Fig. 4: Performance of the different versions of PhysNet-DER on the test set.
From: Outlier-detection for reactive machine learned potential energy surfaces
A–C On the left show residual plots of the error between reference and inference for DER-S, DER-L, and DER-M, respectively. The 1000 points with the largest variance are shaded with a different color (red, orange, and yellow from top to bottom) and directly reflect the model’s capability to detect outliers. The corresponding color bar represents the scale of the values. Squared error distribution (solid lines) and variance distributions (dotted lines) are shown in the center next to A–C for comparison. Complementary to this is the variance distribution shown on the right of both panels. Notice that the x axis on the centre and right are in logarithmic scale.
