Machine-learning enabled optimization of atomic structures using atoms with fractional existence

Abstract

We introduce a method for global optimization of the structure of atomic systems that uses additional atoms with fractional existence. The method allows for movement of atoms over long distances bypassing energy barriers encountered in the conventional position space. The method is based on Gaussian processes, where the extrapolation to fractional existence is performed with a vectorial fingerprint. The method is applied to clusters and two-dimensional systems, where the fractional existence variables are optimized while keeping the atomic positions fixed on a lattice. Simultaneous optimization of atomic coordinates and existence variables is demonstrated on copper clusters of varying size. The existence variables are shown to speed up the global optimization of large and particularly difficult-to-optimize clusters.

6 pages, 5 figures, plus supplement

References in corpus (3)

• Global optimization of atomic structures with gradient-enhanced Gaussian process regression
• Hyperspatial optimisation of structures
• Atomic structure optimization with machine-learning enabled interpolation between chemical elements

Cited by in corpus (5)

• GPAW: An open Python package for electronic-structure calculations
• Generating candidates in global optimization algorithms using complementary energy landscapes
• $\Delta$-model correction of Foundation Model based on the models own understanding
• Accelerating structure search using atomistic graph-based classifiers
• Gradient-based grand canonical optimization enabled by graph neural networks with fractional atomic existence