Spatio-temporal reconstruction of an adhering droplet interface for PIV distortion correction by means of deep learning and glare points

In the present work a Deep Learning technique for the reconstruction of gas-liquid interfaces is introduced, with the scope of obtaining the instantaneous interface of adhering droplets in external shear flows. A purposefully developed optical measurement technique based on the shadowgraphy method is employed that encodes additional 3D-information of the interface in the images via glare points from lateral light sources. On the basis of the images recorded in the experiments the volumetric shape of the droplet is reconstructed by a neural network. The results for experiments with adhering droplets at different velocities of external flow demonstrate that the proposed method reconstructs the instantaneous three-dimensional interface of adhering droplets at both high resolution and spatial accuracy.