FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4379534698> ?p ?o ?g. }

• W4379534698 endingPage "16962" @default.
• W4379534698 startingPage "16952" @default.
• W4379534698 abstract "Porphyrin-based MOFs combine the unique photophysical and electrochemical properties of metalloporphyrins with the catalytic efficiency of MOF materials, making them an important candidate for light energy harvesting and conversion. However, accurate prediction of the band gap of porphyrin-based MOFs is hampered by their complex structure-function relationships. Although machine learning (ML) has performed well in predicting the properties of MOFs with large training datasets, such ML applications become challenging when the training data size of the materials is small. In this study, we first constructed a dataset of 202 porphyrin-based MOFs using DFT computations and increased the training data size using two data augmentation strategies. After that, four state-of-the-art neural network models were pre-trained with the recognized open-source database QMOF and fine-tuned with our augmented self-curated datasets. The GCN models predicted the band gaps of the porphyrin-based materials with the lowest RMSE of 0.2767 eV and MAE of 0.1463 eV. In addition, the data augmentation strategy rotation and mirroring effectively decreased the RMSE by 38.51% and MAE by 50.05%. This study demonstrates that, when proper transfer learning and data augmentation strategies are applied, machine learning models can predict the properties of MOFs using small training data." @default.
• W4379534698 created "2023-06-07" @default.
• W4379534698 creator A5006984682 @default.
• W4379534698 creator A5027346781 @default.
• W4379534698 creator A5063346330 @default.
• W4379534698 creator A5072777312 @default.
• W4379534698 creator A5073927750 @default.
• W4379534698 creator A5082662124 @default.
• W4379534698 creator A5083862643 @default.
• W4379534698 date "2023-01-01" @default.
• W4379534698 modified "2023-10-12" @default.
• W4379534698 title "Predicting band gaps of MOFs on small data by deep transfer learning with data augmentation strategies" @default.
• W4379534698 cites W1862454224 @default.
• W4379534698 cites W1970188546 @default.
• W4379534698 cites W1976492731 @default.
• W4379534698 cites W1981368803 @default.
• W4379534698 cites W1985628158 @default.
• W4379534698 cites W1986731219 @default.
• W4379534698 cites W1990918587 @default.
• W4379534698 cites W1992985800 @default.
• W4379534698 cites W2007395042 @default.
• W4379534698 cites W2023129992 @default.
• W4379534698 cites W2051893057 @default.
• W4379534698 cites W2071542828 @default.
• W4379534698 cites W2074968443 @default.
• W4379534698 cites W2082430297 @default.
• W4379534698 cites W2083222334 @default.
• W4379534698 cites W2092157292 @default.
• W4379534698 cites W2096747776 @default.
• W4379534698 cites W2133964865 @default.
• W4379534698 cites W2134329894 @default.
• W4379534698 cites W2162894172 @default.
• W4379534698 cites W2311565894 @default.
• W4379534698 cites W2315874900 @default.
• W4379534698 cites W2317536418 @default.
• W4379534698 cites W2334017216 @default.
• W4379534698 cites W2620998991 @default.
• W4379534698 cites W2743321689 @default.
• W4379534698 cites W2755269103 @default.
• W4379534698 cites W2757455114 @default.
• W4379534698 cites W2766856748 @default.
• W4379534698 cites W2808651797 @default.
• W4379534698 cites W2884430236 @default.
• W4379534698 cites W2886978164 @default.
• W4379534698 cites W2949095042 @default.
• W4379534698 cites W2952795682 @default.
• W4379534698 cites W2963807552 @default.
• W4379534698 cites W2972418846 @default.
• W4379534698 cites W2976102057 @default.
• W4379534698 cites W3003267829 @default.
• W4379534698 cites W3017022764 @default.
• W4379534698 cites W3118519758 @default.
• W4379534698 cites W3119774682 @default.
• W4379534698 cites W3124761512 @default.
• W4379534698 cites W3133642770 @default.
• W4379534698 cites W3143460494 @default.
• W4379534698 cites W3184051901 @default.
• W4379534698 cites W3213348597 @default.
• W4379534698 cites W4210760849 @default.
• W4379534698 cites W4225994677 @default.
• W4379534698 cites W4226227198 @default.
• W4379534698 cites W4251066830 @default.
• W4379534698 cites W4280570022 @default.
• W4379534698 cites W4318262876 @default.
• W4379534698 cites W4320011602 @default.
• W4379534698 cites W4352998013 @default.
• W4379534698 doi "https://doi.org/10.1039/d3ra02142d" @default.
• W4379534698 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37288371" @default.
• W4379534698 hasPublicationYear "2023" @default.
• W4379534698 type Work @default.
• W4379534698 citedByCount "1" @default.
• W4379534698 crossrefType "journal-article" @default.
• W4379534698 hasAuthorship W4379534698A5006984682 @default.
• W4379534698 hasAuthorship W4379534698A5027346781 @default.
• W4379534698 hasAuthorship W4379534698A5063346330 @default.
• W4379534698 hasAuthorship W4379534698A5072777312 @default.
• W4379534698 hasAuthorship W4379534698A5073927750 @default.
• W4379534698 hasAuthorship W4379534698A5082662124 @default.
• W4379534698 hasAuthorship W4379534698A5083862643 @default.
• W4379534698 hasBestOaLocation W43795346981 @default.
• W4379534698 hasConcept C105795698 @default.
• W4379534698 hasConcept C108583219 @default.
• W4379534698 hasConcept C119857082 @default.
• W4379534698 hasConcept C139945424 @default.
• W4379534698 hasConcept C144024400 @default.
• W4379534698 hasConcept C150899416 @default.
• W4379534698 hasConcept C153180895 @default.
• W4379534698 hasConcept C154945302 @default.
• W4379534698 hasConcept C181966813 @default.
• W4379534698 hasConcept C185592680 @default.
• W4379534698 hasConcept C189645446 @default.
• W4379534698 hasConcept C192562407 @default.
• W4379534698 hasConcept C2779480358 @default.
• W4379534698 hasConcept C33923547 @default.
• W4379534698 hasConcept C41008148 @default.
• W4379534698 hasConcept C46312422 @default.
• W4379534698 hasConcept C49040817 @default.
• W4379534698 hasConcept C50644808 @default.

• next