计算机科学
人工神经网络
人工智能
等变映射
理论计算机科学
图形
算法
图论
深层神经网络
数学
复杂网络
特征(语言学)
理论(学习稳定性)
作者
Yuxing Wang,Zhongwei Zhang,Shuang Lu,Shuyue Shan,Vitaly A. Kuzkin,Anton M. Krivtsov,Jie Chen
出处
期刊:Physical review
[American Physical Society]
日期:2026-05-29
卷期号:113 (6): 065305-065305
摘要
We propose a time-series paradigm named ChronoCast for molecular dynamics simulation using an advanced autoregressive Equivariant Graph Neural Network, which reformulates the conventionally time-consuming integration process into a forecasting task. This reformulation in turn offers a promising solution to overcome the challenge of tremendous computational cost for studying complex physical problems based on traditional algorithms. By incorporating velocity as a node feature and enforcing momentum conservation, the proposed model achieves exceptionally high accuracy in reproducing diverse physical properties. Using the simple Si crystal and complex van der Waals NbSe_{3} nanowires as two examples, we demonstrate that the radial distribution function, mean-squared displacement, and vibrational density of states in both systems can be accurately reproduced by long-term autoregressive forecasting. More importantly, ChronoCast significantly reduces the trajectory generation time by orders of magnitude compared to the ab initio method and by more than half compared to state-of-the-art machine learning potential, demonstrating superior efficiency over these prevailing molecular dynamics simulations. This work offers an accurate and efficient time-series approach for studying the statistical physics of complex dynamical processes.
科研通智能强力驱动
Strongly Powered by AbleSci AI