Achieving DFT accuracy with a machine-learning interatomic potential: Thermomechanics and defects in bcc ferromagnetic iron

Dragoni, Daniele 
Marzari, Nicola 

Thumbnail Image
Change log

We show that the Gaussian Approximation Potential (GAP) machine-learning framework can describe complex magnetic potential energy surfaces, taking ferromagnetic iron as a paradigmatic challenging case. The training database includes total energies, forces, and stresses obtained from density-functional theory in the generalized-gradient approximation, and comprises approximately 150,000 local atomic environments, ranging from pristine and defected bulk configurations to surfaces and generalized stacking faults with different crystallographic orientations. We find the structural, vibrational, and thermodynamic properties of the GAP model to be in excellent agreement with those obtained directly from first-principles electronic-structure calculations. There is good transferability to quantities, such as Peierls energy barriers, which are determined to a large extent by atomic configurations that were not part of the training set. We observe the benefit and the need of using highly converged electronic-structure calculations to sample a target potential energy surface. The end result is a systematically improvable potential that can achieve the same accuracy of density-functional theory calculations, but at a fraction of the computational cost.

Publication Date
Online Publication Date
Acceptance Date
Journal Title
Physical Review Materials
Journal ISSN
Volume Title
Engineering and Physical Sciences Research Council (EP/L014742/1)
Engineering and Physical Sciences Research Council (EP/K014560/1)
Engineering and Physical Sciences Research Council (EP/P022596/1)