In this article, we introduce a machine learning–based reduced-order modeling (ML-ROM) framework through the integration of proper orthogonal decomposition (POD) and deep neural networks (DNNs), in addition to long short-term memory (LSTM) networks. The DNN is utilized to upscale POD temporal coefficients and their respective spatial modes to account for the dynamics represented by the truncated modes. In the second part of the algorithm, temporal evolution of the POD coefficients is obtained by recursively predicting their future states using an LSTM network. The proposed model (ML-ROM) is tested for flow past a circular cylinder characterized by the Navier–Stokes equations. We perform pressure mode decomposition analysis on the flow data using both POD and ML-ROM to predict hydrodynamic forces and demonstrate the accuracy of the proposed strategy for modeling lift and drag coefficients.
Enabling forward uncertainty quantification and sensitivity analysis in cardiac electrophysiology by reduced order modeling and machine learning
