FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386475288> ?p ?o ?g. }

• W4386475288 abstract "The presence of point defects, such as vacancies, plays an important role in materials design. Here, we explore the extrapolative power of a graph neural network (GNN) to predict vacancy formation energies. We show that a model trained only on perfect materials can also be used to predict vacancy formation energies (Evac) of defect structures without the need for additional training data. Such GNN-based predictions are considerably faster than density functional theory (DFT) calculations and show potential as a quick pre-screening tool for defect systems. To test this strategy, we developed a DFT dataset of 530 Evac consisting of 3D elemental solids, alloys, oxides, semiconductors, and 2D monolayer materials. We analyzed and discussed the applicability of such direct and fast predictions. We applied the model to predict 192 494 Evac for 55 723 materials in the JARVIS-DFT database. Our work demonstrates how a GNN-model performs on unseen data." @default.
• W4386475288 created "2023-09-07" @default.
• W4386475288 creator A5019215236 @default.
• W4386475288 creator A5042083426 @default.
• W4386475288 date "2023-09-01" @default.
• W4386475288 modified "2023-09-27" @default.
• W4386475288 title "Can a deep-learning model make fast predictions of vacancy formation in diverse materials?" @default.
• W4386475288 cites W1606333844 @default.
• W4386475288 cites W1970127494 @default.
• W4386475288 cites W1990763630 @default.
• W4386475288 cites W2004436642 @default.
• W4386475288 cites W2004985605 @default.
• W4386475288 cites W2007395042 @default.
• W4386475288 cites W2019281047 @default.
• W4386475288 cites W2070029819 @default.
• W4386475288 cites W2083222334 @default.
• W4386475288 cites W2083561999 @default.
• W4386475288 cites W2105709682 @default.
• W4386475288 cites W2120183722 @default.
• W4386475288 cites W2121192472 @default.
• W4386475288 cites W2158043072 @default.
• W4386475288 cites W2158650224 @default.
• W4386475288 cites W2289974802 @default.
• W4386475288 cites W2336435100 @default.
• W4386475288 cites W2475256989 @default.
• W4386475288 cites W2547490100 @default.
• W4386475288 cites W2757022439 @default.
• W4386475288 cites W2767101995 @default.
• W4386475288 cites W2889627612 @default.
• W4386475288 cites W2902127761 @default.
• W4386475288 cites W2913147132 @default.
• W4386475288 cites W2914701535 @default.
• W4386475288 cites W2942736824 @default.
• W4386475288 cites W3021533372 @default.
• W4386475288 cites W3033534502 @default.
• W4386475288 cites W3042403427 @default.
• W4386475288 cites W3084354688 @default.
• W4386475288 cites W3088347860 @default.
• W4386475288 cites W3094282396 @default.
• W4386475288 cites W3099659667 @default.
• W4386475288 cites W3120624571 @default.
• W4386475288 cites W3125542198 @default.
• W4386475288 cites W3161055157 @default.
• W4386475288 cites W3172720573 @default.
• W4386475288 cites W3178883367 @default.
• W4386475288 cites W3193929840 @default.
• W4386475288 cites W3208687975 @default.
• W4386475288 cites W3212512279 @default.
• W4386475288 cites W4214949685 @default.
• W4386475288 cites W4223910234 @default.
• W4386475288 cites W4226529970 @default.
• W4386475288 cites W4309700933 @default.
• W4386475288 cites W4319865391 @default.
• W4386475288 cites W4385737444 @default.
• W4386475288 doi "https://doi.org/10.1063/5.0135382" @default.
• W4386475288 hasPublicationYear "2023" @default.
• W4386475288 type Work @default.
• W4386475288 citedByCount "0" @default.
• W4386475288 crossrefType "journal-article" @default.
• W4386475288 hasAuthorship W4386475288A5019215236 @default.
• W4386475288 hasAuthorship W4386475288A5042083426 @default.
• W4386475288 hasBestOaLocation W43864752881 @default.
• W4386475288 hasConcept C108225325 @default.
• W4386475288 hasConcept C114221277 @default.
• W4386475288 hasConcept C121332964 @default.
• W4386475288 hasConcept C121864883 @default.
• W4386475288 hasConcept C147597530 @default.
• W4386475288 hasConcept C152365726 @default.
• W4386475288 hasConcept C154945302 @default.
• W4386475288 hasConcept C171250308 @default.
• W4386475288 hasConcept C185592680 @default.
• W4386475288 hasConcept C18762648 @default.
• W4386475288 hasConcept C192562407 @default.
• W4386475288 hasConcept C2524010 @default.
• W4386475288 hasConcept C26873012 @default.
• W4386475288 hasConcept C28719098 @default.
• W4386475288 hasConcept C33923547 @default.
• W4386475288 hasConcept C41008148 @default.
• W4386475288 hasConcept C49040817 @default.
• W4386475288 hasConcept C50644808 @default.
• W4386475288 hasConcept C7070889 @default.
• W4386475288 hasConcept C97355855 @default.
• W4386475288 hasConceptScore W4386475288C108225325 @default.
• W4386475288 hasConceptScore W4386475288C114221277 @default.
• W4386475288 hasConceptScore W4386475288C121332964 @default.
• W4386475288 hasConceptScore W4386475288C121864883 @default.
• W4386475288 hasConceptScore W4386475288C147597530 @default.
• W4386475288 hasConceptScore W4386475288C152365726 @default.
• W4386475288 hasConceptScore W4386475288C154945302 @default.
• W4386475288 hasConceptScore W4386475288C171250308 @default.
• W4386475288 hasConceptScore W4386475288C185592680 @default.
• W4386475288 hasConceptScore W4386475288C18762648 @default.
• W4386475288 hasConceptScore W4386475288C192562407 @default.
• W4386475288 hasConceptScore W4386475288C2524010 @default.
• W4386475288 hasConceptScore W4386475288C26873012 @default.
• W4386475288 hasConceptScore W4386475288C28719098 @default.
• W4386475288 hasConceptScore W4386475288C33923547 @default.
• W4386475288 hasConceptScore W4386475288C41008148 @default.
• W4386475288 hasConceptScore W4386475288C49040817 @default.
• W4386475288 hasConceptScore W4386475288C50644808 @default.

• next