Composition k-NN¶

Mean property of the five training materials nearest in element-fraction space: a composition-only representation, without structure.

Property prediction¶

metric	value	definition
MAE ΔH	0.511 eV/atom	mean absolute error of the formation enthalpy (heat_all)
RMSE ΔH	0.674 eV/atom	root-mean-square error of the formation enthalpy
R² ΔH	0.179	coefficient of determination of the formation enthalpy (0 = no better than the mean)
MAE gap	0.163 eV	mean absolute error of the direct band gap over all test materials; 96% of them have a gap of 0 eV
MAE gap > 0	2.044 eV	mean absolute error of the direct band gap on the test materials with a non-zero gap, the range that inverse design targets
RMSE gap	0.568 eV	root-mean-square error of the direct band gap
R² gap	-0.122	coefficient of determination of the direct band gap; not informative here, because the gap is zero for most materials
MAE ΔH ≠ 0	0.511 eV/atom	mean absolute error of the formation enthalpy on materials where it is not zero
n	3,785	test materials evaluated

Composition k-NN: formation enthalpy, predicted vs. DFT

Composition k-NN: direct band gap, predicted vs. DFT

metric	value	definition
k-NN MAE ΔH	0.511 eV/atom	formation-enthalpy error of a 5-nearest-neighbour probe: each test material takes the mean property of its five nearest training materials in the representation
k-NN MAE gap	0.163 eV	direct-band-gap error of the same probe
n	3,785	test materials evaluated
R@1	–	fraction of test materials for which, among the distinct property profiles of the test split, their own profile's latent is the nearest to their structure latent (materials with identical property values share one profile)

python scripts/benchmarks.py run perov5 --method baseline-composition-knn

Computed on Intel64 Family 6 Model 197 Stepping 2, GenuineIntel (16 threads), CPU only; the evaluation took 22 s.