On phase separation and crystallization of Ge-rich GeSbTe alloys from atomistic simulations with a machine learning interatomic potential

TL;DR

This paper introduces a machine learning interatomic potential for Ge-rich GeSbTe alloys, enabling atomistic simulations of phase separation and crystallization relevant for phase change memory applications.

Contribution

The authors developed a transferable MLIP trained on DFT data, allowing realistic simulations of phase change processes in GeSbTe alloys.

Findings

Simulated crystallization at 600 K shows formation of cubic GeTe and amorphous phases.

The MLIP accurately predicts phase behavior across a wide composition range.

Kinetic effects influence the formation of metastable phases during memory operation.

Abstract

We developed a machine learning interatomic potential (MLIP) for Ge-rich GeSbTe alloys of interest for applications in phase change memories embedded in microcontrollers. The MLIP was generated by fitting with a neural network method a large database of energies and forces computed within density functional theory of elemental, binary, stoichiometric and non-stoichiometric ternary alloys in the Ge-Sb-Te phase diagram. The MLIP is demonstrated to be highly transferable to large regions of the phase diagram around the compositions included in the dataset. The MLIP is then exploited to simulate the crystallization with phase separation of three Ge-rich alloys on the Ge-Sb$_2$Te$_3$ and Ge- Ge$_2$Sb$_2$Te$_5$ tie-lines that correspond to the set process of the memory cell. The transformation on the ns time scale and at 600 K, comparable to the operation conditions of the memory, yields crystalline cubic GeTe slightly Sb-doped and amorphous GeSb and Ge. These metastable phases differ from the thermodynamically stable products and form due to kinetics effects on the short time span of the set operation in phase change memories.