Academic Journal
Προβολή σε EDS

Interpretable Machine Learning Approach for Photocatalytic Degradation in Mn-Doped Semiconductors Using Multilayer Perceptron and SHAP Analysis.

Λεπτομέρειες βιβλιογραφικής εγγραφής
Τίτλος: Interpretable Machine Learning Approach for Photocatalytic Degradation in Mn-Doped Semiconductors Using Multilayer Perceptron and SHAP Analysis.
Συγγραφείς: Baytar, Orhan, Zontul, Metin, Orak, Ceren, Karateke, Seda, Aydın, Hakan, Horoz, Sabit
Πηγή: Catalysts (2073-4344); Jun2026, Vol. 16 Issue 6, p530, 19p
Θεματικοί όροι: Doped semiconductors, Multilayer perceptrons, Photodegradation, Machine learning, Absorption spectra, Nonlinear statistical models, Shapley Additive Explanations
Περίληψη: This study comprehensively investigates the degradation performance of a Mn-doped Zn2SnO4 photocatalyst based on time-dependent UV-Vis absorption spectra. Before machine learning modelling, the effects of experimental parameters such as UV–Vis measurement wavelength, reaction time, and Mn doping ratio were statistically validated using One-Way Analysis of Variance (ANOVA) and Multiple Linear Regression (MLR) methods. To overcome the limitations of linear models in representing complex physical systems, an optimized Multi-Layer Perceptron (MLP) architecture was developed to capture the system's nonlinear dynamics with high accuracy. To validate the model's out-of-sample prediction capability and prevent data leakage potentially arising from spectral data correlation, the "Leave-One-Doping-Level-Out" (LODLO) cross-validation strategy was applied, during which performance metrics of R2 = 0.8889 and M S E = 0.00238 were recorded. To make the neural network's decision-making mechanism transparent, a dual-validation explainability framework comprising Shapley Additive Explanations (SHAP) and Permutation Feature Importance analyses was employed. By quantifying the relative contributions of the experimental parameters to the model predictions, this approach revealed that the UV–Vis measurement wavelength was the dominant predictive variable, followed by the Mn doping ratio and reaction time. This study presents a transparent methodology that offers both strong predictive capability and physically grounded data to shed light on the complex interactions in doped semiconductor photocatalysts. [ABSTRACT FROM AUTHOR]
Copyright of Catalysts (2073-4344) is the property of MDPI and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Βάση Δεδομένων: Complementary Index
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://resolver.ebsco.com/c/fiv2js/result?sid=EBSCO:edb&genre=article&issn=20734344&ISBN=&volume=16&issue=6&date=20260601&spage=530&pages=530-548&title=Catalysts (2073-4344)&atitle=Interpretable%20Machine%20Learning%20Approach%20for%20Photocatalytic%20Degradation%20in%20Mn-Doped%20Semiconductors%20Using%20Multilayer%20Perceptron%20and%20SHAP%20Analysis.&aulast=Baytar%2C%20Orhan&id=DOI:10.3390/catal16060530
    Name: Full Text Finder (for New FTF UI) (ns324271)
    Category: fullText
    Text: Full Text Finder
    MouseOverText: Full Text Finder
Header DbId: edb
DbLabel: Complementary Index
An: 194905988
RelevancyScore: 1082
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 1082.4189453125
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Interpretable Machine Learning Approach for Photocatalytic Degradation in Mn-Doped Semiconductors Using Multilayer Perceptron and SHAP Analysis.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Baytar%2C+Orhan%22">Baytar, Orhan</searchLink><br /><searchLink fieldCode="AR" term="%22Zontul%2C+Metin%22">Zontul, Metin</searchLink><br /><searchLink fieldCode="AR" term="%22Orak%2C+Ceren%22">Orak, Ceren</searchLink><br /><searchLink fieldCode="AR" term="%22Karateke%2C+Seda%22">Karateke, Seda</searchLink><br /><searchLink fieldCode="AR" term="%22Aydın%2C+Hakan%22">Aydın, Hakan</searchLink><br /><searchLink fieldCode="AR" term="%22Horoz%2C+Sabit%22">Horoz, Sabit</searchLink>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: Catalysts (2073-4344); Jun2026, Vol. 16 Issue 6, p530, 19p
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Doped+semiconductors%22">Doped semiconductors</searchLink><br /><searchLink fieldCode="DE" term="%22Multilayer+perceptrons%22">Multilayer perceptrons</searchLink><br /><searchLink fieldCode="DE" term="%22Photodegradation%22">Photodegradation</searchLink><br /><searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink><br /><searchLink fieldCode="DE" term="%22Absorption+spectra%22">Absorption spectra</searchLink><br /><searchLink fieldCode="DE" term="%22Nonlinear+statistical+models%22">Nonlinear statistical models</searchLink><br /><searchLink fieldCode="DE" term="%22Shapley+Additive+Explanations%22">Shapley Additive Explanations</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: This study comprehensively investigates the degradation performance of a Mn-doped Zn<subscript>2</subscript>SnO<subscript>4</subscript> photocatalyst based on time-dependent UV-Vis absorption spectra. Before machine learning modelling, the effects of experimental parameters such as UV–Vis measurement wavelength, reaction time, and Mn doping ratio were statistically validated using One-Way Analysis of Variance (ANOVA) and Multiple Linear Regression (MLR) methods. To overcome the limitations of linear models in representing complex physical systems, an optimized Multi-Layer Perceptron (MLP) architecture was developed to capture the system's nonlinear dynamics with high accuracy. To validate the model's out-of-sample prediction capability and prevent data leakage potentially arising from spectral data correlation, the "Leave-One-Doping-Level-Out" (LODLO) cross-validation strategy was applied, during which performance metrics of R<superscript>2</superscript> = 0.8889 and M S E = 0.00238 were recorded. To make the neural network's decision-making mechanism transparent, a dual-validation explainability framework comprising Shapley Additive Explanations (SHAP) and Permutation Feature Importance analyses was employed. By quantifying the relative contributions of the experimental parameters to the model predictions, this approach revealed that the UV–Vis measurement wavelength was the dominant predictive variable, followed by the Mn doping ratio and reaction time. This study presents a transparent methodology that offers both strong predictive capability and physically grounded data to shed light on the complex interactions in doped semiconductor photocatalysts. [ABSTRACT FROM AUTHOR]
– Name: Abstract
  Label:
  Group: Ab
  Data: <i>Copyright of Catalysts (2073-4344) is the property of MDPI and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edb&AN=194905988
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.3390/catal16060530
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 19
        StartPage: 530
    Subjects:
      – SubjectFull: Doped semiconductors
        Type: general
      – SubjectFull: Multilayer perceptrons
        Type: general
      – SubjectFull: Photodegradation
        Type: general
      – SubjectFull: Machine learning
        Type: general
      – SubjectFull: Absorption spectra
        Type: general
      – SubjectFull: Nonlinear statistical models
        Type: general
      – SubjectFull: Shapley Additive Explanations
        Type: general
    Titles:
      – TitleFull: Interpretable Machine Learning Approach for Photocatalytic Degradation in Mn-Doped Semiconductors Using Multilayer Perceptron and SHAP Analysis.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Baytar, Orhan
      – PersonEntity:
          Name:
            NameFull: Zontul, Metin
      – PersonEntity:
          Name:
            NameFull: Orak, Ceren
      – PersonEntity:
          Name:
            NameFull: Karateke, Seda
      – PersonEntity:
          Name:
            NameFull: Aydın, Hakan
      – PersonEntity:
          Name:
            NameFull: Horoz, Sabit
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 06
              Text: Jun2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 20734344
          Numbering:
            – Type: volume
              Value: 16
            – Type: issue
              Value: 6
          Titles:
            – TitleFull: Catalysts (2073-4344)
              Type: main
ResultId 1