“…Neural networks have been used to model dynamical systems for decades [8,14,34], although recent advances in computing power, data volumes, and deep learning architectures have dramatically improved their capabilities. Reccurrent neural networks naturally model sequential processes and have been used for forecasting [60,37,28,39,38] and closure models for reduced order models [61,36]. Deep learning approaches have also been used recently to find coordinate transformations that make strongly nonlinear systems approximately linear, related to Koopman operator theory [57,64,63,32,29].…”