Laboratoire Charles Coulomb (L2C), Université de Montpellier, CNRS, 34095 Montpellier, France.
Laboratoire de Physique de l'Ecole Normale Supérieure, ENS, Université PSL, CNRS, Sorbonne Université, Université de Paris, F-75005 Paris, France.
Phys Rev Lett. 2023 Jun 9;130(23):238202. doi: 10.1103/PhysRevLett.130.238202.
We introduce GlassMLP, a machine learning framework using physics-inspired structural input to predict the long-time dynamics in deeply supercooled liquids. We apply this deep neural network to atomistic models in 2D and 3D. Its performance is better than the state of the art while being more parsimonious in terms of training data and fitting parameters. GlassMLP quantitatively predicts four-point dynamic correlations and the geometry of dynamic heterogeneity. Transferability across system sizes allows us to efficiently probe the temperature evolution of spatial dynamic correlations, revealing a profound change with temperature in the geometry of rearranging regions.
我们引入了 GlassMLP，这是一个使用物理启发的结构输入的机器学习框架，用于预测深度过冷液体的长时间动力学。我们将这个深度神经网络应用于 2D 和 3D 的原子模型。与最先进的方法相比，它在训练数据和拟合参数方面更加简约，但性能更好。GlassMLP 定量预测了四点动态相关函数和动态非均匀性的几何形状。在不同系统大小之间的可转移性允许我们有效地探测空间动态相关性的温度演化，揭示了在重新排列区域的几何形状上随温度的深刻变化。
