The proposed work will make substantial contributions to our understanding and development of a hybridization framework of Physics-Based (PB) and Machine Learning (ML) models aiming to advance the state of the art in the broad arenas of information theory, Artificial Intelligence (AI) and computer modeling of natural processes. Our main goal is to develop and test a new methodological framework to pave the way to the next generation of CFD models for efficient and robust simulation results. Insights generated by this research will not simply contribute to new knowledge into fundamental information sciences and fluid dynamics but they could also help understanding other fields such as material, chemical and life sciences where large data model outputs provide valuable information that can readily extracted and re-used as prior knowledge for further improved performance and prediction. This PB/ML framework could also be integrated to autonomous systems to improve intelligent and adaptive reconnaissance according to real-time communication with models.?