用GAN学习表面原子运动，速度更快且精度高。
Learning Kinetic Monte Carlo stochastic dynamics with Deep Generative Adversarial Networks
- 用条件GAN模拟表面台阶的随机演化过程
- 生成结果与真实模拟吻合度达95%以上
- 适合材料模拟、计算物理研究者参考
我们证明生成对抗网络（GAN）可有效学习随机动力学，替代传统模型并捕捉热涨落。以二维多粒子系统为例，聚焦表面台阶波动及相关的时变粗糙度。基于动能蒙特卡洛模拟构建数据集后，训练条件GAN以时间上随机推进系统状态，实现新序列生成且计算成本显著降低。针对标准GAN的改进设计提升了收敛性与精度。训练后的网络能定量再现平衡态与非平衡态性质，包括标度律，偏差仅几个百分点。对模型外推能力与未来方向进行了深入讨论。
原文摘要 · Abstract (English)
We show that Generative Adversarial Networks (GANs) may be fruitfully exploited to learn stochastic dynamics, surrogating traditional models while capturing thermal fluctuations. Specifically, we showcase the application to a two-dimensional, many-particle system, focusing on surface-step fluctuations and on the related time-dependent roughness. After the construction of a dataset based on Kinetic Monte Carlo simulations, a conditional GAN is trained to propagate stochastically the state of the system in time, allowing the generation of new sequences with a reduced computational cost. Modifications with respect to standard GANs, which facilitate convergence and increase accuracy, are discussed. The trained network is demonstrated to quantitatively reproduce equilibrium and kinetic properties, including scaling laws, with deviations of a few percent from the exact value. Extrapolation limits and future perspectives are critically discussed.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。