Artificial Neural Networks emulating Representer Method at a shallow water model 2D

Abstract

The goal of the present work is to employ artificial neural networks as a data assimilation method applied to shallow water equation. This model is used to represent ocean dynamics. Data assimilation is a computational procedure to combine observation data with model data for identifying the best initial condition (analysis) to an operational prediction system. Here we compare two techniques: representer method and artificial neural network.