Premium
Simulating Diffusion Properties of Solid‐State Electrolytes via a Neural Network Potential: Performance and Training Scheme
Author(s) -
Marcolongo Aris,
Binninger Tobias,
Zipoli Federico,
Laino Teodoro
Publication year - 2020
Publication title -
chemsystemschem
Language(s) - English
Resource type - Journals
ISSN - 2570-4206
DOI - 10.1002/syst.201900031
Subject(s) - computation , diffusion , computer science , electrolyte , artificial neural network , protocol (science) , training (meteorology) , solid state , key (lock) , component (thermodynamics) , artificial intelligence , thermodynamics , algorithm , chemistry , physics , electrode , medicine , alternative medicine , computer security , pathology , meteorology
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 Li 10 GeP 2 S 12 , Li 7 La 3 Zr 2 O 12 and Na 3 Zr 2 Si 2 PO 12 . 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.