arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.19592cond-mat.mtrl-sci
收藏

通过物理指导预训练提升机器学习互原子势的可靠性

Improving Reliability of Machine Learned Interatomic Potentials With Physics-Informed Pretraining

College of Computing, Georgia Institute of Technology(佐治亚理工学院计算学院);School of Computational Science and Engineering, Georgia Institute of Technology(佐治亚理工学院计算科学与工程学院)

Qianyu Zheng, Victor Fung

AI总结:

通过物理指导预训练提升机器学习互原子势的可靠性,提高预测准确性和MD稳定性。

摘要:

机器学习互原子势(MLIPs)已发展为分子动力学(MD)模拟的强大工具,因其具有竞争力的精度和计算效率。然而,MLIPs在遇到显著偏离其训练数据分布的配置时,往往表现出不物理的行为,导致模拟不稳定和不可靠的动力学,从而限制了MLIPs在材料模拟中的可靠性。我们提出了一种物理指导的预训练策略,利用简单的物理势能来提高基于图的MLIPs在MD模拟中的鲁棒性和稳定性。我们通过部署一个预训练-微调流程来演示这一方法,其中MLIPs最初在带有嵌入原子模型势能标记的数据上进行预训练,随后在量子力学基态数据上进行微调。通过在三个不同的材料系统(磷、硅和材料项目的一部分)和三种代表性的MLIP架构(CGCNN、M3GNet和TorchMD-NET)上评估,我们发现这种物理指导的预训练方法在预测准确性和MD稳定性方面都优于基线方法。

英文摘要:

Machine learned interatomic potentials (MLIPs) have emerged as powerful tools for molecular dynamics (MD) simulations with their competitive accuracy and computational efficiency. However, MLIPs are often observed to exhibit un-physical behavior when encountering configurations which deviate significantly from their training data distribution, leading to simulation instabilities and unreliable dynamics, thus limiting the reliability of MLIPs for materials simulations. We present a physics-informed pretraining strategy that leverages simple physical potentials which can improve the robustness and stability of graph-based MLIPs for MD simulations. We demonstrate this approach by deploying a pretraining-finetuning pipeline where MLIPs are initially pretrained on data labelled with embedded atom model potentials and subsequently finetuned on the quantum mechanical ground truth data. By evaluating across three diverse material systems (phosphorus, silica, and a subset of Materials Project) and three representative MLIP architectures (CGCNN, M3GNet, and TorchMD-NET), we find that this physics-informed pretraining consistently improves both prediction accuracy as well as stability in MD compared to the baselines.

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。

↑