Data-Driven, Physics-Based Feature Extraction from Fluid Flow Fields using Convolutional Neural Networks
Feature identification is an important task in many fluid dynamics applications
and diverse methods have been developed for this purpose. These methods
are based on a physical understanding of the underlying behavior of the flow
in the vicinity of the feature. Particularly, they require the definition of suitable criteria
(i.e. point-based or neighborhood-based derived properties) and proper selection
of thresholds. However, these methods rely on creative visualization of physical idiosyncrasies
of specific features and flow regimes, making them non-universal and
requiring significant effort to develop. Here we present a physics-based, data-driven
method capable of identifying any flow feature it is trained to. We use convolutional
neural networks, a machine learning approach developed for image recognition, and
adapt it to the problem of identifying flow features. This provides a general method
and removes the large burden placed on identifying new features. The method was
tested using mean flow fields from numerical simulations, where the recirculation region
and boundary layer were identified in several two-dimensional flows through
a convergent-divergent channel, and the horseshoe vortex was identified in threedimensional
flow over a wing-body junction.