<ul><li>Reduced order models (ROMs) are important in fluid mechanics for low-cost predictions in engineering applications.</li><li>A new nonlinear reduction strategy is presented for transient flows, incorporating parametrization and uncertainty quantification.</li><li>The strategy uses a variational auto-encoder (VAE) with variational inference for confidence measurement.</li><li>The incorporation of attention mechanisms enhances generalization across different dynamics, improving model performance.</li></ul>

UP-ROM : Uncertainty-Aware and Parametrised dynamic Reduced-Order Model, application to unsteady flows

Discover more