% IMPORTANT: The following is UTF-8 encoded.  This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.

@INPROCEEDINGS{Hilgers:1005347,
      author       = {Hilgers, Robin and Wortmann, Daniel and Blügel, Stefan and
                      Kovacik, Roman},
      title        = {{C}urie {T}emperature {P}rediction {M}odels of {M}agnetic
                      {H}eusler {A}lloys {U}sing {M}achine {L}earning {M}ethods
                      {B}ased on {F}irst-{P}rinciples {D}ata {F}rom {A}b-initio
                      {KKR}-{GF} {C}alculations},
      reportid     = {FZJ-2023-01453},
      year         = {2023},
      note         = {APS was licensed to archive the talk and use the
                      presentation as VOD.},
      abstract     = {Ordered and disordered magnetic Heusler alloys are an
                      important class of materials in science and applications.
                      Using Curie temperatures (Tc) of Heusler alloys calculated
                      by the Korringa-Kohn-Rostoker Green function (KKR-GF) method
                      and a subsequent Monte Carlo (MC) approach [1], we trained
                      and evaluated several machine learning models to predict Tc
                      based on atomic, magnetic, and structural properties. We
                      studied multiple descriptor selection methods to determine
                      the most meaningful physical quantities in the given phase
                      space.We compared the performance of regression and
                      classification models in order to predict the range of the
                      Tc of given compounds without performing the MC
                      calculations. Since the MC calculation takes about as many
                      computational resources as the ab-initio calculation, it
                      would be favorable to replace either step with a less
                      computational intensive method as e.g. machine learning. We
                      discuss the necessity to generate the magnetic ab-initio
                      results in order to make a quantitative prediction of the
                      Tc.This work can be seen as a small-scale case study in
                      which lightweight machine learning algorithms can add value
                      to existing ab-initio data and eventually replace costly
                      computational steps in layered calculation workflows in the
                      future.[1] R. Kovacik et al. (2022),
                      [10.24435/MATERIALSCLOUD:WW-PV]*This work was performed as
                      part of the Helmholtz School for Data Science in Life, Earth
                      and Energy (HDS-LEE) and received funding from the Helmholtz
                      Association of German Research Centres.},
      month         = {Mar},
      date          = {2023-03-06},
      organization  = {APS March Meeting, Las Vegas, Nevada
                       (USA), 6 Mar 2023 - 10 Mar 2023},
      subtyp        = {After Call},
      cin          = {IAS-1},
      cid          = {I:(DE-Juel1)IAS-1-20090406},
      pnm          = {5211 - Topological Matter (POF4-521) / 632 - Materials –
                      Quantum, Complex and Functional Materials (POF4-632) / HDS
                      LEE - Helmholtz School for Data Science in Life, Earth and
                      Energy (HDS LEE) (HDS-LEE-20190612)},
      pid          = {G:(DE-HGF)POF4-5211 / G:(DE-HGF)POF4-632 /
                      G:(DE-Juel1)HDS-LEE-20190612},
      typ          = {PUB:(DE-HGF)6},
      url          = {https://juser.fz-juelich.de/record/1005347},
}