<?xml version="1.0" encoding="UTF-8"?>
<?xml-stylesheet type="text/xsl" href="https://zbc.uz.zgora.pl/style/common/xsl/oai-style.xsl"?>
<OAI-PMH xmlns="http://www.openarchives.org/OAI/2.0/" 
         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
         xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/
         http://www.openarchives.org/OAI/2.0/OAI-PMH.xsd">
	<responseDate>2026-07-31T21:41:19Z</responseDate>
	<request identifier="oai:zbc.uz.zgora.pl:97625" metadataPrefix="oai_dc" verb="GetRecord">
	https://zbc.uz.zgora.pl/oai-pmh-repository.xml</request>
	<GetRecord>
	
  <record>
	<header>
		<identifier>oai:zbc.uz.zgora.pl:97625</identifier>
	    <datestamp>2026-07-31T11:13:47Z</datestamp>
		  <setSpec>DigitalLibraryZielonaGora</setSpec> 	      <setSpec>DigitalLibraryZielonaGora:Repository</setSpec> 	      <setSpec>DigitalLibraryZielonaGora:Repository:ListJurnals:IJAME</setSpec> 	      <setSpec>DigitalLibraryZielonaGora:Repository:Faculties</setSpec> 	      <setSpec>DigitalLibraryZielonaGora:Repository:Faculties:FacultyMechanical</setSpec> 	      <setSpec>DigitalLibraryZielonaGora:Repository:ListJurnals:CEER</setSpec> 	      <setSpec>DigitalLibraryZielonaGora:Repository:TypesWork</setSpec> 	      <setSpec>DigitalLibraryZielonaGora:Repository:TypesWork:Articles</setSpec> 	      <setSpec>DigitalLibraryZielonaGora:Repository:ListJurnals</setSpec> 	      <setSpec>DigitalLibraryZielonaGora:Repository:ListJurnals:CEER:CEER26</setSpec> 	    </header>
		<metadata>
	<oai_dc:dc xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/ http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
<dc:title xml:lang="pl"><![CDATA[Probabilistic prediction of permeability damage in waterflooding using gaussian process regression]]></dc:title>
<dc:creator><![CDATA[Saifi, Redha]]></dc:creator>
<dc:creator><![CDATA[Zeraibi, Nourreddine]]></dc:creator>
<dc:creator><![CDATA[Gareche, Mourad]]></dc:creator>
<dc:creator><![CDATA[Nait Amar, Menad]]></dc:creator>
<dc:creator><![CDATA[Benamara, Chahrazed]]></dc:creator>
<dc:subject xml:lang="pl"><![CDATA[waterflooding]]></dc:subject>
<dc:subject xml:lang="pl"><![CDATA[Gaussian process]]></dc:subject>
<dc:subject xml:lang="pl"><![CDATA[scaling deposition]]></dc:subject>
<dc:subject xml:lang="pl"><![CDATA[machine learning]]></dc:subject>
<dc:subject xml:lang="pl"><![CDATA[damage permeability]]></dc:subject>
<dc:description xml:lang="pl"><![CDATA[Waterflooding represents one of the most extensively employed techniques for secondary oil recovery, where water is injected into reservoirs to displace oil toward production wells and enhance hydrocarbon recovery. However, a major challenge in waterflooding operations is salt precipitation, which results from the chemical incompatibility between the injected water, commonly enriched with divalent cations such as calcium, strontium, and barium, and the formation water, which generally exhibits elevated concentrations of sulfate ions. This chemical interaction leads to the formation of sulfate scales, significantly reducing reservoir permeability and hindering oil recovery efficiency.]]></dc:description>
<dc:description xml:lang="pl"><![CDATA[This study employed Gaussian Process Regression (GPR), a nonparametric, probabilistic machine learning method, to predict the extent of permeability damage resulting from sulfate scale deposition during waterflooding.]]></dc:description>
<dc:description xml:lang="pl"><![CDATA[A dataset of 431 experimental tests was used, incorporating input variables such as ion concentrations, differential pressure, temperature, pore volume, and initial permeability. The GPR model successfully captured the nonlinear relationships between these inputs and the resulting permeability damage. Both graphical and statistical evaluations demonstrated strong agreement between the model predictions and experimental results, with a high coefficient of determination (R? = 0.99) and low prediction errors (RMSE = 0.0839; MAE = 0.0529).]]></dc:description>
<dc:description xml:lang="pl"><![CDATA[The GPR model exhibited enhanced predictive accuracy relative to alternative machine learning algorithms, such as decision trees, support vector machines (SVMs), and artificial neural networks. Furthermore, the probabilistic framework of GPR facilitated the quantification of predictive uncertainty, thereby establishing it as a dependable and robust tool for informed operational decision-making in reservoirs susceptible to scaling.]]></dc:description>
<dc:publisher><![CDATA[Zielona Góra: Uniwersytet Zielonogórski]]></dc:publisher>
<dc:contributor><![CDATA[Jurczak, Paweł - red.]]></dc:contributor>
<dc:date><![CDATA[2026]]></dc:date>
<dc:type xml:lang="pl"><![CDATA[artykuł]]></dc:type>
<dc:format xml:lang="pl"><![CDATA[application/pdf]]></dc:format>
<dc:identifier><![CDATA[http://zbc.uz.zgora.pl/Content/97625/Volume31_Issue2_paper_09.pdf]]></dc:identifier>
<dc:identifier><![CDATA[https://zbc.uz.zgora.pl/dlibra/publication/109397/edition/97625/content]]></dc:identifier>
<dc:identifier><![CDATA[oai:zbc.uz.zgora.pl:97625]]></dc:identifier>
<dc:source xml:lang="pl"><![CDATA[IJAME, volume 31, number 2 (2026)]]></dc:source>
<dc:language><![CDATA[eng]]></dc:language>
<dc:relation><![CDATA[oai:zbc.uz.zgora.pl:publication:109397]]></dc:relation>
<dc:rights xml:lang="pl"><![CDATA[Biblioteka Uniwersytetu Zielonogórskiego]]></dc:rights>
<dc:rights xml:lang="pl"><![CDATA[CC 4.0]]></dc:rights>
</oai_dc:dc>

</metadata>
	  </record>	</GetRecord>
</OAI-PMH>
