Repository logo

Machine-learned interatomic potentials for alloys and alloy phase diagrams

Published version

Change log


Rosenbrock, Conrad W.  ORCID logo
Gubaev, Konstantin 
Shapeev, Alexander V.  ORCID logo
Pártay, Livia B. 


Abstract: We introduce machine-learned potentials for Ag-Pd to describe the energy of alloy configurations over a wide range of compositions. We compare two different approaches. Moment tensor potentials (MTPs) are polynomial-like functions of interatomic distances and angles. The Gaussian approximation potential (GAP) framework uses kernel regression, and we use the smooth overlap of atomic position (SOAP) representation of atomic neighborhoods that consist of a complete set of rotational and permutational invariants provided by the power spectrum of the spherical Fourier transform of the neighbor density. Both types of potentials give excellent accuracy for a wide range of compositions, competitive with the accuracy of cluster expansion, a benchmark for this system. While both models are able to describe small deformations away from the lattice positions, SOAP-GAP excels at transferability as shown by sensible transformation paths between configurations, and MTP allows, due to its lower computational cost, the calculation of compositional phase diagrams. Given the fact that both methods perform nearly as well as cluster expansion but yield off-lattice models, we expect them to open new avenues in computational materials modeling for alloys.



Article, /639/301/1034/1035, /639/301/1034/1037, article

Journal Title

npj Computational Materials

Conference Name

Journal ISSN


Volume Title



Nature Publishing Group UK