Aufgrund von Vorbereitungen auf eine neue Version von KOPS, können derzeit keine Publikationen eingereicht werden. (Due to preparations for a new version of KOPS, no publications can be submitted currently.)

Machine-learned multi-system surrogate models for materials prediction

Cite This

Files in this item

Checksum: MD5:dec22656ec6d865d058526988e8a12b4

NYSHADHAM, Chandramouli, Matthias RUPP, Brayden BEKKER, Alexander V. SHAPEEV, Tim MUELLER, Conrad W. ROSENBROCK, Gábor CSÁNYI, David W. WINGATE, Gus L. W. HART, 2019. Machine-learned multi-system surrogate models for materials prediction. In: npj Computational Materials. Nature Publishing Group. 5(1), 51. eISSN 2057-3960. Available under: doi: 10.1038/s41524-019-0189-9

@article{Nyshadham2019-12Machi-52916, title={Machine-learned multi-system surrogate models for materials prediction}, year={2019}, doi={10.1038/s41524-019-0189-9}, number={1}, volume={5}, journal={npj Computational Materials}, author={Nyshadham, Chandramouli and Rupp, Matthias and Bekker, Brayden and Shapeev, Alexander V. and Mueller, Tim and Rosenbrock, Conrad W. and Csányi, Gábor and Wingate, David W. and Hart, Gus L. W.}, note={Article Number: 51} }

Csányi, Gábor Shapeev, Alexander V. Rosenbrock, Conrad W. Mueller, Tim 2019-12 Shapeev, Alexander V. 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. Wingate, David W. Machine-learned multi-system surrogate models for materials prediction Nyshadham, Chandramouli Rupp, Matthias Mueller, Tim Bekker, Brayden Rosenbrock, Conrad W. Attribution 4.0 International Wingate, David W. Bekker, Brayden 2021-02-19T08:15:27Z Nyshadham, Chandramouli 2021-02-19T08:15:27Z Rupp, Matthias Csányi, Gábor Hart, Gus L. W. eng Hart, Gus L. W.

Downloads since Feb 19, 2021 (Information about access statistics)

Nyshadham_2-1h3gbixbs24pl9.pdf 307

This item appears in the following Collection(s)

Attribution 4.0 International Except where otherwise noted, this item's license is described as Attribution 4.0 International

Search KOPS


My Account