摘要
Surrogate machine-learning models are transforming computational materials science by predicting properties of materials with the accuracy of ab initio methods at a fraction of the computational cost.We demonstrate surrogate models that simultaneously interpolate energies of different materials on a dataset of 10 binary alloys(AgCu,AlFe,AlMg,AlNi,AlTi,CoNi,CuFe,CuNi,FeV,and NbNi)with 10 different species and all possible fcc,bcc,and hcp structures up to eight atoms in the unit cell,15,950 structures in total.We find that the deviation of prediction errors when increasing the number of simultaneously modeled alloys is<1 meV/atom.Several state-of-the-art materials representations and learning algorithms were found to qualitatively agree on the prediction errors of formation enthalpy with relative errors of<2.5% for all systems.
基金
C.N.,B.B.,C.R.,and G.L.W.H.acknowledge the funding from ONR(MURI N00014-13-1-0635)
M.R.acknowledges funding from the EU Horizon 2020 program Grant 676580
The Novel Materials Discovery(NOMAD)Laboratory,a European Center of Excellence
A.V.S.was supported by the Russian Science Foundation(Grant No 18-13-00479)
T.M.acknowledges funding from the National Science Foundation under award number DMR-1352373 and computational resources provided by the Maryland Advanced Research Computing Center(MARCC).