Simulating diffusion properties of solid-state electrolytes via a neural network potential: Performance and training scheme
- Cognitive Computing and Computational Sciences Department, IBM Research – Zurich, Saumerstrasse 4, CH-8803 Ruschlikon, Switzerland
DOI10.24435/materialscloud:2019.0067/v1 (version v1, submitted on 25 October 2019)
How to cite this entry
Aris Marcolongo, Tobias Binninger, Federico Zipoli, Teodoro Laino, Simulating diffusion properties of solid-state electrolytes via a neural network potential: Performance and training scheme, Materials Cloud Archive (2019), doi: 10.24435/materialscloud:2019.0067/v1.
Description
The recently published DeePMD model, based on a deep neural network architecture, brings the hope of solving the time-scale issue which often prevents the application of first principle molecular dynamics to physical systems. With this contribution we assess the performance of the DeePMD potential on a real-life application and model diffusion of ions in solid-state electrolytes. We consider as test cases the well known Li10GeP2S12, Li7La3Zr2O12 and Na3Zr2Si2PO12. We develop and test a training protocol suitable for the computation of diffusion coefficients, which is one of the key properties to be optimized for battery applications, and we find good agreement with previous computations. Our results show that the DeePMD model may be a successful component of a framework to identify novel solid-state electrolytes.
Materials Cloud sections using this data
No Explore or Discover sections associated with this archive entry.
Files
| File name | Size | Description |
|---|---|---|
|
README.txt
MD5MD5: f7f261b0382ffbc121641e2da55f1df3
|
2.3 KiB | |
|
ANN_diffusion.tar.gz
MD5MD5: 6f96927bdbb9a8b986f8b6591f44ad7d
|
45.7 MiB | Configurations used for training of the different materials and data to reproduce the plots. |
License
External references
Keywords
Version history
25 October 2019 [This version]