Machine-Learning-Accelerated Metallene Stabilization from High-Throughput Sandwich Modeling
Abstract
Metallenes have appealing properties, but stabilizing them in a monolayer phase poses synthesis challenges. A recent experiment showed that the van der Waals squeezing method can stabilize certain metallenes in a MoS2 sandwich. This pioneering work motivates systematic studies, but such studies are experimentally impractical, while first-principles modeling remains prohibitive. Here, using universal machine-learning interatomic potentials, we constructed 1620 metallene sandwich heterostructures containing 6 different sandwich layers and 45 metals. We performed phonon calculations, which revealed 1208 dynamically stable structures and narrowed them to 331 after structural filtering. We found that Se-based transition-metal dichalcogenides stabilize metallenes effectively. Specifically, hexagonal and buckled hexagonal crystal lattices exhibit the greatest stability. We further evaluated the thermal stability of selected heterostructures with density-functional theory molecular dynamics simulations at room temperature. By uncovering the physical and chemical factors that govern metallenes stabilization, our results provide systematic insights to guide and accelerate synthesis for future applications.
Related
- Passage of particles through matter and the effective straggling-function: High-fidelity accelerated simulation via Physics-Informed Machine Learning
- Embracing Flow Unsteadiness: A High-Throughput Learning Platform Enables Vortex-Exploiting Bioinspired Propulsion
- Learning shape resonances from the stabilization method
- Machine Learning Accelerated Simulation of Charge Regulation Effects
- Machine Learning Accelerated Plasma Simulation through Physics Guided Time Jumps
BibTeX
@misc{bagheri2026machinelearningaccelerated,
title = {{Machine-Learning-Accelerated Metallene Stabilization from High-Throughput Sandwich Modeling}},
author = {Mohammad Bagheri and Pekka Koskinen},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2608.01779},
eprint = {2608.01779},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2608.01779},
}
RIS
TY - UNPB
TI - Machine-Learning-Accelerated Metallene Stabilization from High-Throughput Sandwich Modeling
AU - Mohammad Bagheri
AU - Pekka Koskinen
PY - 2026
DA - 2026/11/03
PB - arXiv
DO - 10.48550/arxiv.2608.01779
UR - https://arxiv.org/abs/2608.01779
AB - Metallenes have appealing properties, but stabilizing them in a monolayer phase poses synthesis challenges. A recent experiment showed that the van der Waals squeezing method can stabilize certain metallenes in a MoS2 sandwich. This pioneering work motivates systematic studies, but such studies are experimentally impractical, while first-principles modeling remains prohibitive. Here, using universal machine-learning interatomic potentials, we constructed 1620 metallene sandwich heterostructures containing 6 different sandwich layers and 45 metals. We performed phonon calculations, which revealed 1208 dynamically stable structures and narrowed them to 331 after structural filtering. We found that Se-based transition-metal dichalcogenides stabilize metallenes effectively. Specifically, hexagonal and buckled hexagonal crystal lattices exhibit the greatest stability. We further evaluated the thermal stability of selected heterostructures with density-functional theory molecular dynamics simulations at room temperature. By uncovering the physical and chemical factors that govern metallenes stabilization, our results provide systematic insights to guide and accelerate synthesis for future applications.
ER -