Popov, Andrey Anatoliyevich2022-08-242022-08-242022-08-23vt_gsexam:35404http://hdl.handle.net/10919/111608There once was a dream that data-driven models would replace their theory-guided counterparts. We have awoken from this dream. We now know that data cannot replace theory. Data-driven models still have their advantages, mainly in computational efficiency but also providing us with some special sauce that is unreachable by our current theories. This dissertation aims to provide a way in which both the accuracy of theory-guided models, and the computational efficiency of data-driven models can be combined. This combination of theory-guided and data-driven allows us to combine ideas from a much broader set of disciplines, and can help pave the way for robust and fast methods.ETDenIn Copyrightensemble data assimilationdata-driven modelingmultifidelitycovariance shrinkageDissertation