Attempts to use machine learning to develop atmospheric
parameterizations have mainly focused on subgrid effects on temperature
and moisture, but subgrid momentum transport is also important in
simulations of the atmospheric circulation. Here, we use neural networks
to develop a parameterization of subgrid momentum transport that learns
from coarse-grained data of a high-resolution atmospheric simulation in
an idealized aquaplanet domain. We show that substantial subgrid
momentum transport occurs due to convection and non-orographic gravity
waves. The parameterization has a structure that ensures the
conservation of momentum, and it has reasonable skill in predicting
momentum fluxes associated with convection, although its skill is lower
as compared to subgrid energy and moisture fluxes. The neural-network
parameterization is implemented in the same atmospheric model at coarse
resolution and leads to stable simulations. Overall, our results show
that it is challenging to predict subgrid momentum fluxes and that
machine-learning momentum parameterization gives promising results.