Investigation of different topologies of neural networks for data assimilation

Abstract

Neural networks have emerged as a novel scheme for a data assimilation process. Neural network techniques are applied for data assimilation in the Lorenz chaotic system. A radial basis function and a multilayer perceptron neural networks are trained employing 1000, 2000, and 4000 examples. Three different observation intervals are used: 0.01, 0.06 and 0.1 s. The performance of the data assimilation technique is investigated for different architectures of these neural networks.