arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2501.11297cond-mat.mtrl-sci
收藏

基于机器学习的键序势用于探索碳的构型空间

Machine-Learned Bond-Order Potential for Exploring the Configuration Space of Carbon

The University of Tokyo(东京大学);Shinshu University(信州大学)

Ikuma Kohata, Kaoru Hisama, Keigo Otsuka, Shigeo Maruyama

AI总结:

本研究提出了一种基于键序势的机器学习相互原子势,用于高效探索碳的构型空间,并通过多种任务验证其在材料发现中的应用潜力。

摘要:

构建具有最少参数数量的可转移机器学习相互原子势对于其广泛应用至关重要。在这里,我们提出了一种具有键序势功能形式的机器学习相互原子势,以全面探索碳的构型空间。基于物理的设计使该势能在潜在能面的广泛范围内以少量参数实现稳健且准确的描述。我们通过在各种任务上的验证展示了该势能的多功能性,包括声子色散计算、团簇的全局结构搜索、相图计算以及局部最小结构的焓-体积映射。我们预计该势能将有助于发现新型碳材料。

英文摘要:

Construction of transferable machine-learning interatomic potentials with a minimal number of parameters is important for their general applicability. Here, we present a machine-learning interatomic potential with the functional form of the bond-order potential for comprehensive exploration over the configuration space of carbon. The physics-based design of this potential enables robust and accurate description over a wide range of the potential energy surface with a small number of parameters. We demonstrate the versatility of this potential through validations across various tasks, including phonon dispersion calculations, global structure searches for clusters, phase diagram calculations, and enthalpy-volume mappings of local minima structures. We expect that this potential can contribute to the discovery of novel carbon materials.

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。

↑