Reconstructing the pressure field around an undulating body using a physics-informed neural network

Hydrodynamic pressure has often been used by fish and many other aquatic animals for detecting the surrounding environments and predators. Non-invasive methods of measuring the pressure signal on the surface of an undulating body is crucial for advancing our understanding of how fish react to the incoming flow. In this study, the authors propose a method for reconstructing the instantaneous pressure field around an undulating body by training a physics-informed neural network (PINN) on PIV data. We will show that the PINN is less sensitive to the spatio-temporal resolution of the velocity field measurements and provides a more accurate pressure reconstruction, particularly on the surface of the body, when compared to other methods that rely on directly integrating the pressure gradient field. With increased accuracy in the surface pressure prediction, this PINN method can be used as an accurate, invasive array of pressure sensors distributed over the entire fish body.