Fig. 4: ML model benchmarking for accuracy and generalizability. | npj Computational Materials

Fig. 4: ML model benchmarking for accuracy and generalizability.

From: Polymer design for solvent separations by integrating simulations, experiments and known physics via machine learning

Fig. 4: ML model benchmarking for accuracy and generalizability.

This figure presents the test error (OME) as a function of the training set size (corresponding to x% of \({D}_{\,\text{act}\,}^{\exp }\)), averaged over five runs. MT models outperformed single-task (ST1 and ST2), especially with limited data. Physics-enforced PENN-2 models showed the lowest errors as the trainset size grew. MT models with physics-enforced learning improved robustness and generalizability.

Back to article page