Açık Akademik Arşiv Sistemi

Predicting the multiple parameters of organic acceptors through machine learning using RDkit descriptors: An easy and fast pipeline

Show simple item record

dc.contributor.authors Katubi, KM; Saqib, M; Mubashir, T; Tahir, MH; Halawa, MI; Akbar, A; Basha, B; Sulaman, M; Alrowaili, ZA; Al-Buriahi, MS
dc.date.accessioned 2024-02-23T11:45:20Z
dc.date.available 2024-02-23T11:45:20Z
dc.date.issued 2023
dc.identifier.issn 0020-7608
dc.identifier.uri http://dx.doi.org/10.1002/qua.27230
dc.identifier.uri https://hdl.handle.net/20.500.12619/102257
dc.description Bu yayın 06.11.1981 tarihli ve 17506 sayılı Resmî Gazete’de yayımlanan 2547 sayılı Yükseköğretim Kanunu’nun 4/c, 12/c, 42/c ve 42/d maddelerine dayalı 12/12/2019 tarih, 543 sayılı ve 05 numaralı Üniversite Senato Kararı ile hazırlanan Sakarya Üniversitesi Açık Bilim ve Açık Akademik Arşiv Yönergesi gereğince açık akademik arşiv sistemine açık erişim olarak yüklenmiştir.
dc.description.abstract Machine learning (ML) analysis has gained huge importance among researchers for predicting multiple parameters and designing efficient donor and acceptor materials without experimentation. Data are collected from literature and subsequently used for predicting impactful properties of organic solar cells such as power conversion efficiency (PCE) and energy levels (HOMO/LUMO). Importantly, out of various tested models, hist gradient boosting (HGB) and the light gradient boosting (LGBM) regression models revealed better predictive capabilities. To achieve the prediction effectively, the selected (best) ML regression models are further tuned. For the prediction of PCE (test set), the LGBM shows the coefficient of determination (R-2) value of 0.787, which is higher than HGB (R-2 = 0.680). For the prediction of HOMO (test set), the LGBM shows R-2 value of 0.566, which is higher than HGB (R-2 = 0.563). However, for the prediction of LUMO (test set), the LGBM shows R-2 value of 0.605, which is lower than HGB (R-2 = 0.606). Among the three predicted properties, prediction ability is higher for PCE. These models help to predict the efficient acceptors in a short time and less computational cost.
dc.language English
dc.language.iso eng
dc.publisher WILEY
dc.relation.isversionof 10.1002/qua.27230
dc.subject hist gradient boosting regression model
dc.subject light gradient boosting regression model
dc.subject machine learning
dc.subject organic acceptors
dc.subject RDkit
dc.title Predicting the multiple parameters of organic acceptors through machine learning using RDkit descriptors: An easy and fast pipeline
dc.type Article
dc.relation.journal INTERNATIONAL JOURNAL OF QUANTUM CHEMISTRY
dc.identifier.doi 10.1002/qua.27230
dc.identifier.eissn 1097-461X
dc.contributor.author Katubi, Khadijah Mohammedsaleh
dc.contributor.author Saqib, Muhammad
dc.contributor.author Mubashir, Tayyaba
dc.contributor.author Tahir, Mudassir Hussain
dc.contributor.author Halawa, Mohamed Ibrahim
dc.contributor.author Akbar, Alveena
dc.contributor.author Basha, Beriham
dc.contributor.author Sulaman, Muhammad
dc.contributor.author Alrowaili, Z. A.
dc.contributor.author Al-Buriahi, M. S.
dc.relation.publicationcategory Makale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rights.openaccessdesignations Bronze


Files in this item

Files Size Format View

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record