In the literature, it has been shown equivalences between a traditional regression using machine learning and a data assimilation framework. 

We aim at determining learning numerically unresolved parts of dynamic systems by leveraging on both data assimilation and machine learning techniques. The idea of this work is to train the neural network to estimate only the part of prediction which is not already predicted by the physical model. We will combine physical modeling with a neural network to improve the nowcasting of precipitation. The training set needed to train the neural net will be produced by a data assimilation scheme.