Publications Repository - Helmholtz-Zentrum Dresden-Rossendorf

3 Publications

Transferability of DFT surrogate models: Temperature and system size

Fiedler, L.; Cangi, A.


While Density Functional Theory (DFT) is the most common tool for the investigation of materials under extreme conditions, its scaling behavior with respect to both system size and temperature makes large scale simulations challenging. Yet, progress in this regard would enable accurate modeling of planetary interiors or radiation damage in fusion reactor walls.
One possible route to alleviate these scaling problems is through the use of surrogate models, i.e., machine-learning models. These are trained on DFT data and are able to reproduce DFT observables at comparable accuracy, but negligible computational cost.
In order to actually be useful for such investigations, existing models need to be able to work across length scales and be transferable within desired temperature ranges. Here we show how models based on local mappings of electronic structure information [1], implemented in the Materials Learning Algorithms (MALA) package [2] can be trained on small number of atoms and select temperatures, yet perform accurately when used to make predictions for extended systems within a range of temperatures.

Keywords: Density Functional Theory; Machine Learning

  • Poster
    Strongly Coupled Coulomb Systems 2022, 24.-29.07.2022, Görlitz, Deutschland
  • Lecture (Conference)
    Multiscale Modeling of Matter under Extreme Conditions, 11.-16.09.2022, Görlitz, Deutschland
  • Poster
    Big data analytical methods for complex systems, 06.10.2022, Wrocław, Polen


Years: 2023 2022 2021 2020 2019 2018 2017 2016 2015