The use of neural networks for the prediction of zeta potential of kaolinite

Simple item page
dc.contributor.authorErzin Y.
dc.contributor.authorYukselen Y.
dc.date.accessioned2024-07-22T08:21:54Z
dc.date.available2024-07-22T08:21:54Z
dc.date.issued2009
dc.description.abstractThe sign and the magnitude of the zeta potential must be known for many engineering applications. For clay soils, it is usually negative, but it is strongly dependent on the pore fluid chemistry. However, measurement of zeta potential time is time-consuming and requires special and expensive equipment. In this study, the prediction of zeta potential of kaolinite has been investigated by artificial neural networks (ANNs) and multiple regression analyses (MRAs). To achieve this, ANN and MRA models based on zeta potential measurements of kaolinite in the presence of salt and heavy metal cations at different pH values have been developed. The results of the models were compared with the experimental results. The performance indices, including coefficient of determination, root mean square error, mean absolute error, and variance, were used to assess the performance of the prediction capacity of the models developed in this study. The obtained indices make it clear that the constructed ANN models were able to predict zeta potential of kaolinite quite efficiently and outperformed the MRA models. Results showed that ANN models can be used satisfactorily to predict zeta potential of kaolinite as a rapid inexpensive substitute for laboratory techniques. © International Association for Mathematical Geosciences 2009.
dc.identifier.DOI-ID10.1007/s11004-008-9210-4
dc.identifier.issn18748953
dc.identifier.urihttp://akademikarsiv.cbu.edu.tr:4000/handle/123456789/18828
dc.language.isoEnglish
dc.subjectBackpropagation
dc.subjectClay
dc.subjectHeavy metals
dc.subjectKaolinite
dc.subjectRegression analysis
dc.subjectZeta potential
dc.subjectArtificial neural networks
dc.subjectArtificial neural networks approach
dc.subjectClay soil
dc.subjectCoefficient of determination
dc.subjectEngineering applications
dc.subjectHeavy metal cations
dc.subjectLaboratory techniques
dc.subjectMean absolute error
dc.subjectMultiple regression analysis
dc.subjectPerformance indices
dc.subjectpH value
dc.subjectPore fluid chemistry
dc.subjectRoot mean square errors
dc.subjectZeta potential measurements
dc.subjectartificial neural network
dc.subjectclay soil
dc.subjectheavy metal
dc.subjectkaolinite
dc.subjectmeasurement method
dc.subjectmodeling
dc.subjectmultiple regression
dc.subjectprediction
dc.subjectNeural networks
dc.titleThe use of neural networks for the prediction of zeta potential of kaolinite
dc.typeArticle

Files

Collections

Scopus Koleksiyonu