Skip to main content

Table 7 kNN and GP models performance retrieved from Yosipof et al. [41]

From: RANdom SAmple Consensus (RANSAC) algorithm for material-informatics: application to photovoltaic solar cells

Library Activity \(Q_{train}^{2}\) \(Q_{ext}^{2} (R^{2} )\) \(Q_{ext}^{2}\) \((R^{2} )\) (AD) \(Q_{ext}^{2} (R^{2} )\)
kNN GP kNN kNN GP
\(TiO_{2} |Cu_{2} O\) (Ag) J SC 0.92 0.74 0.92 (0.92) 0.92 (0.92) 0.76 (0.76)
V OC 0.78 0.65 0.89 (0.89) 0.89 (0.89) 0.78 (0.77)
IQE 0.91 0.70 0.87 (0.87) 0.87 (0.87) 0.72 (0.73)
\(TiO_{2} |Cu_{2} O\) (Ag|Cu) J SC 0.92 0.76 0.89 (0.89) 0.88 (0.89) 0.74 (0.76)
V OC 0.74 0.61 0.56 (0.55) 0.55 (0.54) 0.50 (0.50)
IQE 0.9 0.72 0.91 (0.91) 0.89 (0.89) 0.72 (0.73)