Accurate identification of geological samples using artificial neural network processing of laser-induced breakdown spectroscopy data

Lui, Siu-Lung; Koujelev, Alexander

doi:10.1039/c1ja10093a

Cited by 32 publications

(9 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…To identify specific elements within the samples, the preprocessed LIBS spectra were compared to a spectral database that includes lines from the National Institute of Standards and Technology Atomic Database [ Kelleher et al ., ; Ralchenko et al ., ], lines from the recently published Mars emission line library [ Cousin et al ., ], and lines from our own spectral libraries [ Koujelev et al ., ; Lui and Koujelev , ; Sobron et al ., ]. Here, we constrained the database search to Al, C, Ca, Fe, K, Li, Mg, Na, S, and Si, as they are typical of most rocks and soils relevant to our investigation.…”

Section: Resultsmentioning

confidence: 99%

Geochemical profile of a layered outcrop in the Atacama analogue using laser‐induced breakdown spectroscopy: Implications for Curiosity investigations in Gale

Sobrón

Lefebvre

Léveillé

et al. 2013

Geophysical Research Letters

View full text Add to dashboard Cite

[1] We performed laboratory laser-induced breakdown spectroscopy (LIBS) and laser Raman spectroscopy measurements on samples from a layered outcrop from the Atacama Desert, Chile. This outcrop is a terrestrial morphological and possibly mineralogical analogue for similar formations that will likely be investigated by the Curiosity rover at Gale Crater. Our results demonstrate that fast LIBS analysis can generate semiquantitative chemical profiles in subminute times using automated data processing tools. Therefore, the LIBS instrument can be an invaluable tactical tool on the Curiosity rover for remote, rapid geochemical survey of layered outcrops, thus serving daily operational needs. The derived chemical profiles, supported by the range of minerals identified by Raman spectroscopy, is consistent with the products of a continental evaporitic lake. In the framework of future surface exploration on Mars, a combined Raman/LIBS investigation may provide a rapid mineralogical/chemical evaluation of targets that can be useful for selecting samples to be eventually collected for sample return purposes or for selecting sample sites to be drilled in the search for astrobiology-relevant species. Citation: Sobron,

show abstract

Section: Resultsmentioning

confidence: 99%

Geochemical profile of a layered outcrop in the Atacama analogue using laser‐induced breakdown spectroscopy: Implications for Curiosity investigations in Gale

Sobrón

Lefebvre

Léveillé

et al. 2013

Geophysical Research Letters

View full text Add to dashboard Cite

show abstract

“…In 1990s, commercialization of LIBS for engineering applications became common, and the number of LIBS-based instrumentations grew rapidly. LIBS now has become an irreplaceable analysis method and has been used extensively in many fields including online monitoring of industrial process (Gurell et al 2012;Legnaioli et al 2012;Werheit et al 2011), archeological identification (Staicu et al 2012;Kasem et al 2011;Colao et al 2010), environmental monitoring (Ayyalasomayajula et al 2012;Dell'Aglio et al 2011;Awan et al 2013), geological exploration (Rakovsky et al 2012;Pace et al 2011;Lui and Koujelev 2011), national defense Moros et al 2012), and space exploration (McCanta et al 2013;Wiens et al 2013;Fabre et al 2011).…”

Section: Development and Application Of Libsmentioning

confidence: 99%

Laser-induced breakdown spectroscopy application in environmental monitoring of water quality: a review

et al. 2014

Environ Monit Assess

View full text Add to dashboard Cite

Water quality monitoring is a critical part of environmental management and protection, and to be able to qualitatively and quantitatively determine contamination and impurity levels in water is especially important. Compared to the currently available water quality monitoring methods and techniques, laser-induced breakdown spectroscopy (LIBS) has several advantages, including no need for sample pre-preparation, fast and easy operation, and chemical free during the process. Therefore, it is of great importance to understand the fundamentals of aqueous LIBS analysis and effectively apply this technique to environmental monitoring. This article reviews the research conducted on LIBS analysis for liquid samples, and the article content includes LIBS theory, history and applications, quantitative analysis of metallic species in liquids, LIBS signal enhancement methods and data processing, characteristics of plasma generated by laser in water, and the factors affecting accuracy of analysis results. Although there have been many research works focusing on aqueous LIBS analysis, detection limit and stability of this technique still need to be improved to satisfy the requirements of environmental monitoring standard. In addition, determination of nonmetallic species in liquid by LIBS is equally important and needs immediate attention from the community. This comprehensive review will assist the readers to better understand the aqueous LIBS technique and help to identify current research needs for environmental monitoring of water quality.

show abstract

“…CSA LIBS dataset [32][33][34][35][36], collected by the Canadian Space Agency, which helps the planetary exploration. Similar with NASA, it also provides different types of soil samples and their corresponding trace elements and oxide concentrations.…”

Section: A Datasetsmentioning

confidence: 99%

Hackem-LIBS: An Heterogeneous Stacking Ensemble Model for Laser-Induced Breakdown Spectroscopy Elemental Quantitative Analysis

Zeng

Gong

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Laser-Induced Breakdown Spectroscopy (LIBS) is a popular technique for elemental quantitative analysis in chemistry community, based on which, various methods are developed to determinate the concentrations of chemical samples. Despite the successful applications of the existing methods, they still struggle to obtain accurate samples analyses, due to their limited prediction capability, the complex compositions of samples and mutual interference of elements. In this paper, we propose a novel heterogeneous stacking ensemble learning model called Heterogeneous stACKing Ensemble Model LIBS (Hackem-LIBS) to achieve LIBS quantitative analysis with higher accuracy. Specifically, we propose a stacking ensemble learning framework consisting two stages. In the first stage, we train different heterogeneous component learners with multiple sub-training sets and pick out the optimal learners. In the second stage, we leverage the enhanced features predicted by the selected learners to train a stronger metalearner, which is used to make the final prediction. In addition, we combine Genetic Algorithm (GA) with Sequential Forward Selection (SFS) to reduce the redundancy of training features, which ensures more effective learning and higher computation efficiency. Extensive experiments on two public benchmarks are conducted and the results show that our approach achieves better accuracy in determinating the concentrations of elements and is practically applicable to the quantitative analysis of complex chemical samples via the LIBS technique.

show abstract

Accurate identification of geological samples using artificial neural network processing of laser-induced breakdown spectroscopy data

Cited by 32 publications

References 24 publications

Geochemical profile of a layered outcrop in the Atacama analogue using laser‐induced breakdown spectroscopy: Implications for Curiosity investigations in Gale

Geochemical profile of a layered outcrop in the Atacama analogue using laser‐induced breakdown spectroscopy: Implications for Curiosity investigations in Gale

Laser-induced breakdown spectroscopy application in environmental monitoring of water quality: a review

Hackem-LIBS: An Heterogeneous Stacking Ensemble Model for Laser-Induced Breakdown Spectroscopy Elemental Quantitative Analysis

Contact Info

Product

Resources

About