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 2502.04668physics.chem-phcs.LG
收藏

机器学习长程系统原子间势

Machine-Learning Interatomic Potentials for Long-Range Systems

School of Mathematical Sciences, Shanghai Jiao Tong University, Shanghai 200240, China(上海交通大学数学科学学院);Center for Computational Mathematics, Flatiron Institute, Simons Foundation, New York 10010, USA(Flatiron研究所计算数学中心);MOE-LSC, Shanghai Jiao Tong University, Shanghai 200240, China(上海交通大学教育部重点实验室)

Yajie Ji, Jiuyang Liang, Zhenli Xu

AI总结:

针对机器学习原子间势忽视长程相互作用的问题,提出高斯和神经网络(SOG-Net),通过潜变量学习网络和傅里叶卷积层整合长程效应,以近线性复杂度高效模拟长程系统。

摘要:

机器学习原子间势已成为分子模拟中一类革命性的力场模型,以极低的计算成本提供量子力学精度,并能够在延长的时间尺度上模拟大规模系统。然而,它们通常侧重于模拟局部环境,忽略了至关重要的长程相互作用。我们提出了一种高斯和神经网络(SOG-Net),这是一个轻量级且通用的框架,用于将长程相互作用整合到机器学习力场中。SOG-Net采用了一个潜变量学习网络,无缝连接短程和长程组件,并结合了一个高效的傅里叶卷积层来纳入长程效应。通过在不同卷积层学习高斯和乘子,SOG-Net自适应地捕获各种长程衰减行为,同时通过非均匀快速傅里叶变换在训练和模拟过程中保持接近线性的计算复杂度。该方法被证明对广泛的长程系统有效。

英文摘要:

Machine-learning interatomic potentials have emerged as a revolutionary class of force-field models in molecular simulations, delivering quantum-mechanical accuracy at a fraction of the computational cost and enabling the simulation of large-scale systems over extended timescales. However, they often focus on modeling local environments, neglecting crucial long-range interactions. We propose a Sum-of-Gaussians Neural Network (SOG-Net), a lightweight and versatile framework for integrating long-range interactions into machine learning force field. The SOG-Net employs a latent-variable learning network that seamlessly bridges short-range and long-range components, coupled with an efficient Fourier convolution layer that incorporates long-range effects. By learning sum-of-Gaussians multipliers across different convolution layers, the SOG-Net adaptively captures diverse long-range decay behaviors while maintaining close-to-linear computational complexity during training and simulation via non-uniform fast Fourier transforms. The method is demonstrated effective for a broad range of long-range systems.

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。

↑