Table 1 Identification of the important features for predicting EFA values.

From: Discovery of high-entropy ceramics via machine learning

Predictor rank Model
Stoichiometric attributes CALPHAD
1 avg(ionic character) avg(ionic character)
2 min(electrons) Liquidus temperature*
3 avg. dev(s-valence electrons) range(electronegativity)
4 max(atomic weight) avg. dev(d-valence electrons)
5 max(covalent radius) max(atomic weight)
6 fwm(covalent radius) fwm(f-valence electrons)
7 range(Mendeleev number) max(covalent radius)
8 avg. dev(melting temp) max(unfilled valence electrons)
9 fwm(unfilled s-valence) fwm(covalent radius)
10 fwm(f-electrons) range(unfilled valence electrons)
  1. The top ten features for the ML model with only the chemical attributes are on the left. The top ten features for the ML model including CALPHAD features are on the right. Both models rely on similar features regarding electronegativity, ionic character, and electron orbitals for making the best predictions. The avg(x) and avg. dev(x) denote the composition-weighted average and average deviation, respectively, calculated over the vector of elemental values for each compound. The min(x), max(x), fwm(x), and range(x) correspond to the minimum, maximum, fraction-weighted mean, and range of an attribute for each compound. Features marked with an * are computed from CALPHAD.