Exploiting instability mechanisms for the efficient data-driven forecasting of extreme events in airfoil flow

For certain Reynolds numbers, airfoil flow is susceptible to sporadic high amplitude fluctuations in the aerodynamic forces. These extreme excursions may be seen as prototypical of the kind of unsteady and intermittent dynamics relevant to the flow around airfoils and wings in a variety of real-world applications. Through a wavelet and spectral analysis of the surface pressure and vorticity fields we find that these extreme events arise due to the instability of a second slower frequency component distinct from the vortex shedding mode. During these events, this extreme event frequency draws energy from the energetically dominant vortex shedding flow and undergoes an abrupt transfer of energy from small to large scales. We exploit this phenomenon for the data-driven forecasting of extreme events from sparse measurements of the surface pressure through a preprocessing algorithm which extracts this extreme event frequency content from the measured data. Using our preprocessing algorithm, we are able to accurately forecast extreme events using a simple feed-forward network architecture – a significant reduction in computational complexity as compared to the recursive architectures more commonly used for such tasks.