4D-Var data assimilation using an adjoint model of a neural network
Four-dimensional variational (4D-Var) data assimilation is an effective
assimilation method for obtaining physically consistent time-varying
states. In this study, I propose a method using a neural network
surrogate model obtained by machine learning to solve one of the most
serious challenges in 4D-Var, which is to construct an adjoint model.
The feasibility of the method was demonstrated by a 4D-Var experiment
using a surrogate model for the Lorenz 96 model. Several effective
procedures have been proposed to obtain an accurate surrogate model and
the assimilated initial conditions: two-stage learning (i.e., single-
and multi-step learning) of neural networks, limiting the target states
of the surrogate model to a small subspace of the state phase space, and
updating the surrogate model during 4D-Var iterations.