Export citation

Export citation

Choose format for download:

Download Citation

    Size and temperature transferability of direct and local deep neural networks for atomic forces

    Natalia Kuritz1, Goren Gordon2, and Amir Natan1,3,*

    • 1Department of Physical Electronics, Tel Aviv University, Tel Aviv 69978, Israel
    • 2Department of Industrial Engineering, Tel Aviv University, Tel Aviv 69978, Israel
    • 3The Sackler Center for Computational Molecular and Materials Science, Tel Aviv University, Tel Aviv 69978, Israel

    • *amirnatan@post.tau.ac.il

    Phys. Rev. B 98, 094109 – Published 20 September, 2018

    DOI: https://doi.org/10.1103/PhysRevB.98.094109

    Abstract

    A direct and local deep learning (DL) model for atomic forces is presented. We demonstrate the model performance in bulk aluminum, sodium, and silicon and show that its errors are comparable to those found in state-of-the-art machine learning and DL models. We then analyze the model's performance as a function of the number of neighbors included and show that one can ascertain physical attributes of the system from the analysis of the deep learning model's behavior. Finally, we test the size scaling performance of the model and the transferability between different temperatures and show that our model performs well in both scaling to larger systems and high- to low-temperature predictability.

    Physics Subject Headings (PhySH)

    Authorization Required

    We need you to provide your credentials before accessing this content.

    Supplemental Material (Subscription Required)

    References (Subscription Required)

    Outline

    Information

    Sign In to Your Journals Account

    Filter

    Filter

    Article Lookup

    Enter a citation