This minisymposium covers applications of state-of-the-art computational fluid dynamics (CFD) simulations for multi-physics problems in science and engineering. Topics of interest include, but are not limited to, reactive flows, multiphase/multiscale flows, Newtonian/non-Newtonian fluid flows, and turbulent flows. It serves as a forum to exchange ideas for future developments in the field. Emphasis is placed on novel computational methods, advanced simulations, and innovative uses of deep machine learning. Recent advances in data-driven analytics and AI are expanding the boundaries of traditional disciplines such as fluid science and engineering. CFD integrated with machine learning offers promising approaches to address complex flow problems across multiple spatial and temporal scales, while enabling efficient surrogate modeling to reduce computational costs. Contributions from students and early-career researchers are especially welcome, particularly those tackling unsolved or insufficiently addressed problems with creative strategies.