Snapshot of a deep learning simulation of more than 10,000 beryllium atoms (IMAGE)

Helmholtz-Zentrum Dresden-Rossendorf

Snapshot of a deep learning simulation of more than 10,000 beryllium atoms

Caption

Snapshot of a deep learning simulation of more than 10,000 beryllium atoms. The distribution of electrons in this material is visualized as red (delocalized electrons) and blue (electrons located close to the atomic nuclei) point clouds. This simulation is not feasible using conventional DFT calculation. Thanks to MALA, it was accomplished within about 5 minutes employing just 150 central processing units. Graphical filters have been used to increase the intelligibility of the simulation. The white areas at the fringes are also due to the filters. The scheme in the background hints at how deep learning works.

Credit

HZDR / CASUS

Usage Restrictions

Credit must be given to the creator. Only noncommercial uses of the work are permitted. Adaptations must be shared under the same terms.

License

CC BY-NC-SA

Disclaimer: AAAS and EurekAlert! are not responsible for the accuracy of news releases posted to EurekAlert! by contributing institutions or for the use of any information through the EurekAlert system.