Machine learning is rapidly becoming a core technology for scientific computing, with numerous opportunities to advance the field of computational fluid dynamics. This paper highlights some of the areas of highest potential impact, including to accelerate direct numerical simulations, to improve turbulence closure modelling, and to develop enhanced reduced-order models. In each of these areas, it is possible to improve machine learning capabilities by incorporating physics into the process, and in turn, to improve the simulation of fluids to uncover new physical understanding. Despite the promise of machine learning described here, we also note that classical methods are often more efficient for many tasks. We also emphasize that in order to harness the full potential of machine learning to improve computational fluid dynamics, it is essential for the community to continue to establish benchmark systems and best practices for open-source software, data sharing, and reproducible research.