Fig. 8: Results of a GNN model for LSHR grain-scale elastic response generated with a single tessellation and “shuffled” orientation sets using the lattice orientation (components of the Rodrigues vector r) as nodal features. | npj Computational Materials

Fig. 8: Results of a GNN model for LSHR grain-scale elastic response generated with a single tessellation and “shuffled” orientation sets using the lattice orientation (components of the Rodrigues vector r) as nodal features.

From: Graph neural network modeling of grain-scale anisotropic elastic behavior using simulated and measured microscale data

Fig. 8

a Learning rates using various numbers of CEFEM simulations for training and testing. b Histogram and c scatter plot of the grain-scale stress predictions on a new microstructure comparing those from a GNN trained with data from the shuffled orientation sets in a single tessellation (GNN-S) and full-field CEFEM.

Back to article page