Comparative Analysis of Geochemical Data Processing Methods for Allocation of Anomalies and Background

In this paper, the capabilities of demotic unsupervised learning approaches were investigated to improve the procedure of geochemical anomaly identification. The separation of anomalous concentrations from the background is a crucial task in the mathematical analysis of geochemical data. The convent...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Geochemistry international 2020-04, Vol.58 (4), p.472-485
Hauptverfasser: Esmaeiloghli, S., Tabatabaei, S. H.
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 485
container_issue 4
container_start_page 472
container_title Geochemistry international
container_volume 58
creator Esmaeiloghli, S.
Tabatabaei, S. H.
description In this paper, the capabilities of demotic unsupervised learning approaches were investigated to improve the procedure of geochemical anomaly identification. The separation of anomalous concentrations from the background is a crucial task in the mathematical analysis of geochemical data. The conventional methods rely on the statistical thresholds routinely; however, determining such boundary values fundamentally entails a normally distributed data and the involvement of expert knowledge. The unsupervised machine learning provides state-of-the-art facilities based on the information theory that leveraged to classify the geochemical data into the anomaly and background concentrations with specific characteristics. To examine the integrity of performance of geochemical data processing tools, the prevalent unsupervised learning methods of k -means, k -medoids, k -medians, expectation-maximization (EM) clustering, density-based spatial clustering of applications with noise (DBSCAN), and self-organizing maps (SOM), as well as traditional threshold-based techniques of the mean plus two standard deviations ( ) and the concentration-number (C-N) fractal model were subjected to the separation of Cu anomalies from the background within 300 rock samples collected from Shadan porphyry copper deposit, northeast Iran. The efficiency of methods was quantitatively measured using criteria comprising student’s t -test, signal to noise ratio, and the pooled coefficient of variation. The appraisal criteria have confirmed that most of the unsupervised techniques manage to isolate the geochemical anomalies from the background with a more significant contrast compared to the conventional methods of and C-N fractal model. The EM clustering has revealed the best performance among them so that it allocates the anomalies with the maximum resolution and distinguishes the weak anomalies from the high background. The anomaly Cu map obtained by the EM method has represented a significant spatial pattern that is properly consistent with the geological and mineralization evidences within the study area. The utilization of unsupervised learning methods substantially enjoys some advantages such as anomaly intensification, automaticity, being fast and non-parametric, and the capability to expand to the multivariate analysis.
doi_str_mv 10.1134/S0016702920040084
format Article
fullrecord <record><control><sourceid>gale_proqu</sourceid><recordid>TN_cdi_proquest_journals_2388033372</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><galeid>A720578490</galeid><sourcerecordid>A720578490</sourcerecordid><originalsourceid>FETCH-LOGICAL-a378t-5a86b9f8f1028eb68e4757a5d1febdb03daf6b4505b04c3b704a5fec19a45efc3</originalsourceid><addsrcrecordid>eNp1kEFr3DAQhUVpINukPyA3Qc9OR5ZkyUd326aFhBSSns1YHm2ceqWt5C3k31dmCz2UMoeBmfcN8x5jVwKuhZDq_QOAaAzUbQ2gAKx6xTZC66YSbWNfs826rtb9OXuT83MRKdmaDfPbuD9gwmX6RbwLOL_kKfPo-Q1F90T7yeHMP-KC_FuKjnKewo7f0fIUx8x9TLyb5-gKHsNKdSHucZ4ocwwj_4Duxy7FYxgv2ZnHOdPbP_2Cff_86XH7pbq9v_m67W4rlMYulUbbDK23XkBtaWgsKaMN6lF4GsYB5Ii-GZQGPYBycjCgUHtyokWlyTt5wd6d7h5S_HmkvPTP8ZiKrdzX0lqQUpq6qK5Pqh3O1E_BxyWhKzWuhmMgP5V5Z2rQxqoWCiBOgEsx50S-P6Rpj-mlF9Cv-ff_5F-Y-sTkog07Sn9f-T_0GwePh4Y</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2388033372</pqid></control><display><type>article</type><title>Comparative Analysis of Geochemical Data Processing Methods for Allocation of Anomalies and Background</title><source>SpringerNature Journals</source><creator>Esmaeiloghli, S. ; Tabatabaei, S. H.</creator><creatorcontrib>Esmaeiloghli, S. ; Tabatabaei, S. H.</creatorcontrib><description>In this paper, the capabilities of demotic unsupervised learning approaches were investigated to improve the procedure of geochemical anomaly identification. The separation of anomalous concentrations from the background is a crucial task in the mathematical analysis of geochemical data. The conventional methods rely on the statistical thresholds routinely; however, determining such boundary values fundamentally entails a normally distributed data and the involvement of expert knowledge. The unsupervised machine learning provides state-of-the-art facilities based on the information theory that leveraged to classify the geochemical data into the anomaly and background concentrations with specific characteristics. To examine the integrity of performance of geochemical data processing tools, the prevalent unsupervised learning methods of k -means, k -medoids, k -medians, expectation-maximization (EM) clustering, density-based spatial clustering of applications with noise (DBSCAN), and self-organizing maps (SOM), as well as traditional threshold-based techniques of the mean plus two standard deviations ( ) and the concentration-number (C-N) fractal model were subjected to the separation of Cu anomalies from the background within 300 rock samples collected from Shadan porphyry copper deposit, northeast Iran. The efficiency of methods was quantitatively measured using criteria comprising student’s t -test, signal to noise ratio, and the pooled coefficient of variation. The appraisal criteria have confirmed that most of the unsupervised techniques manage to isolate the geochemical anomalies from the background with a more significant contrast compared to the conventional methods of and C-N fractal model. The EM clustering has revealed the best performance among them so that it allocates the anomalies with the maximum resolution and distinguishes the weak anomalies from the high background. The anomaly Cu map obtained by the EM method has represented a significant spatial pattern that is properly consistent with the geological and mineralization evidences within the study area. The utilization of unsupervised learning methods substantially enjoys some advantages such as anomaly intensification, automaticity, being fast and non-parametric, and the capability to expand to the multivariate analysis.</description><identifier>ISSN: 0016-7029</identifier><identifier>EISSN: 1556-1968</identifier><identifier>DOI: 10.1134/S0016702920040084</identifier><language>eng</language><publisher>Moscow: Pleiades Publishing</publisher><subject>Anomalies ; Automation ; Clustering ; Coefficient of variation ; Comparative analysis ; Copper ; Copper industry ; Data ; Data analysis ; Data processing ; Earth and Environmental Science ; Earth Sciences ; Electronic data processing ; Fractal models ; Fractals ; Geochemistry ; Information theory ; Learning algorithms ; Machine learning ; Mathematical analysis ; Measurement methods ; Methods ; Mineralization ; Multivariate analysis ; Numerical analysis ; Porphyry ; Porphyry copper ; Sediment samples ; Self organizing maps ; Separation ; Signal to noise ratio ; Statistical methods</subject><ispartof>Geochemistry international, 2020-04, Vol.58 (4), p.472-485</ispartof><rights>Pleiades Publishing, Ltd. 2020</rights><rights>COPYRIGHT 2020 Springer</rights><rights>Pleiades Publishing, Ltd. 2020.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-a378t-5a86b9f8f1028eb68e4757a5d1febdb03daf6b4505b04c3b704a5fec19a45efc3</citedby><cites>FETCH-LOGICAL-a378t-5a86b9f8f1028eb68e4757a5d1febdb03daf6b4505b04c3b704a5fec19a45efc3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://link.springer.com/content/pdf/10.1134/S0016702920040084$$EPDF$$P50$$Gspringer$$H</linktopdf><linktohtml>$$Uhttps://link.springer.com/10.1134/S0016702920040084$$EHTML$$P50$$Gspringer$$H</linktohtml><link.rule.ids>314,780,784,27924,27925,41488,42557,51319</link.rule.ids></links><search><creatorcontrib>Esmaeiloghli, S.</creatorcontrib><creatorcontrib>Tabatabaei, S. H.</creatorcontrib><title>Comparative Analysis of Geochemical Data Processing Methods for Allocation of Anomalies and Background</title><title>Geochemistry international</title><addtitle>Geochem. Int</addtitle><description>In this paper, the capabilities of demotic unsupervised learning approaches were investigated to improve the procedure of geochemical anomaly identification. The separation of anomalous concentrations from the background is a crucial task in the mathematical analysis of geochemical data. The conventional methods rely on the statistical thresholds routinely; however, determining such boundary values fundamentally entails a normally distributed data and the involvement of expert knowledge. The unsupervised machine learning provides state-of-the-art facilities based on the information theory that leveraged to classify the geochemical data into the anomaly and background concentrations with specific characteristics. To examine the integrity of performance of geochemical data processing tools, the prevalent unsupervised learning methods of k -means, k -medoids, k -medians, expectation-maximization (EM) clustering, density-based spatial clustering of applications with noise (DBSCAN), and self-organizing maps (SOM), as well as traditional threshold-based techniques of the mean plus two standard deviations ( ) and the concentration-number (C-N) fractal model were subjected to the separation of Cu anomalies from the background within 300 rock samples collected from Shadan porphyry copper deposit, northeast Iran. The efficiency of methods was quantitatively measured using criteria comprising student’s t -test, signal to noise ratio, and the pooled coefficient of variation. The appraisal criteria have confirmed that most of the unsupervised techniques manage to isolate the geochemical anomalies from the background with a more significant contrast compared to the conventional methods of and C-N fractal model. The EM clustering has revealed the best performance among them so that it allocates the anomalies with the maximum resolution and distinguishes the weak anomalies from the high background. The anomaly Cu map obtained by the EM method has represented a significant spatial pattern that is properly consistent with the geological and mineralization evidences within the study area. The utilization of unsupervised learning methods substantially enjoys some advantages such as anomaly intensification, automaticity, being fast and non-parametric, and the capability to expand to the multivariate analysis.</description><subject>Anomalies</subject><subject>Automation</subject><subject>Clustering</subject><subject>Coefficient of variation</subject><subject>Comparative analysis</subject><subject>Copper</subject><subject>Copper industry</subject><subject>Data</subject><subject>Data analysis</subject><subject>Data processing</subject><subject>Earth and Environmental Science</subject><subject>Earth Sciences</subject><subject>Electronic data processing</subject><subject>Fractal models</subject><subject>Fractals</subject><subject>Geochemistry</subject><subject>Information theory</subject><subject>Learning algorithms</subject><subject>Machine learning</subject><subject>Mathematical analysis</subject><subject>Measurement methods</subject><subject>Methods</subject><subject>Mineralization</subject><subject>Multivariate analysis</subject><subject>Numerical analysis</subject><subject>Porphyry</subject><subject>Porphyry copper</subject><subject>Sediment samples</subject><subject>Self organizing maps</subject><subject>Separation</subject><subject>Signal to noise ratio</subject><subject>Statistical methods</subject><issn>0016-7029</issn><issn>1556-1968</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><recordid>eNp1kEFr3DAQhUVpINukPyA3Qc9OR5ZkyUd326aFhBSSns1YHm2ceqWt5C3k31dmCz2UMoeBmfcN8x5jVwKuhZDq_QOAaAzUbQ2gAKx6xTZC66YSbWNfs826rtb9OXuT83MRKdmaDfPbuD9gwmX6RbwLOL_kKfPo-Q1F90T7yeHMP-KC_FuKjnKewo7f0fIUx8x9TLyb5-gKHsNKdSHucZ4ocwwj_4Duxy7FYxgv2ZnHOdPbP_2Cff_86XH7pbq9v_m67W4rlMYulUbbDK23XkBtaWgsKaMN6lF4GsYB5Ii-GZQGPYBycjCgUHtyokWlyTt5wd6d7h5S_HmkvPTP8ZiKrdzX0lqQUpq6qK5Pqh3O1E_BxyWhKzWuhmMgP5V5Z2rQxqoWCiBOgEsx50S-P6Rpj-mlF9Cv-ff_5F-Y-sTkog07Sn9f-T_0GwePh4Y</recordid><startdate>20200401</startdate><enddate>20200401</enddate><creator>Esmaeiloghli, S.</creator><creator>Tabatabaei, S. H.</creator><general>Pleiades Publishing</general><general>Springer</general><general>Springer Nature B.V</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7QH</scope><scope>7UA</scope><scope>C1K</scope><scope>F1W</scope><scope>H96</scope><scope>L.G</scope></search><sort><creationdate>20200401</creationdate><title>Comparative Analysis of Geochemical Data Processing Methods for Allocation of Anomalies and Background</title><author>Esmaeiloghli, S. ; Tabatabaei, S. H.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a378t-5a86b9f8f1028eb68e4757a5d1febdb03daf6b4505b04c3b704a5fec19a45efc3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Anomalies</topic><topic>Automation</topic><topic>Clustering</topic><topic>Coefficient of variation</topic><topic>Comparative analysis</topic><topic>Copper</topic><topic>Copper industry</topic><topic>Data</topic><topic>Data analysis</topic><topic>Data processing</topic><topic>Earth and Environmental Science</topic><topic>Earth Sciences</topic><topic>Electronic data processing</topic><topic>Fractal models</topic><topic>Fractals</topic><topic>Geochemistry</topic><topic>Information theory</topic><topic>Learning algorithms</topic><topic>Machine learning</topic><topic>Mathematical analysis</topic><topic>Measurement methods</topic><topic>Methods</topic><topic>Mineralization</topic><topic>Multivariate analysis</topic><topic>Numerical analysis</topic><topic>Porphyry</topic><topic>Porphyry copper</topic><topic>Sediment samples</topic><topic>Self organizing maps</topic><topic>Separation</topic><topic>Signal to noise ratio</topic><topic>Statistical methods</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Esmaeiloghli, S.</creatorcontrib><creatorcontrib>Tabatabaei, S. H.</creatorcontrib><collection>CrossRef</collection><collection>Aqualine</collection><collection>Water Resources Abstracts</collection><collection>Environmental Sciences and Pollution Management</collection><collection>ASFA: Aquatic Sciences and Fisheries Abstracts</collection><collection>Aquatic Science &amp; Fisheries Abstracts (ASFA) 2: Ocean Technology, Policy &amp; Non-Living Resources</collection><collection>Aquatic Science &amp; Fisheries Abstracts (ASFA) Professional</collection><jtitle>Geochemistry international</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Esmaeiloghli, S.</au><au>Tabatabaei, S. H.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Comparative Analysis of Geochemical Data Processing Methods for Allocation of Anomalies and Background</atitle><jtitle>Geochemistry international</jtitle><stitle>Geochem. Int</stitle><date>2020-04-01</date><risdate>2020</risdate><volume>58</volume><issue>4</issue><spage>472</spage><epage>485</epage><pages>472-485</pages><issn>0016-7029</issn><eissn>1556-1968</eissn><abstract>In this paper, the capabilities of demotic unsupervised learning approaches were investigated to improve the procedure of geochemical anomaly identification. The separation of anomalous concentrations from the background is a crucial task in the mathematical analysis of geochemical data. The conventional methods rely on the statistical thresholds routinely; however, determining such boundary values fundamentally entails a normally distributed data and the involvement of expert knowledge. The unsupervised machine learning provides state-of-the-art facilities based on the information theory that leveraged to classify the geochemical data into the anomaly and background concentrations with specific characteristics. To examine the integrity of performance of geochemical data processing tools, the prevalent unsupervised learning methods of k -means, k -medoids, k -medians, expectation-maximization (EM) clustering, density-based spatial clustering of applications with noise (DBSCAN), and self-organizing maps (SOM), as well as traditional threshold-based techniques of the mean plus two standard deviations ( ) and the concentration-number (C-N) fractal model were subjected to the separation of Cu anomalies from the background within 300 rock samples collected from Shadan porphyry copper deposit, northeast Iran. The efficiency of methods was quantitatively measured using criteria comprising student’s t -test, signal to noise ratio, and the pooled coefficient of variation. The appraisal criteria have confirmed that most of the unsupervised techniques manage to isolate the geochemical anomalies from the background with a more significant contrast compared to the conventional methods of and C-N fractal model. The EM clustering has revealed the best performance among them so that it allocates the anomalies with the maximum resolution and distinguishes the weak anomalies from the high background. The anomaly Cu map obtained by the EM method has represented a significant spatial pattern that is properly consistent with the geological and mineralization evidences within the study area. The utilization of unsupervised learning methods substantially enjoys some advantages such as anomaly intensification, automaticity, being fast and non-parametric, and the capability to expand to the multivariate analysis.</abstract><cop>Moscow</cop><pub>Pleiades Publishing</pub><doi>10.1134/S0016702920040084</doi><tpages>14</tpages></addata></record>
fulltext fulltext
identifier ISSN: 0016-7029
ispartof Geochemistry international, 2020-04, Vol.58 (4), p.472-485
issn 0016-7029
1556-1968
language eng
recordid cdi_proquest_journals_2388033372
source SpringerNature Journals
subjects Anomalies
Automation
Clustering
Coefficient of variation
Comparative analysis
Copper
Copper industry
Data
Data analysis
Data processing
Earth and Environmental Science
Earth Sciences
Electronic data processing
Fractal models
Fractals
Geochemistry
Information theory
Learning algorithms
Machine learning
Mathematical analysis
Measurement methods
Methods
Mineralization
Multivariate analysis
Numerical analysis
Porphyry
Porphyry copper
Sediment samples
Self organizing maps
Separation
Signal to noise ratio
Statistical methods
title Comparative Analysis of Geochemical Data Processing Methods for Allocation of Anomalies and Background
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T21%3A32%3A35IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-gale_proqu&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Comparative%20Analysis%20of%20Geochemical%20Data%20Processing%20Methods%20for%20Allocation%20of%20Anomalies%20and%20Background&rft.jtitle=Geochemistry%20international&rft.au=Esmaeiloghli,%20S.&rft.date=2020-04-01&rft.volume=58&rft.issue=4&rft.spage=472&rft.epage=485&rft.pages=472-485&rft.issn=0016-7029&rft.eissn=1556-1968&rft_id=info:doi/10.1134/S0016702920040084&rft_dat=%3Cgale_proqu%3EA720578490%3C/gale_proqu%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2388033372&rft_id=info:pmid/&rft_galeid=A720578490&rfr_iscdi=true