H.C.M. furtado, H.F. de Campos Velho, E.E.N. Macau (2008): Data Assimilation: Particle Filter and Artificial Neural Networks, 6th International Conference on Inverse Problems in Engineering: Theory and Practice (ICIPE-2008), June 15-19, Dourdan (Paris), France.

Abstract: The goal of this work is to present the performance of the Neural Network Multilayer Perceptrons trained to emulate a Particle Filter in the context of data assimilation. Techniques for data assimilation are applied for the Lorenz system, which presents a strong nonlinearity and chaotic nature. The cross validation method was used for training the network. Good results were obtained applying the multilayer perceptrons neural network.