arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2412.02191cond-mat.mtrl-sci
收藏

通过机器学习原子间势探索氧化铝的能量景观

Exploring the energy landscape of aluminas through machine learning interatomic potential

Lei Zhang, Wenhao Luo, Renxi Liu, Mohan Chen, Zhongbo Yan, Kun Cao

AI总结:

本文基于神经进化势方法构建了氧化铝的通用机器学习原子间势,通过迭代训练和最远点采样实现势能面穷尽采样,成功给出含过渡态氧化铝和α-Al₂O₃的相图并外推至极端条件,同时评估了γ-Al₂O₃结构模型。

摘要:

氧化铝(alumina, Al$_2$O$_3$)以多种结构存在,并具有广泛的工业应用。虽然α-Al$_2$O$_3$的晶体结构已得到充分确认,但过渡态氧化铝的结构仍存在很大争议。在本研究中,我们提出了一种适用于氧化铝的通用机器学习原子间势(MLIP),采用神经进化势(NEP)方法进行训练。数据集通过迭代训练和最远点采样构建,确保生成最具代表性的构型,以对势能面进行穷尽采样。该势的准确性和普适性通过在包括高温和高压在内的广泛条件下的模拟得到验证。基于NEP,我们给出了一个同时包含过渡态氧化铝和α-Al$_2$O$_3$的相图。我们还成功地将氧化铝的相图外推至极端条件(温度和压力范围分别为[0, 4000] K和[0, 200] GPa),同时在描述较温和条件下的性质时保持高精度。此外,结合我们开发的结构搜索工作流,NEP对现有γ-Al$_2$O$_3$结构模型进行了评估。本工作开发的NEP能够在更大尺度和更长时间尺度上对各种氧化铝进行高精度动态模拟,同时也为过渡态氧化铝结构的研究提供了新的见解。

英文摘要:

Aluminum oxide (alumina, Al$_2$O$_3$) exists in various structures and has broad industrial applications. While the crystal structure of $α$-Al$_2$O$_3$ is well-established, those of transitional aluminas remain highly debated. In this study, we propose a universal machine learning interatomic potential (MLIP) for aluminas, trained using the neuroevolution potential (NEP) approach. The dataset is constructed through iterative training and farthest point sampling, ensuring the generation of the most representative configurations for an exhaustive sampling of the potential energy surface. The accuracy and generality of the potential are validated through simulations under a wide range of conditions, including high temperatures and pressures. A phase diagram is presented that includes both transitional aluminas and $α$-Al$_2$O$_3$ based on the NEP. We also successfully extrapolate the phase diagram of aluminas under extreme conditions ([0, 4000] K and [0, 200] GPa ranges of temperature and pressure, respectively), while maintaining high accuracy in describing their properties under more moderate conditions. Furthermore, combined with our developed structure search workflow, the NEP provides an evaluation of existing $γ$-Al$_2$O$_3$ structure models. The NEP developed in this work enables highly accurate dynamic simulations of various aluminas on larger scales and longer timescales, while also offering new insights into the study of transitional aluminas structures.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑