fig9

High-entropy alloy catalysts: high-throughput and machine learning-driven design

Figure 9. (A) OH* adsorption energies for 871 2 × 2 periodic unit cells. (B) O* adsorption energies for 998 2 × 2 periodic unit cells. (C) OH* adsorption. The linear model was trained on 871 symmetric 2 × 2 unit cells (blue dots) and tested on 76 asymmetric 3 × 4 unit cells (red crosses). The linear model used 15 parameters. (D) O* adsorption. The linear model was trained on 998 symmetric 2 × 2 unit cells (blue dots) and tested on 36 asymmetric 3 × 4 unit cells (red crosses). The linear model used 55 parameters. The dashed lines span the region ± 0.1 eV, where most of the data were seen to be contained. (E) OH* adsorption. Each color represents an individual on-top binding site as in (A). (F) O* adsorption. Each color represents an individual FCC hollow binding site, as shown in (B). (G) Workflow of Bayesian optimization algorithm. The algorithm was terminated after n = 150 samples to ensure sufficient evaluations for gauging the deviation in the number of samples needed for the discovery of the optimal compositions. For evaluation of the acquisition function, n = 1000 random compositions were sampled. (A-F) Reproduced with permission[60]. Copyright 2019, Elsevier. (G) Reproduced with permission[84]. Copyright 2021, Wiley-VCH. FCC: face-centered cubic.

Journal of Materials Informatics
ISSN 2770-372X (Online)
Follow Us

Portico

All published articles are preserved here permanently:

https://www.portico.org/publishers/oae/

Portico

All published articles are preserved here permanently:

https://www.portico.org/publishers/oae/