001020052 001__ 1020052
001020052 005__ 20250401102817.0
001020052 0247_ $$2datacite_doi$$a10.34734/FZJ-2023-05853
001020052 037__ $$aFZJ-2023-05853
001020052 041__ $$aEnglish
001020052 1001_ $$0P:(DE-Juel1)186072$$aWasmer, Johannes$$b0$$eCorresponding author$$ufzj
001020052 1112_ $$aVirtual Materials Design 2021$$conline$$d2021-07-20 - 2021-07-21$$gVMD21$$wGermany
001020052 245__ $$aComparison of structural representations for machine learning-enhanced DFT of impurity embeddings
001020052 260__ $$c2022
001020052 3367_ $$033$$2EndNote$$aConference Paper
001020052 3367_ $$2BibTeX$$aINPROCEEDINGS
001020052 3367_ $$2DRIVER$$aconferenceObject
001020052 3367_ $$2ORCID$$aCONFERENCE_POSTER
001020052 3367_ $$2DataCite$$aOutput Types/Conference Poster
001020052 3367_ $$0PUB:(DE-HGF)24$$2PUB:(DE-HGF)$$aPoster$$bposter$$mposter$$s1704197607_26653$$xAfter Call
001020052 502__ $$cRWTH Aachen University
001020052 520__ $$aThe acceleration or even replacement of ab initio methods for atomistic systems with surrogate models based on machine learning has gained traction in recent years [1]. This development stands on two pillars: The first one is the fast growth of materials databases, thanks in part to high-throughput calculation (HTC) infrastructures such as AiiDA [2]. The second one is advances in method development in atomistic machine learning, where finding the best representation of an atomic system as input for model training has been identified as a crucial step to success. Structural representations rely, like the Schrödinger equation, only on the atom positions and their chemical identity within a system [3], and are thus most suitable for this task.Here we investigate the possibility to accelerate the density functional theory (DFT) code juKKR [4] with machine learning starting potentials. This code has been used for instance to perform HTC on impurity embeddings into topological insulators [5]. We use a combinatorial approach to generate 7000 impurity embeddings from most elements of the periodic table into elemental crystals with the help of AiiDA. We generate their fingerprints using structural descriptors implemented in the DScribe package [6], such as smooth overlap of atomic positions. To benchmark their representational power for these embeddings, we present the results of a simple classification experiment.We acknowledge support by the Joint Lab Virtual Materials Design (JL-VMD) and thank for computing time granted by the JARA Vergabegremium and provided on the JARA Partition part of the supercomputer CLAIX at RWTH Aachen University. This work was funded by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) under Germany's Excellence Strategy – Cluster of Excellence Matter and Light for Quantum Computing (ML4Q) EXC 2004/1 – 390534769, and by AIDAS2 – AI, Data Analytics and Scalable Simulation – a virtual lab between CEA, France and FZJ, Germany.
001020052 536__ $$0G:(DE-HGF)POF4-5211$$a5211 - Topological Matter (POF4-521)$$cPOF4-521$$fPOF IV$$x0
001020052 536__ $$0G:(GEPRIS)390534769$$aDFG project 390534769 - EXC 2004: Materie und Licht für Quanteninformation (ML4Q) (390534769)$$c390534769$$x1
001020052 536__ $$0G:(BMBF)390534769$$aEXC 2004:  Matter and Light for Quantum Computing (ML4Q) (390534769)$$c390534769$$x2
001020052 536__ $$0G:(DE-Juel-1)aidas_20200731$$aAIDAS - Joint Virtual Laboratory for AI, Data Analytics and Scalable Simulation (aidas_20200731)$$caidas_20200731$$x3
001020052 7001_ $$0P:(DE-Juel1)157882$$aRüssmann, Philipp$$b1$$ufzj
001020052 7001_ $$0P:(DE-Juel1)130548$$aBlügel, Stefan$$b2$$ufzj
001020052 8564_ $$uhttps://www.cecam.org/workshop-details/1093
001020052 8564_ $$uhttps://juser.fz-juelich.de/record/1020052/files/Poster%20source.svg$$yRestricted
001020052 8564_ $$uhttps://juser.fz-juelich.de/record/1020052/files/Poster.pdf$$yOpenAccess
001020052 8564_ $$uhttps://juser.fz-juelich.de/record/1020052/files/Poster.gif?subformat=icon$$xicon$$yOpenAccess
001020052 8564_ $$uhttps://juser.fz-juelich.de/record/1020052/files/Poster.jpg?subformat=icon-1440$$xicon-1440$$yOpenAccess
001020052 8564_ $$uhttps://juser.fz-juelich.de/record/1020052/files/Poster.jpg?subformat=icon-180$$xicon-180$$yOpenAccess
001020052 8564_ $$uhttps://juser.fz-juelich.de/record/1020052/files/Poster.jpg?subformat=icon-640$$xicon-640$$yOpenAccess
001020052 909CO $$ooai:juser.fz-juelich.de:1020052$$pdriver$$pVDB$$popen_access$$popenaire
001020052 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)186072$$aForschungszentrum Jülich$$b0$$kFZJ
001020052 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)157882$$aForschungszentrum Jülich$$b1$$kFZJ
001020052 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)130548$$aForschungszentrum Jülich$$b2$$kFZJ
001020052 9131_ $$0G:(DE-HGF)POF4-521$$1G:(DE-HGF)POF4-520$$2G:(DE-HGF)POF4-500$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF4-5211$$aDE-HGF$$bKey Technologies$$lNatural, Artificial and Cognitive Information Processing$$vQuantum Materials$$x0
001020052 9141_ $$y2023
001020052 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
001020052 920__ $$lyes
001020052 9201_ $$0I:(DE-Juel1)IAS-1-20090406$$kIAS-1$$lQuanten-Theorie der Materialien$$x0
001020052 9201_ $$0I:(DE-Juel1)PGI-1-20110106$$kPGI-1$$lQuanten-Theorie der Materialien$$x1
001020052 980__ $$aposter
001020052 980__ $$aVDB
001020052 980__ $$aUNRESTRICTED
001020052 980__ $$aI:(DE-Juel1)IAS-1-20090406
001020052 980__ $$aI:(DE-Juel1)PGI-1-20110106
001020052 9801_ $$aFullTexts