Chaotic model with data assimilation using NARX network

Authors:
Michael Siek;Dimitri Solomatine
Affiliations:
UNESCO-IHE Institute for Water Education, Delft, The Netherlands;UNESCO-IHE, Institute for Water Education and Water Resources Section, Delft University of Technology, The Netherlands
Venue:
IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
Year:
2009

Citing 3
Cited 1

Time Series Analysis: Forecasting and Control

Time Series Analysis: Forecasting and Control
Long-term time series prediction with the NARX network: An empirical evaluation

Neurocomputing
A delay damage model selection algorithm for NARX neural networks

IEEE Transactions on Signal Processing

Behavioural pattern identification and prediction in intelligent environments

Applied Soft Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper introduces a novel data assimilation technique where Nonlinear AutoRegressive with eXogenous inputs (NARX) model is used to re-analyze and improve chaotic model forecasts. The chaotic model is built using adaptive local models based on the dynamical neighbors in the reconstructed phase space of the observed time series data. The proposed method was implemented to build the storm surge model for the North Sea. The results demonstrated that the chaotic model with data assimilation has a significant increase of forecasting accuracy compared to standard chaotic model without data assimilation, a standard ANN model and the European operational storm surge numerical models.