EUVIMEDEUVIMED entdecken
Crossref

A machine learning q‐RASPR approach for efficient predictions of the specific surface area of perovskites**

Arkaprava Banerjee iD, Agnieszka Gajewicz-Skretna iD, Kunal Roy iD

Molecular Informatics · 2023

DOI: 10.1002/minf.202200261 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Molecular Informatics, 2023. Verfasst von Arkaprava Banerjee und 2 weiteren Autor:innen. Beteiligte Einrichtung: Drug Theoretics and Cheminformatics Laboratory, Department of Pharmaceutical Technology, Jadavpur University, Kolkata, 700 032, India. Hauptthemen laut MEDLINE: Machine Learning, Oxides. Die Arbeit wurde bisher 32-mal zitiert (Crossref) und nennt 40 Literaturangaben. Gefördert von: Science and Engineering Research Board (SERB), Life Science Research Board, DRDO, India.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In this study, the specific surface area of various perovskites was modeled using a novel quantitative read‐across structure‐property relationship (q‐RASPR) approach, which clubs both Read‐Across (RA) and quantitative structure‐property relationship (QSPR) together. After optimization of the hyper‐parameters, certain similarity‐based error measures for each query compound were obtained. Clubbing some of these error‐based measures with the previously selected features along with the Read‐Across prediction function, a number of machine learning models were developed using Partial Least Squares (PLS), Ridge Regression (RR), Linear Support Vector Regression (LSVR), Random Forest (RF) regression, Gradient Boost (GBoost), Adaptive Boosting (Adaboost), Multiple Layer Perceptron (MLP) regression and k‐Nearest Neighbor (kNN) regression. Based on the repeated cross‐validation as well as external prediction quality and interpretability, the PLS model (n Training = 38, n Test = 12, =0.737, was selected as the best predictor which underscored the previously reported results. The finally selected model should efficiently predict specific surface areas of other perovskites for their use in photocatalysis. The new q‐RASPR method also appears promising for the prediction of several other property endpoints of interest in materials science.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningOxidesNeural Networks, ComputerQuantitative Structure-Activity RelationshipTitaniumCalcium Compounds

Stichwörter der Autor:innen

machine learningperovskitesphotocatalysisq-RASPRspecific surface area

Substanzen

OxidesperovskiteTitaniumCalcium Compounds

Autor:innen und Institutionen

  • Drug Theoretics and Cheminformatics Laboratory, Department of Pharmaceutical Technology, Jadavpur University, Kolkata, 700 032, India.
  • Laboratory of Environmental Chemoinformatics, Faculty of Chemistry, University of Gdansk, Gdansk, Wita Stwosza 63, 80-308 Gdansk, Poland.

ORCID-Profile: Arkaprava Banerjee, Agnieszka Gajewicz-Skretna, Kunal Roy

Förderung

  • Science and Engineering Research Board (SERB)
  • Life Science Research Board, DRDO, India

Zitieren

APA

Banerjee, A., Gajewicz-Skretna, A., & Roy, K. (2023). A machine learning q‐RASPR approach for efficient predictions of the specific surface area of perovskites**. Molecular Informatics. https://doi.org/10.1002/minf.202200261

Vancouver

Banerjee A, Gajewicz-Skretna A, Roy K. A machine learning q‐RASPR approach for efficient predictions of the specific surface area of perovskites**. Molecular Informatics. 2023. doi:10.1002/minf.202200261

BibTeX
@article{Banerjee2023,
  author = {Banerjee, Arkaprava and Gajewicz-Skretna, Agnieszka and Roy, Kunal},
  title = {A machine learning q‐RASPR approach for efficient predictions of the specific surface area of perovskites**},
  journal = {Molecular Informatics},
  year = {2023},
  doi = {10.1002/minf.202200261}
}
Kostenlos starten →