Fig. 5: Results of Gaussian Process Modeling Regression Tasks.
From: Physics-Informed Bayesian learning of electrohydrodynamic polymer jet printing dynamics
a Fitting normalized (\({R}_{j}/{R}_{o}\,\)) jet radius observation data (n = 5) obtained from the computer vision metrology module of the GPJet framework at specific z axis coordinates along the normalized jet length (\(Z/{R}_{o}\,\)). b Fitting normalized jet radius using a higher number of observation data (n = 10) compared to the previous case a. c Fitting lag distance (\({L}_{j}\)) observation data (n = 3) obtained from the computer vision metrology module of the GPJet framework for specific speed ratios (\({U}_{c}/{V}_{{jm}}\)). d Fitting lag distance using all available observation data (n = 12). For non-normalized quantities units are in SI. Filled contours (shading) represent uncertainty bounds (95% confidence intervals (CIs)).
