arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2409.07947cond-mat.mtrl-sci
收藏

用于高保真机器学习原子间势的数据高效多保真训练

Data-efficient multi-fidelity training for high-fidelity machine learning interatomic potentials

Jaesun Kim, Jisu Kim, Jaehoon Kim, Jiho Lee, Yutack Park, Youngho Kang, Seungwu Han

AI总结:

该研究提出基于等变图神经网络的多保真MLIP训练框架,仅需少量高保真数据即可准确学习高保真势能面,性能优于迁移学习与Δ-学习,可扩展至耦合簇级别保真度,为构建高精度通用或定制原子间势提供新路径。

摘要:

机器学习原子间势(MLIPs)用于从从头算中估算势能面(PES),能以更低的计算成本提供接近量子水平的精度。然而,构建高保真数据库的高昂成本阻碍了MLIPs在要求高化学精度的体系中的应用。我们利用等变图神经网络,提出了一种可同时在多保真数据库上训练的MLIP框架。该方法仅需极少的高保真数据,就能准确学习高保真势能面(PES)。我们在Li$_6$PS$_5$Cl和In$_x$Ga$_{1-x}$N体系上测试了该框架。计算结果表明,高保真元梯度广义近似(meta-GGA)数据库未覆盖的几何空间与成分空间,可通过低保真GGA数据有效推断,从而提升了精度和分子动力学稳定性。我们还开发了一种通用MLIP,它同时利用来自Materials Project的GGA和meta-GGA数据,显著提升了MLIP在高准确度任务上的性能,例如预测一般晶体的凸包以上能量。此外,我们证明了当前的多保真学习比迁移学习或Δ-学习更有效,且还可应用于学习更高保真度的结果,最高可达耦合簇级别。我们认为,该方法通过有效扩充高保真数据集,有望用于构建高精度的定制化或通用MLIP。

英文摘要:

Machine learning interatomic potentials (MLIPs) are used to estimate potential energy surfaces (PES) from ab initio calculations, providing near quantum-level accuracy with reduced computational costs. However, the high cost of assembling high-fidelity databases hampers the application of MLIPs to systems that require high chemical accuracy. Utilizing an equivariant graph neural network, we present an MLIP framework that trains on multi-fidelity databases simultaneously. This approach enables the accurate learning of high-fidelity PES with minimal high-fidelity data. We test this framework on the Li$_6$PS$_5$Cl and In$_x$Ga$_{1-x}$N systems. The computational results indicate that geometric and compositional spaces not covered by the high-fidelity meta-gradient generalized approximation (meta-GGA) database can be effectively inferred from low-fidelity GGA data, thus enhancing accuracy and molecular dynamics stability. We also develop a general-purpose MLIP that utilizes both GGA and meta-GGA data from the Materials Project, significantly enhancing MLIP performance for high-accuracy tasks such as predicting energies above hull for crystals in general. Furthermore, we demonstrate that the present multi-fidelity learning is more effective than transfer learning or $Δ$-learning an d that it can also be applied to learn higher-fidelity up to the coupled-cluster level. We believe this methodology holds promise for creating highly accurate bespoke or universal MLIPs by effectively expanding the high-fidelity dataset.

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。

↑