A general-purpose machine learning Pt interatomic potential for an accurate description of bulk, surfaces and nanoparticles

Abstract

A Gaussian approximation machine learning interatomic potential for platinum is presented. It has been trained on DFT data computed for bulk, surfaces and nanostructured platinum, in particular nanoparticles. Across the range of tested properties, which include bulk elasticity, surface energetics and nanoparticle stability, this potential shows excellent transferability and agreement with DFT, providing state-of-the-art accuracy at low computational cost. We showcase the possibilities for modeling of Pt systems enabled by this potential with two examples: the pressure-temperature phase diagram of Pt calculated using nested sampling and a study of the spontaneous crystallization of a large Pt nanoparticle based on classical dynamics simulations over several nanoseconds.

References in corpus (3)

• Machine-learning based interatomic potential for amorphous carbon
• Nested sampling for physical scientists
• Constant-pressure nested sampling with atomistic dynamics

Cited by in corpus (8)

• General-purpose machine-learned potential for 16 elemental metals and their alloys
• Machine Learning and Data-Driven Methods in Computational Surface and Interface Science
• Recent advances in describing and driving crystal nucleation using machine learning and artificial intelligence
• Searching for iron nanoparticles with a general-purpose Gaussian approximation potential
• Replica exchange nested sampling
• Guest Editorial: Special Topic on Software for Atomistic Machine Learning
• Improved capabilities of the TurboGAP code for radiation induced cascade simulations: an illustration with silicon
• Active learning potentials for first-principles phase diagrams using replica-exchange nested sampling