Fig. 7: Performance of the ML models expressed by R² applied to atmospheric corrosion (refs. ^{1,2,3,4,6,9,11}).

Data points were segmented by ‘Targets’ (current I, CR, depth) and by ‘ML models’. R² values are distinguished for the training (‘O’) and testing (‘X’) performances. Meaningful entries from the following features were included in the plot: the ‘Material’ (Zn, steel¹¹, steels⁶); the ‘Selected features’ (elements, phys. features¹). Q_ACM indicates the RF with charge correction⁴. The purple and green arrows, respectively, indicate the data points from refs. ³ and ⁹ (modelling on the same dataset). The difference between values a, b, c and a′, b′, c′ highlights a low generalisation ability².