions on training data, the disconnect between physical principles and algorithms, the low generalization ability and massive data processing ability of the model.

Abstract Image

激光诱导击穿光谱学中的机器学习:综述
激光诱导击穿光谱(LIBS)是一种光谱分析技术,因其在线/原位检测的独特优势而具有巨大的应用潜力。然而,由于其发射源--激光诱导等离子体--在空间上的不均匀性和时间上的急剧变化性,很难找到或很难生成一个合适的时空窗口来采集具有较低矩阵效应的高重复性信号。基于物理原理的传统校准模型的量化结果并不令人满意,因为这些模型无法弥补复杂的矩阵效应和信号波动。机器学习是一种新兴的方法,它可以通过建立多元回归模型,智能地将复杂的 LIBS 光谱数据与其定性或/和定量组成相关联,从而获得相对更好的定性和定量性能。本综述从两个主要方面总结了机器学习在 LIBS 中的应用进展:i) 机器学习模型的数据预处理,包括光谱选择、变量重构和去噪,以提高定性/定量性能;ii) 机器学习方法可降低矩阵效应和 LIBS 光谱波动的影响,从而获得更好的定量性能。综述还指出了研究人员在利用机器学习算法提高 LIBS 分析性能的未来研究中需要解决的问题,如对训练数据的限制、物理原理与算法之间的脱节、模型的低泛化能力和海量数据处理能力等。
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 求助全文
来源期刊
Frontiers of Physics
Frontiers of Physics PHYSICS, MULTIDISCIPLINARY-
CiteScore
9.20
自引率
9.30%
发文量
898
审稿时长
6-12 weeks
期刊介绍: Frontiers of Physics is an international peer-reviewed journal dedicated to showcasing the latest advancements and significant progress in various research areas within the field of physics. The journal's scope is broad, covering a range of topics that include: Quantum computation and quantum information Atomic, molecular, and optical physics Condensed matter physics, material sciences, and interdisciplinary research Particle, nuclear physics, astrophysics, and cosmology The journal's mission is to highlight frontier achievements, hot topics, and cross-disciplinary points in physics, facilitating communication and idea exchange among physicists both in China and internationally. It serves as a platform for researchers to share their findings and insights, fostering collaboration and innovation across different areas of physics.
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信