Unraveling the crystallization kinetics of the Ge₂Sb₂Te₅ phase change compound with a machine-learned interatomic potential

The phase change compound Ge₂Sb₂Te₅ (GST225) is exploited in advanced non-volatile electronic memories and in neuromorphic devices which both rely on a fast and reversible transition between the crystalline and amorphous phases induced by Joule heating. The crystallization kinetics of GST225 is a key functional feature for the operation of these devices. We report here on the development of a machine-learned interatomic potential for GST225 that allowed us to perform large scale molecular dynamics simulations (over 10000 atoms for over 100 ns) to uncover the details of the crystallization kinetics in a wide range of temperatures of interest for the programming of the devices. The potential is obtained by fitting with a deep neural network (NN) scheme a large quantum-mechanical database generated within Density Functional Theory. The availability of a highly efficient and yet highly accurate NN potential opens the possibility to simulate phase change materials at the length and time scales of the real devices.

相变化合物Ge₂Sb₂Te₅（GST225）被应用于先进非易失性电子存储器与神经形态器件中，这两类器件均依靠焦耳热诱导的晶相与非晶相间的快速可逆相变实现工作。GST225的结晶动力学是这类器件运行的关键功能特性。本文报道了一种针对GST225的机器学习原子间势的开发工作，借助该势函数我们得以开展大规模分子动力学模拟（模拟体系包含逾10000个原子，模拟时长超100纳秒），从而在器件编程所需的宽泛温度区间内揭示结晶动力学的细节。该势函数通过深度神经网络（Deep Neural Network，NN）架构拟合基于密度泛函理论（Density Functional Theory）生成的大型量子力学数据库而得到。这款兼具高效性与高精度的NN势函数的问世，使得在真实器件的空间与时间尺度下模拟相变材料成为可能。