Transferable machine learning model for multi-target nanoscale simulations in hydrogen-carbon system from crystal to amorphous

Abstract Carbon materials especially with hydrogenation have attracted wide attention for their novel physical and chemical properties and broad application prospects. A systematic theoretical simulation method accurately describing atomic interactions for hydrogen-carbon systems is crucial for the...

Full description

Saved in:
Bibliographic Details
Main Authors: Weiqi Chen, Zhiyue Xu, Kang Wang, Lei Gao, Aisheng Song, Tianbao Ma
Format: Article
Language:English
Published: Nature Portfolio 2025-05-01
Series:npj Computational Materials
Online Access:https://doi.org/10.1038/s41524-025-01629-y
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850203931719761920
author Weiqi Chen
Zhiyue Xu
Kang Wang
Lei Gao
Aisheng Song
Tianbao Ma
author_facet Weiqi Chen
Zhiyue Xu
Kang Wang
Lei Gao
Aisheng Song
Tianbao Ma
author_sort Weiqi Chen
collection DOAJ
description Abstract Carbon materials especially with hydrogenation have attracted wide attention for their novel physical and chemical properties and broad application prospects. A systematic theoretical simulation method accurately describing atomic interactions for hydrogen-carbon systems is crucial for the design of carbon-based materials and their industrial applications. Multiphases of hydrogenated carbon materials, from crystal to amorphous, with covalent network and diverse chemical reactions bring huge difficulties to construct a general interatomic potential under various conditions. Here, we demonstrate a transferable active machine learning scheme with separated training of sub-feature spaces and target-oriented finetuning, and construct a general-purpose pre-trained machine learning potential (MLP) for hydrogen-carbon systems. The pre-trained MLP is further efficiently transferred to three target spaces of deposition, friction and fracture with scale reliability. This work provides a robust tool for the theoretical research of hydrogen-carbon systems and a general scheme for developing transferable MLPs in multiphase systems across compositional and conditional complexity.
format Article
id doaj-art-bf3482f57cf040dcbfd5bf694936c9a2
institution OA Journals
issn 2057-3960
language English
publishDate 2025-05-01
publisher Nature Portfolio
record_format Article
series npj Computational Materials
spelling doaj-art-bf3482f57cf040dcbfd5bf694936c9a22025-08-20T02:11:23ZengNature Portfolionpj Computational Materials2057-39602025-05-0111111410.1038/s41524-025-01629-yTransferable machine learning model for multi-target nanoscale simulations in hydrogen-carbon system from crystal to amorphousWeiqi Chen0Zhiyue Xu1Kang Wang2Lei Gao3Aisheng Song4Tianbao Ma5State Key Laboratory of Tribology in Advanced Equipment, Tsinghua UniversityState Key Laboratory of Tribology in Advanced Equipment, Tsinghua UniversityState Key Laboratory of Tribology in Advanced Equipment, Tsinghua UniversityBeijing Advanced Innovation Center for Materials Genome Engineering, University of Science and Technology BeijingState Key Laboratory of Tribology in Advanced Equipment, Tsinghua UniversityState Key Laboratory of Tribology in Advanced Equipment, Tsinghua UniversityAbstract Carbon materials especially with hydrogenation have attracted wide attention for their novel physical and chemical properties and broad application prospects. A systematic theoretical simulation method accurately describing atomic interactions for hydrogen-carbon systems is crucial for the design of carbon-based materials and their industrial applications. Multiphases of hydrogenated carbon materials, from crystal to amorphous, with covalent network and diverse chemical reactions bring huge difficulties to construct a general interatomic potential under various conditions. Here, we demonstrate a transferable active machine learning scheme with separated training of sub-feature spaces and target-oriented finetuning, and construct a general-purpose pre-trained machine learning potential (MLP) for hydrogen-carbon systems. The pre-trained MLP is further efficiently transferred to three target spaces of deposition, friction and fracture with scale reliability. This work provides a robust tool for the theoretical research of hydrogen-carbon systems and a general scheme for developing transferable MLPs in multiphase systems across compositional and conditional complexity.https://doi.org/10.1038/s41524-025-01629-y
spellingShingle Weiqi Chen
Zhiyue Xu
Kang Wang
Lei Gao
Aisheng Song
Tianbao Ma
Transferable machine learning model for multi-target nanoscale simulations in hydrogen-carbon system from crystal to amorphous
npj Computational Materials
title Transferable machine learning model for multi-target nanoscale simulations in hydrogen-carbon system from crystal to amorphous
title_full Transferable machine learning model for multi-target nanoscale simulations in hydrogen-carbon system from crystal to amorphous
title_fullStr Transferable machine learning model for multi-target nanoscale simulations in hydrogen-carbon system from crystal to amorphous
title_full_unstemmed Transferable machine learning model for multi-target nanoscale simulations in hydrogen-carbon system from crystal to amorphous
title_short Transferable machine learning model for multi-target nanoscale simulations in hydrogen-carbon system from crystal to amorphous
title_sort transferable machine learning model for multi target nanoscale simulations in hydrogen carbon system from crystal to amorphous
url https://doi.org/10.1038/s41524-025-01629-y
work_keys_str_mv AT weiqichen transferablemachinelearningmodelformultitargetnanoscalesimulationsinhydrogencarbonsystemfromcrystaltoamorphous
AT zhiyuexu transferablemachinelearningmodelformultitargetnanoscalesimulationsinhydrogencarbonsystemfromcrystaltoamorphous
AT kangwang transferablemachinelearningmodelformultitargetnanoscalesimulationsinhydrogencarbonsystemfromcrystaltoamorphous
AT leigao transferablemachinelearningmodelformultitargetnanoscalesimulationsinhydrogencarbonsystemfromcrystaltoamorphous
AT aishengsong transferablemachinelearningmodelformultitargetnanoscalesimulationsinhydrogencarbonsystemfromcrystaltoamorphous
AT tianbaoma transferablemachinelearningmodelformultitargetnanoscalesimulationsinhydrogencarbonsystemfromcrystaltoamorphous