Atomistic structure search using local surrogate mode
This work addresses computational efficiency in materials science and chemistry for researchers, but it is incremental as it builds on existing methods like GAP and basin hopping.
The authors tackled the problem of accelerating global structure search for atomistic systems by introducing a local surrogate model based on the Gaussian approximation potential formalism, which replaces some local relaxations in basin hopping and demonstrates robustness across molecules, nanoparticles, and surfaces.
We describe a local surrogate model for use in conjunction with global structure search methods. The model follows the Gaussian approximation potential (GAP) formalism and is based on a the smooth overlap of atomic positions descriptor with sparsification in terms of a reduced number of local environments using mini-batch $k$-means. The model is implemented in the Atomistic Global Optimization X framework and used as a partial replacement of the local relaxations in basin hopping structure search. The approach is shown to be robust for a wide range of atomistic system including molecules, nano-particles, surface supported clusters and surface thin films. The benefits in a structure search context of a local surrogate model are demonstrated. This includes the ability to transfer learning from smaller systems as well as the possibility to perform concurrent multi-stoichiometry searches.