Fig. 5: Performance of the trained SNAP model for MOF-5. | npj Computational Materials

Fig. 5: Performance of the trained SNAP model for MOF-5.

From: Quantum-accurate machine learning potentials for metal-organic frameworks using temperature driven active learning

Fig. 5

Parity plots for energy (left-hand side panel), forces (middle panel) and virial-stress components (right-hand side panel) of the MOF-5 SNAP, computed over the training (596 configurations – upper panel) and test set (1191 configurations – lower panels). The RMSE for the test set are 0.6 meV/atom, 84 meV/Å and 11.6 MPa respectively for energy, forces and virial-stress components.

Back to article page