001018604 001__ 1018604
001018604 005__ 20231128201907.0
001018604 0247_ $$2datacite_doi$$a10.34734/FZJ-2023-04922
001018604 037__ $$aFZJ-2023-04922
001018604 041__ $$aEnglish
001018604 1001_ $$0P:(DE-Juel1)179506$$aHilgers, Robin$$b0$$eCorresponding author$$ufzj
001018604 245__ $$aMachine Learning-based estimation and explainable artificial intelligence-supported interpretation of the critical temperature from magnetic ab initio Heusler alloys data
001018604 260__ $$c2023
001018604 3367_ $$0PUB:(DE-HGF)25$$2PUB:(DE-HGF)$$aPreprint$$bpreprint$$mpreprint$$s1701181826_4646
001018604 3367_ $$2ORCID$$aWORKING_PAPER
001018604 3367_ $$028$$2EndNote$$aElectronic Article
001018604 3367_ $$2DRIVER$$apreprint
001018604 3367_ $$2BibTeX$$aARTICLE
001018604 3367_ $$2DataCite$$aOutput Types/Working Paper
001018604 500__ $$aNon-exclusive perpetual license
001018604 520__ $$aMachine Learning (ML) has impacted numerous areas of materials science, most prominently improving molecular simulations, where force fields were trained on previously relaxed structures. One natural next step is to predict material properties beyond structure. In this work, we investigate the applicability and explainability of ML methods in the use case of estimating the critical temperature for magnetic Heusler alloys calculated using ab initio methods determined materials-specific magnetic interactions and a subsequent Monte Carlo (MC) approach. We compare the performance of regression and classification models to predict the range of the critical temperature of given compounds without performing the MC calculations. Since the MC calculation requires computational resources in the same order of magnitude as the density-functional theory (DFT) calculation, it would be advantageous to replace either step with a less computationally intensive method such as ML. We discuss the necessity to generate the magnetic ab initio results to make a quantitative prediction of the critical temperature. We used state-of-the-art explainable artificial intelligence (XAI) methods to extract physical relations and deepen our understanding of patterns learned by our models from the examined data.
001018604 536__ $$0G:(DE-HGF)POF4-5211$$a5211 - Topological Matter (POF4-521)$$cPOF4-521$$fPOF IV$$x0
001018604 536__ $$0G:(DE-Juel1)HDS-LEE-20190612$$aHDS LEE - Helmholtz School for Data Science in Life, Earth and Energy (HDS LEE) (HDS-LEE-20190612)$$cHDS-LEE-20190612$$x1
001018604 65027 $$0V:(DE-MLZ)SciArea-120$$2V:(DE-HGF)$$aCondensed Matter Physics$$x0
001018604 65027 $$0V:(DE-MLZ)SciArea-170$$2V:(DE-HGF)$$aMagnetism$$x1
001018604 65027 $$0V:(DE-MLZ)SciArea-180$$2V:(DE-HGF)$$aMaterials Science$$x2
001018604 65017 $$0V:(DE-MLZ)GC-1604-2016$$2V:(DE-HGF)$$aMagnetic Materials$$x0
001018604 7001_ $$0P:(DE-Juel1)131042$$aWortmann, Daniel$$b1$$ufzj
001018604 7001_ $$0P:(DE-Juel1)130548$$aBlügel, Stefan$$b2$$ufzj
001018604 773__ $$y2023
001018604 8564_ $$uhttps://arxiv.org/abs/2311.15423
001018604 8564_ $$uhttps://juser.fz-juelich.de/record/1018604/files/Paper.pdf$$yOpenAccess
001018604 8564_ $$uhttps://juser.fz-juelich.de/record/1018604/files/Paper.gif?subformat=icon$$xicon$$yOpenAccess
001018604 8564_ $$uhttps://juser.fz-juelich.de/record/1018604/files/Paper.jpg?subformat=icon-1440$$xicon-1440$$yOpenAccess
001018604 8564_ $$uhttps://juser.fz-juelich.de/record/1018604/files/Paper.jpg?subformat=icon-180$$xicon-180$$yOpenAccess
001018604 8564_ $$uhttps://juser.fz-juelich.de/record/1018604/files/Paper.jpg?subformat=icon-640$$xicon-640$$yOpenAccess
001018604 909CO $$ooai:juser.fz-juelich.de:1018604$$popenaire$$popen_access$$pVDB$$pdriver$$pdnbdelivery
001018604 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)179506$$aForschungszentrum Jülich$$b0$$kFZJ
001018604 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)131042$$aForschungszentrum Jülich$$b1$$kFZJ
001018604 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)130548$$aForschungszentrum Jülich$$b2$$kFZJ
001018604 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$$x0
001018604 9141_ $$y2023
001018604 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
001018604 920__ $$lyes
001018604 9201_ $$0I:(DE-Juel1)IAS-1-20090406$$kIAS-1$$lQuanten-Theorie der Materialien$$x0
001018604 9201_ $$0I:(DE-Juel1)PGI-1-20110106$$kPGI-1$$lQuanten-Theorie der Materialien$$x1
001018604 980__ $$apreprint
001018604 980__ $$aVDB
001018604 980__ $$aUNRESTRICTED
001018604 980__ $$aI:(DE-Juel1)IAS-1-20090406
001018604 980__ $$aI:(DE-Juel1)PGI-1-20110106
001018604 9801_ $$aFullTexts