001046210 001__ 1046210
001046210 005__ 20260106202633.0
001046210 0247_ $$2doi$$a10.1039/D5TA05090A
001046210 0247_ $$2ISSN$$a2050-7488
001046210 0247_ $$2ISSN$$a2050-7496
001046210 0247_ $$2datacite_doi$$a10.34734/FZJ-2025-03746
001046210 037__ $$aFZJ-2025-03746
001046210 082__ $$a530
001046210 1001_ $$0P:(DE-HGF)0$$aHarper, Angela F$$b0$$eFirst author
001046210 245__ $$aPerformance metrics for tensorial learning: prediction of Li4Ti5O12 nuclear magnetic resonance observables at experimental accuracy
001046210 260__ $$aLondon ˜[u.a.]œ$$bRSC$$c2025
001046210 3367_ $$2DRIVER$$aarticle
001046210 3367_ $$2DataCite$$aOutput Types/Journal article
001046210 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1767698819_16804
001046210 3367_ $$2BibTeX$$aARTICLE
001046210 3367_ $$2ORCID$$aJOURNAL_ARTICLE
001046210 3367_ $$00$$2EndNote$$aJournal Article
001046210 520__ $$aPredicting observable quantities from first principles calculations is the next frontier within the field of machine learning (ML) for materials modelling. While ML models have shown success for the prediction of scalar properties such as energetics or band gaps, models and performance metrics for the learning of higher order tensor-based observables have not yet been formalized. ML models for experimental observables, including tensorial quantities, are essential for exploiting the full potential of the paradigm shift enabled by machine learned interatomic potentials by mapping the structure–property relationship in an equally efficient way. In this work, we establish performance metrics for accurately predicting the electric field gradient tensor (EFG) underlying nuclear magnetic resonance (NMR) spectroscopy. We further demonstrate the superiority of a tensorial learning approach that fully encodes the corresponding symmetries over a separate scalar learning of individual tensor-derived observables. To this end we establish an extensive EFG dataset representative of real experimental applications and develop performance metrics for model evaluation which directly focus on the targeted NMR observables. Finally, by leveraging the computational efficiency of the ML method employed, we predict quadrupolar observables for 1512 atom models of Li4Ti5O12, a high performance Li-ion battery anode material, which is capable of accurately distinguishing local atomic environments via their NMR observables. This workflow and dataset sets the standard for the next generation of tensorial based learning for spectroscopic observables.
001046210 536__ $$0G:(DE-HGF)POF4-1223$$a1223 - Batteries in Application (POF4-122)$$cPOF4-122$$fPOF IV$$x0
001046210 588__ $$aDataset connected to CrossRef, Journals: juser.fz-juelich.de
001046210 7001_ $$0P:(DE-Juel1)192562$$aKöcher, Simone Swantje$$b1$$eCorresponding author$$ufzj
001046210 7001_ $$0P:(DE-HGF)0$$aReuter, Karsten$$b2
001046210 7001_ $$0P:(DE-Juel1)184961$$aScheurer, Christoph$$b3$$ufzj
001046210 773__ $$0PERI:(DE-600)2702232-8$$a10.1039/D5TA05090A$$gp. 10.1039.D5TA05090A$$p35389–35399$$tJournal of materials chemistry / A$$v13$$x2050-7488$$y2025
001046210 8564_ $$uhttps://juser.fz-juelich.de/record/1046210/files/d5ta05090a.pdf$$yOpenAccess
001046210 8767_ $$d2025-10-29$$eHybrid-OA$$jPublish and Read
001046210 909CO $$ooai:juser.fz-juelich.de:1046210$$popenaire$$popen_access$$pdriver$$pVDB$$popenCost$$pdnbdelivery
001046210 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)192562$$aForschungszentrum Jülich$$b1$$kFZJ
001046210 9101_ $$0I:(DE-HGF)0$$6P:(DE-Juel1)192562$$a Fritz Haber Institut der Max Planck Gesellschaft Berlin$$b1
001046210 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)184961$$aForschungszentrum Jülich$$b3$$kFZJ
001046210 9101_ $$0I:(DE-HGF)0$$6P:(DE-Juel1)184961$$a Fritz Haber Institut der Max Planck Gesellschaft Berlin$$b3
001046210 9131_ $$0G:(DE-HGF)POF4-122$$1G:(DE-HGF)POF4-120$$2G:(DE-HGF)POF4-100$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF4-1223$$aDE-HGF$$bForschungsbereich Energie$$lMaterialien und Technologien für die Energiewende (MTET)$$vElektrochemische Energiespeicherung$$x0
001046210 9141_ $$y2025
001046210 915pc $$0PC:(DE-HGF)0000$$2APC$$aAPC keys set
001046210 915pc $$0PC:(DE-HGF)0001$$2APC$$aLocal Funding
001046210 915pc $$0PC:(DE-HGF)0002$$2APC$$aDFG OA Publikationskosten
001046210 915pc $$0PC:(DE-HGF)0110$$2APC$$aTIB: Royal Society of Chemistry 2021
001046210 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2024-12-05
001046210 915__ $$0StatID:(DE-HGF)0160$$2StatID$$aDBCoverage$$bEssential Science Indicators$$d2024-12-05
001046210 915__ $$0StatID:(DE-HGF)1160$$2StatID$$aDBCoverage$$bCurrent Contents - Engineering, Computing and Technology$$d2024-12-05
001046210 915__ $$0StatID:(DE-HGF)1150$$2StatID$$aDBCoverage$$bCurrent Contents - Physical, Chemical and Earth Sciences$$d2024-12-05
001046210 915__ $$0StatID:(DE-HGF)0113$$2StatID$$aWoS$$bScience Citation Index Expanded$$d2024-12-05
001046210 915__ $$0StatID:(DE-HGF)9910$$2StatID$$aIF >= 10$$bJ MATER CHEM A : 2022$$d2024-12-05
001046210 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2024-12-05
001046210 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
001046210 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bJ MATER CHEM A : 2022$$d2024-12-05
001046210 915__ $$0StatID:(DE-HGF)0430$$2StatID$$aNational-Konsortium$$d2024-12-05$$wger
001046210 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2024-12-05
001046210 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2024-12-05
001046210 920__ $$lyes
001046210 9201_ $$0I:(DE-Juel1)IET-1-20110218$$kIET-1$$lGrundlagen der Elektrochemie$$x0
001046210 980__ $$ajournal
001046210 980__ $$aVDB
001046210 980__ $$aUNRESTRICTED
001046210 980__ $$aI:(DE-Juel1)IET-1-20110218
001046210 980__ $$aAPC
001046210 9801_ $$aAPC
001046210 9801_ $$aFullTexts