Figure 3
From: Multi-fidelity information fusion with concatenated neural networks
Boundary layer prediction for laminar flat plate flow at \(x/L=0.5\) along with the observations used for training the ML and PGML model. The amount of observations data used for training the model is 10% (left), 30% (middle), and 50% (right). The shaded area corresponds to two standard deviation (2-SD) band.
