Salvato in:
Dettagli Bibliografici
Autori principali: Wang, Yinan, Wang, Xiaoyang, Wang, Zhenyu, Wu, Jing, Lv, Jian, Wang, Han
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2509.10293
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911151411953664
author Wang, Yinan
Wang, Xiaoyang
Wang, Zhenyu
Wu, Jing
Lv, Jian
Wang, Han
author_facet Wang, Yinan
Wang, Xiaoyang
Wang, Zhenyu
Wu, Jing
Lv, Jian
Wang, Han
contents High-pressure crystal structure prediction (CSP) underpins advances in condensed matter physics, planetary science, and materials discovery. Yet, most large atomistic models are trained on near-ambient, equilibrium data, leading to degraded stress accuracy at tens to hundreds of gigapascals and sparse coverage of pressure-stabilized stoichiometries and dense coordination motifs. Here, we introduce OpenCSP, a machine learning framework for CSP tasks spanning ambient to high-pressure conditions. This framework comprises an open-source pressure-resolved dataset alongside a suite of publicly available atomistic models that are jointly optimized for accuracy in energy, force, and stress predictions. The dataset is constructed via randomized high-pressure sampling and iteratively refined through an uncertainty-guided concurrent learning strategy, which enriches underrepresented compression regimes while suppressing redundant DFT labeling. Despite employing a training corpus one to two orders of magnitude smaller than those of leading large models, OpenCSP achieves comparable or superior performance in high-pressure enthalpy ranking and stability prediction. Across benchmark CSP tasks spanning a wide pressure window, our models match or surpass MACE-MPA-0, MatterSim v1 5M, and GRACE-2L-OAM, with the largest gains observed at elevated pressures. These results demonstrate that targeted, pressure-aware data acquisition coupled with scalable architectures enables data-efficient, high-fidelity CSP, paving the way for autonomous materials discovery under ambient and extreme conditions.
format Preprint
id arxiv_https___arxiv_org_abs_2509_10293
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle OpenCSP: A Deep Learning Framework for Crystal Structure Prediction from Ambient to High Pressure
Wang, Yinan
Wang, Xiaoyang
Wang, Zhenyu
Wu, Jing
Lv, Jian
Wang, Han
Materials Science
High-pressure crystal structure prediction (CSP) underpins advances in condensed matter physics, planetary science, and materials discovery. Yet, most large atomistic models are trained on near-ambient, equilibrium data, leading to degraded stress accuracy at tens to hundreds of gigapascals and sparse coverage of pressure-stabilized stoichiometries and dense coordination motifs. Here, we introduce OpenCSP, a machine learning framework for CSP tasks spanning ambient to high-pressure conditions. This framework comprises an open-source pressure-resolved dataset alongside a suite of publicly available atomistic models that are jointly optimized for accuracy in energy, force, and stress predictions. The dataset is constructed via randomized high-pressure sampling and iteratively refined through an uncertainty-guided concurrent learning strategy, which enriches underrepresented compression regimes while suppressing redundant DFT labeling. Despite employing a training corpus one to two orders of magnitude smaller than those of leading large models, OpenCSP achieves comparable or superior performance in high-pressure enthalpy ranking and stability prediction. Across benchmark CSP tasks spanning a wide pressure window, our models match or surpass MACE-MPA-0, MatterSim v1 5M, and GRACE-2L-OAM, with the largest gains observed at elevated pressures. These results demonstrate that targeted, pressure-aware data acquisition coupled with scalable architectures enables data-efficient, high-fidelity CSP, paving the way for autonomous materials discovery under ambient and extreme conditions.
title OpenCSP: A Deep Learning Framework for Crystal Structure Prediction from Ambient to High Pressure
topic Materials Science
url https://arxiv.org/abs/2509.10293