Machine-Learning X-Ray Absorption Spectra to Quantitative Accuracy
Source: http://link.aps.org/doi/10.1103/PhysRevLett.124.156401
Author(s): Matthew R. Carbone, Mehmet Topsakal, Deyu Lu, and Shinjae Yoo
Simulations of excited state properties, such as spectral functions, are often computationally expensive and therefore not suitable for high-throughput modeling. As a proof of principle, we demonstrate that graph-based neural networks can be used to predict the x-ray absorption near-edge structure s…
[Phys. Rev. Lett. 124, 156401] Published Thu Apr 16, 2020
