Matches in SemOpenAlex for { <https://semopenalex.org/work/W3104968270> ?p ?o ?g. }
- W3104968270 endingPage "084005" @default.
- W3104968270 startingPage "084005" @default.
- W3104968270 abstract "We present a novel deep learning (DL) approach to produce highly accurate predictions of macroscopic physical properties of solid solution binary alloys and magnetic systems. The major idea is to make use of the correlations between different physical properties in alloy systems to improve the prediction accuracy of neural network (NN) models. We use multitasking NN models to simultaneously predict the total energy, charge density and magnetic moment. These physical properties mutually serve as constraints during the training of the multitasking NN, resulting in more reliable DL models because multiple physics properties are correctly learned by a single model. Two binary alloys, copper-gold (CuAu) and iron-platinum (FePt), were studied. Our results show that once the multitasking NN's are trained, they can estimate the material properties for a specific configuration hundreds of times faster than first-principles density functional theory calculations while retaining comparable accuracy. We used a simple measure based on the root-mean-squared errors (RMSE) to quantify the quality of the NN models, and found that the inclusion of charge density and magnetic moment as physical constraints leads to more stable models that exhibit improved accuracy and reduced uncertainty for the energy predictions." @default.
- W3104968270 created "2020-11-23" @default.
- W3104968270 creator A5003874504 @default.
- W3104968270 creator A5008691625 @default.
- W3104968270 creator A5019108731 @default.
- W3104968270 creator A5051882926 @default.
- W3104968270 creator A5060737716 @default.
- W3104968270 creator A5066258147 @default.
- W3104968270 date "2020-12-14" @default.
- W3104968270 modified "2023-09-27" @default.
- W3104968270 title "Fast and stable deep-learning predictions of material properties for solid solution alloys**" @default.
- W3104968270 cites W1772299910 @default.
- W3104968270 cites W1992976489 @default.
- W3104968270 cites W2006326929 @default.
- W3104968270 cites W2030976617 @default.
- W3104968270 cites W2031975877 @default.
- W3104968270 cites W2035912401 @default.
- W3104968270 cites W2046001409 @default.
- W3104968270 cites W2046505730 @default.
- W3104968270 cites W2047165001 @default.
- W3104968270 cites W2105192472 @default.
- W3104968270 cites W2230728100 @default.
- W3104968270 cites W2258120943 @default.
- W3104968270 cites W2486933018 @default.
- W3104968270 cites W2567135055 @default.
- W3104968270 cites W2782434877 @default.
- W3104968270 cites W2807356398 @default.
- W3104968270 cites W2900986313 @default.
- W3104968270 cites W2917193084 @default.
- W3104968270 cites W2921533983 @default.
- W3104968270 cites W2946640364 @default.
- W3104968270 cites W3006359473 @default.
- W3104968270 cites W3023479823 @default.
- W3104968270 cites W3048497553 @default.
- W3104968270 cites W3099950071 @default.
- W3104968270 cites W3102845444 @default.
- W3104968270 cites W3106482122 @default.
- W3104968270 cites W3209042722 @default.
- W3104968270 cites W836966646 @default.
- W3104968270 doi "https://doi.org/10.1088/1361-648x/abcb10" @default.
- W3104968270 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/33202401" @default.
- W3104968270 hasPublicationYear "2020" @default.
- W3104968270 type Work @default.
- W3104968270 sameAs 3104968270 @default.
- W3104968270 citedByCount "6" @default.
- W3104968270 countsByYear W31049682702022 @default.
- W3104968270 countsByYear W31049682702023 @default.
- W3104968270 crossrefType "journal-article" @default.
- W3104968270 hasAuthorship W3104968270A5003874504 @default.
- W3104968270 hasAuthorship W3104968270A5008691625 @default.
- W3104968270 hasAuthorship W3104968270A5019108731 @default.
- W3104968270 hasAuthorship W3104968270A5051882926 @default.
- W3104968270 hasAuthorship W3104968270A5060737716 @default.
- W3104968270 hasAuthorship W3104968270A5066258147 @default.
- W3104968270 hasBestOaLocation W31049682702 @default.
- W3104968270 hasConcept C105795698 @default.
- W3104968270 hasConcept C107418235 @default.
- W3104968270 hasConcept C121332964 @default.
- W3104968270 hasConcept C121864883 @default.
- W3104968270 hasConcept C124101348 @default.
- W3104968270 hasConcept C139945424 @default.
- W3104968270 hasConcept C154945302 @default.
- W3104968270 hasConcept C15744967 @default.
- W3104968270 hasConcept C179254644 @default.
- W3104968270 hasConcept C180747234 @default.
- W3104968270 hasConcept C192562407 @default.
- W3104968270 hasConcept C26873012 @default.
- W3104968270 hasConcept C2780009758 @default.
- W3104968270 hasConcept C33923547 @default.
- W3104968270 hasConcept C41008148 @default.
- W3104968270 hasConcept C48372109 @default.
- W3104968270 hasConcept C50644808 @default.
- W3104968270 hasConcept C54553102 @default.
- W3104968270 hasConcept C62520636 @default.
- W3104968270 hasConcept C94375191 @default.
- W3104968270 hasConceptScore W3104968270C105795698 @default.
- W3104968270 hasConceptScore W3104968270C107418235 @default.
- W3104968270 hasConceptScore W3104968270C121332964 @default.
- W3104968270 hasConceptScore W3104968270C121864883 @default.
- W3104968270 hasConceptScore W3104968270C124101348 @default.
- W3104968270 hasConceptScore W3104968270C139945424 @default.
- W3104968270 hasConceptScore W3104968270C154945302 @default.
- W3104968270 hasConceptScore W3104968270C15744967 @default.
- W3104968270 hasConceptScore W3104968270C179254644 @default.
- W3104968270 hasConceptScore W3104968270C180747234 @default.
- W3104968270 hasConceptScore W3104968270C192562407 @default.
- W3104968270 hasConceptScore W3104968270C26873012 @default.
- W3104968270 hasConceptScore W3104968270C2780009758 @default.
- W3104968270 hasConceptScore W3104968270C33923547 @default.
- W3104968270 hasConceptScore W3104968270C41008148 @default.
- W3104968270 hasConceptScore W3104968270C48372109 @default.
- W3104968270 hasConceptScore W3104968270C50644808 @default.
- W3104968270 hasConceptScore W3104968270C54553102 @default.
- W3104968270 hasConceptScore W3104968270C62520636 @default.
- W3104968270 hasConceptScore W3104968270C94375191 @default.
- W3104968270 hasIssue "8" @default.
- W3104968270 hasLocation W31049682701 @default.
- W3104968270 hasLocation W31049682702 @default.