fig8

Borides as promising M<sub>2</sub>AX phase materials with high elastic modulus using machine learning and optimization

Figure 8. Comparison of acquisition functions and number of initial function evaluations in Bayesian optimization with an ensemble of XGB models, with various ranges (or bounds) for the features (A) min to max, (B) ± 20% from V2PC, and (C) ± 10% from V2PC. Features corresponding to the maximum predicted elastic modulus are shown in the table. XGB: XGBoost; EI: expected improvement; PI: probability improvement; LCB: lower confidence bound.

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/