Backpropagation and gradient descent for an optimized dynamic mode decomposition

Abstract: We present a robust and flexible optimization approach for dynamic mode decomposition analysis of data with complex dynamics and low signal-to-noise ratios. The approach borrows techniques and insights from the field of deep learning. Specifically, we employ automatic differentiation and stochastic gradient descent to compute eigenvalues, modes, and mode amplitudes simultaneously. The method allows embedding regularization or physical constraints into the operator definition. The optimization approach is applied to three examples of increasing complexity, the most challenging of which is an experimental dataset of transonic shock buffet on a swept at realistic flight conditions.