Machine learning sparse tight-binding parameters for defects
Loading...
Access rights
openAccess
URL
Journal Title
Journal ISSN
Volume Title
A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä
This publication is imported from Aalto University research portal.
View publication in the Research portal (opens in new window)
View/Open full text file from the Research portal (opens in new window)
Other link related to publication (opens in new window)
View publication in the Research portal (opens in new window)
View/Open full text file from the Research portal (opens in new window)
Other link related to publication (opens in new window)
Date
2022-05-20
Major/Subject
Mcode
Degree programme
Language
en
Pages
11
1-11
1-11
Series
npj Computational Materials, Volume 8, issue 1
Abstract
We employ machine learning to derive tight-binding parametrizations for the electronic structure of defects. We test several machine learning methods that map the atomic and electronic structure of a defect onto a sparse tight-binding parameterization. Since Multi-layer perceptrons (i.e., feed-forward neural networks) perform best we adopt them for our further investigations. We demonstrate the accuracy of our parameterizations for a range of important electronic structure properties such as band structure, local density of states, transport and level spacing simulations for two common defects in single layer graphene. Our machine learning approach achieves results comparable to maximally localized Wannier functions (i.e., DFT accuracy) without prior knowledge about the electronic structure of the defects while also allowing for a reduced interaction range which substantially reduces calculation time. It is general and can be applied to a wide range of other materials, enabling accurate large-scale simulations of material properties in the presence of different defects.Description
Funding Information: We acknowledge support from the FWF DACH project I3827-N36, COST action CA18234, the Academy of Finland through projects 316601 and 334532 and the doctoral colleges Solids4Fun W1243-N16 funded by the FWF and TU-D funded by TU Wien. Christoph Schattauer acknowledges support as a recipient of a DOC fellowship of the Austrian Academy of Sciences. Numerical calculations were performed on the Vienna Scientific Clusters VSC3 and VSC4. Funding Information: iPALM imaging was done in collaboration with the Advanced Imaging Center at Janelia Research Campus, a facility jointly supported by the Gordon and Betty Moore Foundation and the Howard Hughes Medical Institute. ChIA-Drop analysis was done by Minji Kim and Michał Denkiewicz. Molecular graphics and analyses performed with UCSF Chimera, developed by the Resource for Biocomputing, Visualization, and Informatics at the University of California, San Francisco, with support from NIH P41-GM103311. This work was carried out within „Three-dimensional Human Genome structure at the population scale: computational algorithm and experimental validation for lymphoblastoid cell lines of selected families from 1000 Genomes Project” project carried out within the TEAM programme of the Foundation for Polish Science co-financed by the European Union under the European Regional Development Fund, co-supported by Polish National Science Centre (2019/35/O/ST6/02484 and 2020/37/B/NZ2/03757) and the grant 1U54DK107967-01 “Nucleome Positioning System for Spatiotemporal Genome Organization and Regulation” within 4D Nucleome NIH program. The work was co-supported by the European Commission as Horizon 2020 Marie Skłodowska-Curie ITN Enhpathy grant “Molecular Basis of Human enhanceropathies”. DP was co-funded by Warsaw University of Technology within the Excellence Initiative: Research University (IDUB) programme; and POB Cybersecurity and data analysis of Warsaw University of Technology within the Excellence Initiative: Research University (IDUB) programme. Computations were performed thanks to the Laboratory of Bioinformatics and Computational Genomics, Faculty of Mathematics and Information Science, Warsaw University of Technology using Artificial Intelligence HPC platform financed by Polish Ministry of Science and Higher Education (decision no. 7054/IA/SP/2020 of 2020-08-28). Publisher Copyright: © 2022, The Author(s).
Keywords
Other note
Citation
Schattauer, C, Todorović, M, Ghosh, K, Rinke, P & Libisch, F 2022, ' Machine learning sparse tight-binding parameters for defects ', npj Computational Materials, vol. 8, no. 1, 116, pp. 1-11 . https://doi.org/10.1038/s41524-022-00791-x