Figure 3
From: Learning from droplet flows in microfluidic channels using deep neural networks
(a) Flow rate measurement: the measured results are compared with the true values for a water-IPA concentration of 5.5%. The red points are the flow rates for which the network is trained and the blue points are the new flow rates. Error bars show the standard deviation of the predicted values. (b) Examples of the flow regime transitions that occur at 0.45 ml/h and 1.45 ml/h flow rate of water-IPA. Silicone oil flow rate is 2 ml/h. The scale bar is 100 μm.
