Physicsnpj Computational Materials
Completing density functional theory by machine learning hidden messages from molecules
R. Nagai, R. Akashi, et al.
This groundbreaking research by Ryo Nagai, Ryosuke Akashi, and Osamu Sugino reveals a novel method for constructing the exchange-correlation energy functional in Kohn-Sham DFT using machine learning. Their approach surprisingly offers high accuracy across numerous molecules, on par with traditional functionals, enhancing the capabilities of DFT.
Related Publications
Explore these studies to deepen your understanding
Adjacent work that informs or extends this paper's methodology and findings.
Engineering and Technology
Generative design of stable semiconductor materials using deep learning and density functional theory
E. M. D. Siriwardane, Y. Zhao, et al.
Medicine and Health
Functional and structural reorganization in brain tumors: a machine learning approach using desynchronized functional oscillations
J. Falcó-roget, A. Cacciola, et al.
Materials Science
Structural changes during glass formation extracted by computational homology with machine learning
A. Hirata, T. Wada, et al.
Chemistry
Predicting glass structure by physics-informed machine learning
M. L. Bødker, M. Bauchy, et al.
