Regensburg 2022 – scientific programme
Parts | Days | Selection | Search | Updates | Downloads | Help
O: Fachverband Oberflächenphysik
O 83: Frontiers of Electronic Structure Theory: Focus on Artificial Intelligence Applied to Real Materials 4
O 83.5: Talk
Friday, September 9, 2022, 11:30–11:45, S054
Active learning and element-embedding approach in neural networks for infinite-layer versus perovskite oxides — Armin Sahinovic and •Benjamin Geisler — Fakultät für Physik, Universität Duisburg-Essen
The observation of superconductivity in NdNiO2 films on SrTiO3(001) by Li et al. [1] has sparked considerable interest in the materials class of infinite-layer oxides. Here we combine first-principles simulations and active learning of neural networks to explore formation energies of oxygen vacancy layers, lattice parameters, and their statistical correlations in infinite-layer versus perovskite oxides across the periodic table, and place the superconducting nickelate and cuprate families in a comprehensive context. Neural networks accurately predict these observables, which act as a fingerprint of the complex reduction reaction, using only a fraction of the data for training. Unbiased by external knowledge, element embedding autonomously identifies chemical similarities between the individual elements in line with human knowledge. Active learning renders the training highly efficient, based on the physical concepts of entropy and information, and provides systematic accuracy control [2]. We recently applied this concept also to nitrides and fluorides [3]. This exemplifies how AI may assist on the quantum scale in discovering novel materials with optimized properties.
[1] D. Li et al., Nature 572, 624 (2019)
[2] A. Sahinovic and B. Geisler, PR Research 3, L042022 (2021)
[3] A. Sahinovic and B. Geisler, J. Phys.: Condens. Matter 34, 214003 (2022)