Determination of low Z elements concentrations in geological samples by energy dispersive X-ray fluorescence with a back propagation neural network

Due to complex scattering from the sample dark matrix, absorption in the detector window and the competing Auger effect with higher cross-section for low Z elements (Z 0.95. It implied that the modeling approaches significantly overcome matrix effects between the concentrations of low Z elements and...

Full description

Saved in:
Bibliographic Details
Published in:Spectrochimica acta. Part B: Atomic spectroscopy 2022-10, Vol.196, p.106518, Article 106518
Main Authors: Shao, Jinfa, Li, Rongwu, Pan, Qiuli, Cheng, Lin
Format: Article
Language:English
Subjects:
Backpropagation neural network
Compton scatter
Energy dispersive X-ray fluorescence
Geological samples
Low Z elements
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-c227t-b23db2fbc36ff81a2ab5717500c97b0916096d9971641ef0362de79760c5e67e3
cites cdi_FETCH-LOGICAL-c227t-b23db2fbc36ff81a2ab5717500c97b0916096d9971641ef0362de79760c5e67e3
container_end_page
container_issue
container_start_page 106518
container_title Spectrochimica acta. Part B: Atomic spectroscopy
container_volume 196
creator Shao, Jinfa
Li, Rongwu
Pan, Qiuli
Cheng, Lin
description Due to complex scattering from the sample dark matrix, absorption in the detector window and the competing Auger effect with higher cross-section for low Z elements (Z 0.95. It implied that the modeling approaches significantly overcome matrix effects between the concentrations of low Z elements and Compton scatter peaks. So, the method has the potential for being widely used in the analysis of samples rich in low Z elements. [Display omitted] •A BPNN quantitative analysis model of low Z elements in geological samples was developed.•The Compton scatter data ware used for model training.•The model prediction performance is improved by training on correlated elements concentration.•The application of K-fold cross validation improves model accuracy.
doi_str_mv 10.1016/j.sab.2022.106518
format article
fullrecord <record><control><sourceid>elsevier_cross</sourceid><recordid>TN_cdi_crossref_primary_10_1016_j_sab_2022_106518</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0584854722001628</els_id><sourcerecordid>S0584854722001628</sourcerecordid><originalsourceid>FETCH-LOGICAL-c227t-b23db2fbc36ff81a2ab5717500c97b0916096d9971641ef0362de79760c5e67e3</originalsourceid><addsrcrecordid>eNp9kE1OwzAQhS0EEqVwAHZzgRTbqe1ErFD5lSqxAQmxsRxnEtwmcWSnrXoOLkxKWbOaGY3emzcfIdeMzhhl8mY1i6aYccr5OEvBshMyYZlKk1RIcUomVGTzJBNzdU4uYlxRSrngYkK-73HA0LrODM534Cto_A4-ARtssRsiWN_ZsQm_-wiugxp942tnTQPRtH2DEYo9YIeh3kPpYo8hui3CRxLMHqpm4wPG0cMi7NzwBQYKY9fQB9-b-ni2w00Y7Tocdj6sL8lZZZqIV391St4fH94Wz8ny9ellcbdMLOdqSAqelgWvCpvKqsqY4aYQiilBqc1VQXMmaS7LPFdMzhlWNJW8RJUrSa1AqTCdEnb0tcHHGLDSfXCtCXvNqD5Q1Ss9UtUHqvpIddTcHjU4Bts6DDpad_itdAHtoEvv_lH_AEhIg0c</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Determination of low Z elements concentrations in geological samples by energy dispersive X-ray fluorescence with a back propagation neural network</title><source>Elsevier:Jisc Collections:Elsevier Read and Publish Agreement 2022-2024:Freedom Collection (Reading list)</source><creator>Shao, Jinfa ; Li, Rongwu ; Pan, Qiuli ; Cheng, Lin</creator><creatorcontrib>Shao, Jinfa ; Li, Rongwu ; Pan, Qiuli ; Cheng, Lin</creatorcontrib><description>Due to complex scattering from the sample dark matrix, absorption in the detector window and the competing Auger effect with higher cross-section for low Z elements (Z &lt; 14), direct quantification of low Z elements by measuring characteristic X-ray fluorescence intensities during energy dispersive X-ray fluorescence (EDXRF) analysis of geological samples is challenging. This paper reports the chemometric quantitative analysis model of low Z elements (O, Na, Mg, and Al) in geological samples obtained by training the backpropagation neural network (BPNN) using the Compton scatter data combined with the concentrations of measurable elements. The training data is derived from the measured spectra of soil and rock standard samples and their synthetic samples configured with compounds. The standardized Compton scatter data and correlated element concentrations were used as the input data of the BPNN model. The prediction results of the BPNN model show that the coefficient of determination (R2) values between true and predicted concentrations for O, Na, Mg, and Al are both &gt;0.95. It implied that the modeling approaches significantly overcome matrix effects between the concentrations of low Z elements and Compton scatter peaks. So, the method has the potential for being widely used in the analysis of samples rich in low Z elements. [Display omitted] •A BPNN quantitative analysis model of low Z elements in geological samples was developed.•The Compton scatter data ware used for model training.•The model prediction performance is improved by training on correlated elements concentration.•The application of K-fold cross validation improves model accuracy.</description><identifier>ISSN: 0584-8547</identifier><identifier>EISSN: 1873-3565</identifier><identifier>DOI: 10.1016/j.sab.2022.106518</identifier><language>eng</language><publisher>Elsevier B.V</publisher><subject>Backpropagation neural network ; Compton scatter ; Energy dispersive X-ray fluorescence ; Geological samples ; Low Z elements</subject><ispartof>Spectrochimica acta. Part B: Atomic spectroscopy, 2022-10, Vol.196, p.106518, Article 106518</ispartof><rights>2022 Elsevier B.V.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c227t-b23db2fbc36ff81a2ab5717500c97b0916096d9971641ef0362de79760c5e67e3</citedby><cites>FETCH-LOGICAL-c227t-b23db2fbc36ff81a2ab5717500c97b0916096d9971641ef0362de79760c5e67e3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,777,781,27906,27907</link.rule.ids></links><search><creatorcontrib>Shao, Jinfa</creatorcontrib><creatorcontrib>Li, Rongwu</creatorcontrib><creatorcontrib>Pan, Qiuli</creatorcontrib><creatorcontrib>Cheng, Lin</creatorcontrib><title>Determination of low Z elements concentrations in geological samples by energy dispersive X-ray fluorescence with a back propagation neural network</title><title>Spectrochimica acta. Part B: Atomic spectroscopy</title><description>Due to complex scattering from the sample dark matrix, absorption in the detector window and the competing Auger effect with higher cross-section for low Z elements (Z &lt; 14), direct quantification of low Z elements by measuring characteristic X-ray fluorescence intensities during energy dispersive X-ray fluorescence (EDXRF) analysis of geological samples is challenging. This paper reports the chemometric quantitative analysis model of low Z elements (O, Na, Mg, and Al) in geological samples obtained by training the backpropagation neural network (BPNN) using the Compton scatter data combined with the concentrations of measurable elements. The training data is derived from the measured spectra of soil and rock standard samples and their synthetic samples configured with compounds. The standardized Compton scatter data and correlated element concentrations were used as the input data of the BPNN model. The prediction results of the BPNN model show that the coefficient of determination (R2) values between true and predicted concentrations for O, Na, Mg, and Al are both &gt;0.95. It implied that the modeling approaches significantly overcome matrix effects between the concentrations of low Z elements and Compton scatter peaks. So, the method has the potential for being widely used in the analysis of samples rich in low Z elements. [Display omitted] •A BPNN quantitative analysis model of low Z elements in geological samples was developed.•The Compton scatter data ware used for model training.•The model prediction performance is improved by training on correlated elements concentration.•The application of K-fold cross validation improves model accuracy.</description><subject>Backpropagation neural network</subject><subject>Compton scatter</subject><subject>Energy dispersive X-ray fluorescence</subject><subject>Geological samples</subject><subject>Low Z elements</subject><issn>0584-8547</issn><issn>1873-3565</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><recordid>eNp9kE1OwzAQhS0EEqVwAHZzgRTbqe1ErFD5lSqxAQmxsRxnEtwmcWSnrXoOLkxKWbOaGY3emzcfIdeMzhhl8mY1i6aYccr5OEvBshMyYZlKk1RIcUomVGTzJBNzdU4uYlxRSrngYkK-73HA0LrODM534Cto_A4-ARtssRsiWN_ZsQm_-wiugxp942tnTQPRtH2DEYo9YIeh3kPpYo8hui3CRxLMHqpm4wPG0cMi7NzwBQYKY9fQB9-b-ni2w00Y7Tocdj6sL8lZZZqIV391St4fH94Wz8ny9ellcbdMLOdqSAqelgWvCpvKqsqY4aYQiilBqc1VQXMmaS7LPFdMzhlWNJW8RJUrSa1AqTCdEnb0tcHHGLDSfXCtCXvNqD5Q1Ss9UtUHqvpIddTcHjU4Bts6DDpad_itdAHtoEvv_lH_AEhIg0c</recordid><startdate>202210</startdate><enddate>202210</enddate><creator>Shao, Jinfa</creator><creator>Li, Rongwu</creator><creator>Pan, Qiuli</creator><creator>Cheng, Lin</creator><general>Elsevier B.V</general><scope>AAYXX</scope><scope>CITATION</scope></search><sort><creationdate>202210</creationdate><title>Determination of low Z elements concentrations in geological samples by energy dispersive X-ray fluorescence with a back propagation neural network</title><author>Shao, Jinfa ; Li, Rongwu ; Pan, Qiuli ; Cheng, Lin</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c227t-b23db2fbc36ff81a2ab5717500c97b0916096d9971641ef0362de79760c5e67e3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Backpropagation neural network</topic><topic>Compton scatter</topic><topic>Energy dispersive X-ray fluorescence</topic><topic>Geological samples</topic><topic>Low Z elements</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Shao, Jinfa</creatorcontrib><creatorcontrib>Li, Rongwu</creatorcontrib><creatorcontrib>Pan, Qiuli</creatorcontrib><creatorcontrib>Cheng, Lin</creatorcontrib><collection>CrossRef</collection><jtitle>Spectrochimica acta. Part B: Atomic spectroscopy</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Shao, Jinfa</au><au>Li, Rongwu</au><au>Pan, Qiuli</au><au>Cheng, Lin</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Determination of low Z elements concentrations in geological samples by energy dispersive X-ray fluorescence with a back propagation neural network</atitle><jtitle>Spectrochimica acta. Part B: Atomic spectroscopy</jtitle><date>2022-10</date><risdate>2022</risdate><volume>196</volume><spage>106518</spage><pages>106518-</pages><artnum>106518</artnum><issn>0584-8547</issn><eissn>1873-3565</eissn><abstract>Due to complex scattering from the sample dark matrix, absorption in the detector window and the competing Auger effect with higher cross-section for low Z elements (Z &lt; 14), direct quantification of low Z elements by measuring characteristic X-ray fluorescence intensities during energy dispersive X-ray fluorescence (EDXRF) analysis of geological samples is challenging. This paper reports the chemometric quantitative analysis model of low Z elements (O, Na, Mg, and Al) in geological samples obtained by training the backpropagation neural network (BPNN) using the Compton scatter data combined with the concentrations of measurable elements. The training data is derived from the measured spectra of soil and rock standard samples and their synthetic samples configured with compounds. The standardized Compton scatter data and correlated element concentrations were used as the input data of the BPNN model. The prediction results of the BPNN model show that the coefficient of determination (R2) values between true and predicted concentrations for O, Na, Mg, and Al are both &gt;0.95. It implied that the modeling approaches significantly overcome matrix effects between the concentrations of low Z elements and Compton scatter peaks. So, the method has the potential for being widely used in the analysis of samples rich in low Z elements. [Display omitted] •A BPNN quantitative analysis model of low Z elements in geological samples was developed.•The Compton scatter data ware used for model training.•The model prediction performance is improved by training on correlated elements concentration.•The application of K-fold cross validation improves model accuracy.</abstract><pub>Elsevier B.V</pub><doi>10.1016/j.sab.2022.106518</doi></addata></record>
fulltext fulltext
identifier ISSN: 0584-8547
ispartof Spectrochimica acta. Part B: Atomic spectroscopy, 2022-10, Vol.196, p.106518, Article 106518
issn 0584-8547
1873-3565
language eng
recordid cdi_crossref_primary_10_1016_j_sab_2022_106518
source Elsevier:Jisc Collections:Elsevier Read and Publish Agreement 2022-2024:Freedom Collection (Reading list)
subjects Backpropagation neural network
Compton scatter
Energy dispersive X-ray fluorescence
Geological samples
Low Z elements
title Determination of low Z elements concentrations in geological samples by energy dispersive X-ray fluorescence with a back propagation neural network
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-17T08%3A03%3A44IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-elsevier_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Determination%20of%20low%20Z%20elements%20concentrations%20in%20geological%20samples%20by%20energy%20dispersive%20X-ray%20fluorescence%20with%20a%20back%20propagation%20neural%20network&rft.jtitle=Spectrochimica%20acta.%20Part%20B:%20Atomic%20spectroscopy&rft.au=Shao,%20Jinfa&rft.date=2022-10&rft.volume=196&rft.spage=106518&rft.pages=106518-&rft.artnum=106518&rft.issn=0584-8547&rft.eissn=1873-3565&rft_id=info:doi/10.1016/j.sab.2022.106518&rft_dat=%3Celsevier_cross%3ES0584854722001628%3C/elsevier_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c227t-b23db2fbc36ff81a2ab5717500c97b0916096d9971641ef0362de79760c5e67e3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true