% 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”.

@ARTICLE{Hilgers:1041738,
      author       = {Hilgers, Robin and Wortmann, Daniel and Blügel, Stefan},
      title        = {{M}achine {L}earning-based estimation and explainable
                      artificial intelligence-supported interpretation of the
                      critical temperature from magnetic ab initio {H}eusler
                      alloys data},
      journal      = {Physical review materials},
      volume       = {9},
      number       = {4},
      issn         = {2475-9953},
      address      = {College Park, MD},
      publisher    = {APS},
      reportid     = {FZJ-2025-02414},
      pages        = {044412},
      year         = {2025},
      abstract     = {Machine 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 (𝑇c) 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 𝑇c 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 𝑇c. 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.},
      cin          = {PGI-1},
      ddc          = {530},
      cid          = {I:(DE-Juel1)PGI-1-20110106},
      pnm          = {5211 - Topological Matter (POF4-521)},
      pid          = {G:(DE-HGF)POF4-5211},
      typ          = {PUB:(DE-HGF)16},
      UT           = {WOS:001495003900001},
      doi          = {10.1103/PhysRevMaterials.9.044412},
      url          = {https://juser.fz-juelich.de/record/1041738},
}