Initial rate of H2 production (kinetics model) Final H2 concentration (yield model)
Autoprediction 0.006 0.99 0.031 0.996
k-fold cross-validation (k=10) 0.006 1 0.043 0.992
Validation 0.202 0.952 0.324 0.905
Table 4: Performance of ANN models built on the “Base zero” dataset. This learning dataset is composed of input and output vectors derived from 65,536 different simulations of the H2 producing system. Shown are the Root Mean Square Errors (RMSE) and the coefficient of determination (R2) of the kinetics and yield models. Results for autoprediction and k-fold cross validation were evaluated on the learning dataset itself. Results for validation were evaluated on the independent “Base V” dataset (see Method for details).