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

2026/04/15 by Omar Abou El Kheir, Dario Baratella, Marco Bernasconi · 1 voice
Physics and Astronomy · #cond-mat.dis-nn #cond-mat.mtrl-sci

paper · pdf · doi:10.1039/d6tc01214k

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-Sb₂Te₃ and Ge- Ge₂Sb₂Te₅ 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.

Citations

• Viscosity, breakdown of Stokes-Einstein relation and dynamical heterogeneity in supercooled liquid Ge₂Sb₂Te₅ from simulations with a neural network potential
• A practical guide to machine learning interatomic potentials -- Status and future
• Full-cycle device-scale simulations of memory materials with a tailored atomic-cluster-expansion potential
• Million-atom simulation of the set process in phase change memories at the real device scale
• Modeling Short-Range and Three-Membered Ring Structures in Lithium Borosilicate Glasses using Machine Learning Potential
• LAMMPS - a flexible simulation tool for particle-based materials modeling at the atomic, meso, and continuum scales
• Memory devices and applications for in-memory computing
• DScribe: Library of descriptors for machine learning in materials science
• DeePMD-kit: A deep learning package for many-body potential energy representation and molecular dynamics
• Breakdown of Stokes-Einstein relation in the supercooled liquid state of phase change materials
• A consistent and accurateab initioparametrization of density functional dispersion correction (DFT-D) for the 94 elements H-Pu
• Coexistence of tetrahedral and octahedral-like sites in amorphous phase change materials
• Semiempirical GGA‐type density functional constructed with a long‐range dispersion correction
• Quickstep: Fast and accurate density functional calculations using a mixed Gaussian and plane waves approach
• Escaping free-energy minima

Discussions

• 相変化メモリ（PCM）に用いられるGeリッチGeSbTe合金の結晶化・相分離プロセスを、機械学習ポテンシャル（MLIP）を用いた原子レベルシミュレーションで詳細に解析しました。DFT計算で学習したMLIPにより、メモリ動作条件（600K、nsスケール）下での相変化挙動を忠実に再現し、熱力学的に安定な相とは異なる準安定相が形成されるメカニズムを解明しました。これにより、PCMの性能向上に繋がる材料設 [bsky, 0 points, 0 comments]

Related

• Unveiling the crystallization kinetics in Ge-rich Ge_xTe alloys by large scale simulations with a machine-learned interatomic potential
• Million-atom simulation of the set process in phase change memories at the real device scale
• Computationally Efficient Machine-Learned Model for GST Phase Change Materials via Direct and Indirect Learning
• A Fully Coupled Multi-Physics Model to Simulate Phase Change Memory Operations in Ge-rich Ge₂Sb₂Te₅ Alloys
• Simulation of the crystallization kinetics of Ge₂Sb₂Te₅ nanoconfined in superlattice geometries for phase change memories