First-principles modeling of electronic transport properties and the prospects of machine learning the electronic structure of matter at scale

In this talk, I will present two lines of our research. In the first part, I will discuss the application of time-dependent density functional theory (TDDFT) in modeling observables induced in matter under extreme conditions, such as the electron loss function relevant to scattering experiments with X-ray free electron lasers [1] and the electrical conductivity in metals [2]. In the second part, I will highlight our recent progress in leveraging Artificial Intelligence (AI) to enhance the efficiency of electronic structure calculations [3]. Specifically, I will focus on our efforts to accelerate Kohn-Sham density functional theory calculations at finite temperatures by integrating deep neural networks into the Materials Learning Algorithms framework [4,5]. Our results demonstrate significant improvements in calculation speed for metals up to their melting point. Additionally, our implementation of automated machine learning has led to substantial savings in computational resources for identifying optimal neural network architectures, paving the way for large-scale AI-driven investigations [6]. Lastly, I will present our latest breakthrough, showcasing the capability of neural-network-driven electronic structure calculations for systems containing over 100,000 atoms [7].

[1] Z. Moldabekov, T. Dornheim, A. Cangi, Sci. Rep. 12, 1093 (2022).
[2] K. Ramakrishna, M. Lokamani, A. Baczewski, J. Vorberger, A. Cangi, Phys. Rev. B 107, 115131 (2023).
[3] L. Fiedler, K. Shah, M. Bussmann, A. Cangi, Phys. Rev. Materials 6, 040301, (2022).
[4] A. Cangi, J. A. Ellis, L. Fiedler, D. Kotik, N. A. Modine, V. Oles, G. A. Popoola, S. Rajamanickam, S. Schmerler, J. A. Stephens, A. P. Thompson, MALA, https://doi.org/10.5281/zenodo.5557254 (2021).
[5] J. A. Ellis, L. Fiedler, G. A. Popoola, N. A. Modine, J. A. Stephens, A. P. Thompson, A. Cangi, Phys. Rev. B 104, 035120 (2021).
[6] L. Fiedler, N. Hoffmann, P. Mohammed, G. A. Popoola, T. Yovell, V. Oles, J. A. Ellis, S. Rajamanickam, A. Cangi, Mach. Learn.: Sci. Technol. 3, 045008 (2022).
[7] L. Fiedler, N. A. Modine, S. Schmerler, D. J. Vogel, G. A. Popoola, A. P. Thompson, S. Rajamanickam, A. Cangi, Npj Comput. Mater., accepted (2023).