XFEL SASE pulses can enhance time-dependent observables

EM Liane, M Simmermacher, PM Weber… - Journal of Physics B …, 2024 - iopscience.iop.org
X-ray free electron lasers (XFELs) have emerged as powerful sources of short and intense x-
ray pulses. We propose a simple and robust procedure which takes advantage of the …

Towards efficient and accurate input for data-driven materials science from large-scale all-electron density functional theory (DFT) simulations

S Kokott, A Marek, F Merz, P Karpov… - … and Simulation in …, 2024 - pure.mpg.de
Science is and always has been based on data, but the terms' data-centric'and the'4th
paradigm'of materials research indicate a radical change in how information is retrieved …

EdgeAI: Machine learning via direct attached accelerator for streaming data processing at high shot rate x-ray free-electron lasers

M Kraus, N Layad, Z Liu, R Coffee - Frontiers in Physics, 2022 - frontiersin.org
We present a case for low batch-size inference with the potential for adaptive training of a
lean encoder model. We do so in the context of a paradigmatic example of machine learning …

[PDF][PDF] 3.5: Synthetic Hamilton Matrices for Deep Learning

SK Giri, U Saalmann, JM Rost - Roadmap on Data-Centric Materials Science - arxiv.org
Training of Deep Learning (DL) models requires a large amount of data in the first place and
the data set must be sufficiently diverse for the network to be transferable such that it …