A pre-trained deep potential model for sulfide solid electrolytes with broad coverage and high accuracy

Abstract Solid electrolytes with fast ion transport are crucial for solid state lithium metal batteries. Chemical doping has been the most effective strategy for improving ion condictiviy, and atomistic simulation with machine-learning potentials helps optimize doping by predicting ion conductivity...

Full description

Saved in:
Bibliographic Details
Main Authors: Ruoyu Wang, Mingyu Guo, Yuxiang Gao, Xiaoxu Wang, Yuzhi Zhang, Bin Deng, Mengchao Shi, Linfeng Zhang, Zhicheng Zhong
Format: Article
Language:English
Published: Nature Portfolio 2025-08-01
Series:npj Computational Materials
Online Access:https://doi.org/10.1038/s41524-025-01764-6
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849226050980020224
author Ruoyu Wang
Mingyu Guo
Yuxiang Gao
Xiaoxu Wang
Yuzhi Zhang
Bin Deng
Mengchao Shi
Linfeng Zhang
Zhicheng Zhong
author_facet Ruoyu Wang
Mingyu Guo
Yuxiang Gao
Xiaoxu Wang
Yuzhi Zhang
Bin Deng
Mengchao Shi
Linfeng Zhang
Zhicheng Zhong
author_sort Ruoyu Wang
collection DOAJ
description Abstract Solid electrolytes with fast ion transport are crucial for solid state lithium metal batteries. Chemical doping has been the most effective strategy for improving ion condictiviy, and atomistic simulation with machine-learning potentials helps optimize doping by predicting ion conductivity for various composition. Yet most existing machine-learning models are trained on narrow chemistry, requiring retraining for each new system, which wastes transferable knowledge and incurs significant cost. Here, we propose a pre-trained deep potential model purpose-built for sulfide solid electrolytes with attention mechanism, known as DPA-SSE. The training set includes 15 elements and consists of both equilibrium and extensive out-of-equilibrium configurations. DPA-SSE achieves a high energy resolution of less than 2 meV/atom for dynamical trajectories up to 1150 K, and reproduces experimental ion conductivity with remarkable accuracy. DPA-SSE generalizes well to complex electrolytes with mixes of cation and anion atoms, and enables highly efficient dynamical simulation via model distillation. DPA-SSE also serves as a platform for continuous learning and can be fine-tuned with minimal downstream data. These results demonstrate the possibility of a new pathway for the AI-driven development of solid electrolytes with exceptional performance.
format Article
id doaj-art-347e285fc59f4f45963da8d3851ebd78
institution Kabale University
issn 2057-3960
language English
publishDate 2025-08-01
publisher Nature Portfolio
record_format Article
series npj Computational Materials
spelling doaj-art-347e285fc59f4f45963da8d3851ebd782025-08-24T11:40:13ZengNature Portfolionpj Computational Materials2057-39602025-08-0111111010.1038/s41524-025-01764-6A pre-trained deep potential model for sulfide solid electrolytes with broad coverage and high accuracyRuoyu Wang0Mingyu Guo1Yuxiang Gao2Xiaoxu Wang3Yuzhi Zhang4Bin Deng5Mengchao Shi6Linfeng Zhang7Zhicheng Zhong8School of Artificial Intelligence and Data Science, University of Science and Technology of ChinaDP TechnologySchool of Artificial Intelligence and Data Science, University of Science and Technology of ChinaDP TechnologyDP TechnologyDP TechnologySuzhou LabDP TechnologySchool of Artificial Intelligence and Data Science, University of Science and Technology of ChinaAbstract Solid electrolytes with fast ion transport are crucial for solid state lithium metal batteries. Chemical doping has been the most effective strategy for improving ion condictiviy, and atomistic simulation with machine-learning potentials helps optimize doping by predicting ion conductivity for various composition. Yet most existing machine-learning models are trained on narrow chemistry, requiring retraining for each new system, which wastes transferable knowledge and incurs significant cost. Here, we propose a pre-trained deep potential model purpose-built for sulfide solid electrolytes with attention mechanism, known as DPA-SSE. The training set includes 15 elements and consists of both equilibrium and extensive out-of-equilibrium configurations. DPA-SSE achieves a high energy resolution of less than 2 meV/atom for dynamical trajectories up to 1150 K, and reproduces experimental ion conductivity with remarkable accuracy. DPA-SSE generalizes well to complex electrolytes with mixes of cation and anion atoms, and enables highly efficient dynamical simulation via model distillation. DPA-SSE also serves as a platform for continuous learning and can be fine-tuned with minimal downstream data. These results demonstrate the possibility of a new pathway for the AI-driven development of solid electrolytes with exceptional performance.https://doi.org/10.1038/s41524-025-01764-6
spellingShingle Ruoyu Wang
Mingyu Guo
Yuxiang Gao
Xiaoxu Wang
Yuzhi Zhang
Bin Deng
Mengchao Shi
Linfeng Zhang
Zhicheng Zhong
A pre-trained deep potential model for sulfide solid electrolytes with broad coverage and high accuracy
npj Computational Materials
title A pre-trained deep potential model for sulfide solid electrolytes with broad coverage and high accuracy
title_full A pre-trained deep potential model for sulfide solid electrolytes with broad coverage and high accuracy
title_fullStr A pre-trained deep potential model for sulfide solid electrolytes with broad coverage and high accuracy
title_full_unstemmed A pre-trained deep potential model for sulfide solid electrolytes with broad coverage and high accuracy
title_short A pre-trained deep potential model for sulfide solid electrolytes with broad coverage and high accuracy
title_sort pre trained deep potential model for sulfide solid electrolytes with broad coverage and high accuracy
url https://doi.org/10.1038/s41524-025-01764-6
work_keys_str_mv AT ruoyuwang apretraineddeeppotentialmodelforsulfidesolidelectrolyteswithbroadcoverageandhighaccuracy
AT mingyuguo apretraineddeeppotentialmodelforsulfidesolidelectrolyteswithbroadcoverageandhighaccuracy
AT yuxianggao apretraineddeeppotentialmodelforsulfidesolidelectrolyteswithbroadcoverageandhighaccuracy
AT xiaoxuwang apretraineddeeppotentialmodelforsulfidesolidelectrolyteswithbroadcoverageandhighaccuracy
AT yuzhizhang apretraineddeeppotentialmodelforsulfidesolidelectrolyteswithbroadcoverageandhighaccuracy
AT bindeng apretraineddeeppotentialmodelforsulfidesolidelectrolyteswithbroadcoverageandhighaccuracy
AT mengchaoshi apretraineddeeppotentialmodelforsulfidesolidelectrolyteswithbroadcoverageandhighaccuracy
AT linfengzhang apretraineddeeppotentialmodelforsulfidesolidelectrolyteswithbroadcoverageandhighaccuracy
AT zhichengzhong apretraineddeeppotentialmodelforsulfidesolidelectrolyteswithbroadcoverageandhighaccuracy
AT ruoyuwang pretraineddeeppotentialmodelforsulfidesolidelectrolyteswithbroadcoverageandhighaccuracy
AT mingyuguo pretraineddeeppotentialmodelforsulfidesolidelectrolyteswithbroadcoverageandhighaccuracy
AT yuxianggao pretraineddeeppotentialmodelforsulfidesolidelectrolyteswithbroadcoverageandhighaccuracy
AT xiaoxuwang pretraineddeeppotentialmodelforsulfidesolidelectrolyteswithbroadcoverageandhighaccuracy
AT yuzhizhang pretraineddeeppotentialmodelforsulfidesolidelectrolyteswithbroadcoverageandhighaccuracy
AT bindeng pretraineddeeppotentialmodelforsulfidesolidelectrolyteswithbroadcoverageandhighaccuracy
AT mengchaoshi pretraineddeeppotentialmodelforsulfidesolidelectrolyteswithbroadcoverageandhighaccuracy
AT linfengzhang pretraineddeeppotentialmodelforsulfidesolidelectrolyteswithbroadcoverageandhighaccuracy
AT zhichengzhong pretraineddeeppotentialmodelforsulfidesolidelectrolyteswithbroadcoverageandhighaccuracy