fig3

Machine learning-assisted high-entropy alloy discovery: a perspective

Figure 3. MLP for efficient atomistic simulations of HEAs. (A) Overview of the four generations of NNP; (B) Schematic illustration of the second-generation NNP architecture and its short-range environment descriptors. The figures are quoted with permission from Behler[46]; (C) Performance evaluation of UNEP-v1 for MoTaVW alloys, including mono-vacancy formation energies from UNEP-v1 and EAM, as well as comparisons of UNEP-v1, EAM, and DFT results for equimolar MoTaVW alloys. The figures are quoted with permission from Song et al.[48]; (D) Training efficiency and convergence on a multicomponent Pd-Cu-Ni-P alloy dataset.

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/