The full field dynamics of a separated, noise-amplifier flow, the Backward-Facing Step at Re h = 1385, have been identified by probe-like, upstream measurements using an artificial Neural Network. Local visual sensors, coming from time-resolved Particle Image Velocimetry, were used as inputs and the dynamic Proper Orthogonal Decomposition coefficients were defined as goals-outputs for this non-linear mapping. The coefficients time-series were predicted and the instantaneous velocity fields were reconstructed with satisfying accuracy. The choices of inputs-sensors, training data-set size, hidden layer neurons and training hyperparameters are discussed for this experimental fluid system.

We present a data-driven methodology to achieve identification of coherent structures dynamics and system order reduction of an experimental turbulent boundary layer (TBL) flow. The flow is characterized using time-resolved Optical Flow Particle Image Velocimetry, leading to dense velocity fields that can be used both to monitor the overall dynamics of the flow and to define as many local visual sensors as needed. A Proper Orthogonal Decomposition (POD) is first applied to define a reduced-order system. A non-linear mapping between the local upstream sensors (inputssensors) and the full-field dynamics (POD coefficients) as outputs is sought using an optimal Focused Time-Delay (FTD) Artificial Neural Network (ANN). The choices of sensors, ANN architecture and training parameters are shown to play a critical role. It is verified that a shallow ANN, with the proper sensor memory size, can lead to a satisfying full-field dynamics identification, coherent structure reconstruction, and system order reduction of this turbulent flow.