Fig. 6
From: Predicting the dissolution kinetics of silicate glasses by topology-informed machine learning
Predictions from “topology-informed” machine learning, that is, by explicitly accounting for the exponential dependence of the dissolution rate on the inputs, capturing the distinct acidic and caustic regimes, and describing the glass structure in terms of the number of topological constraints per atom nc (“Model IV”). a Evolution of the relative root square mean square error (RRMSE) of the training and validation sets with respect to the polynomial degree p. The minimum in the RRMSE of the validation set indicates p = 1 as an optimal polynomial degree (i.e., linear model). b Predicted dissolution rate for p = 1 as a function of the measured dissolution rate
