Saved in:
Bibliographic Details
Main Authors: Yin, Yue, He, Jiangshan, Li, Runze, Qiu, Yunze, Wang, Dingsheng, Li, Jun, Xiao, Hai
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.19445
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917094621184000
author Yin, Yue
He, Jiangshan
Li, Runze
Qiu, Yunze
Wang, Dingsheng
Li, Jun
Xiao, Hai
author_facet Yin, Yue
He, Jiangshan
Li, Runze
Qiu, Yunze
Wang, Dingsheng
Li, Jun
Xiao, Hai
contents Dual-atom catalysts supported on nitrogen-doped graphene (DAC/NG) are emerging as a family of promising catalysts that can overcome intrinsic limitations of single-atom catalysts. However, comprehensive assessment of their structural stability is prohibitively demanding due to a vast local configurational space. Here we introduce LOCAL, a locality-based framework that combines graph convolutional networks with active learning to efficiently predict DAC/NG stability by leveraging chemically intuitive locality quantified by crystal orbital Hamilton population analysis. We demonstrate the effectiveness of LOCAL over a comprehensive dataset of 611,648 DAC/NG structures, achieving a test mean absolute error of 0.15~eV while invoking density functional theory calculations for only 16,704 structures (2.7% of the dataset). Thus, LOCAL enables efficient and accurate construction of phase diagrams for DAC/NG across diverse compositions reciprocally validated with experimentally synthesized configurations for representative systems. Our framework composes an essential methodology for accelerating the discovery and optimization of high-performance complex catalysts.
format Preprint
id arxiv_https___arxiv_org_abs_2503_19445
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LOCAL: A Locality-based Active Learning Framework for Predicting the Stability of Dual-Atom Catalysts
Yin, Yue
He, Jiangshan
Li, Runze
Qiu, Yunze
Wang, Dingsheng
Li, Jun
Xiao, Hai
Chemical Physics
Dual-atom catalysts supported on nitrogen-doped graphene (DAC/NG) are emerging as a family of promising catalysts that can overcome intrinsic limitations of single-atom catalysts. However, comprehensive assessment of their structural stability is prohibitively demanding due to a vast local configurational space. Here we introduce LOCAL, a locality-based framework that combines graph convolutional networks with active learning to efficiently predict DAC/NG stability by leveraging chemically intuitive locality quantified by crystal orbital Hamilton population analysis. We demonstrate the effectiveness of LOCAL over a comprehensive dataset of 611,648 DAC/NG structures, achieving a test mean absolute error of 0.15~eV while invoking density functional theory calculations for only 16,704 structures (2.7% of the dataset). Thus, LOCAL enables efficient and accurate construction of phase diagrams for DAC/NG across diverse compositions reciprocally validated with experimentally synthesized configurations for representative systems. Our framework composes an essential methodology for accelerating the discovery and optimization of high-performance complex catalysts.
title LOCAL: A Locality-based Active Learning Framework for Predicting the Stability of Dual-Atom Catalysts
topic Chemical Physics
url https://arxiv.org/abs/2503.19445