Coastal upwelling prediction with a mixture of neural networks

For the analysis and prediction of coastal upwelling in a study region off the northwest African coast, artificial neural networks are applied to wind data and remotely sensed sea surface temperature (SST) data. The coastal upwelling phenomenon is seen as an input-output system, built by the dependence between local wind events as input and upwelling, quantified by the SST index as output. To gain a priori knowledge about the input-output system, it is studied from a theoretical point of view with coastal upwelling simulations, which are performed with a three-dimensional (3D) ocean circulation model on artificial wind data. The dynamics observed in these studies are found to be bounded and dependent on previous states as well as nonlinear, which motivates the application of artificial neural network (ANN) techniques as a nonlinear modeling technique. To cope with this type of system and with the nonstationarity of the parameters used, a mixture of neural networks is applied for system analysis and prediction. The output space of the system is segmented in an unsupervised manner, while the modular neural networks are specializing on one segment each. It is shown that different dynamic structures in the input-output system are detected by the mixture approach and prediction is improved. The synergetic approach presented, using numerical models to gain a priori knowledge for the choice and design of a neural prediction tool, is appealing for implementing simulations or modeling into an operational application, for instance, geographical information systems (GISs) or decision support systems (DSSs).

[1]  Esther Levin,et al.  Accelerated Learning in Layered Neural Networks , 1988, Complex Syst..

[2]  Klaus-Robert Müller,et al.  Analysis of switching dynamics with competing neural networks , 1995 .

[3]  John Moody,et al.  Fast Learning in Networks of Locally-Tuned Processing Units , 1989, Neural Computation.

[4]  Christopher M. Bishop,et al.  Neural networks for pattern recognition , 1995 .

[5]  K. Brink.  The near-surface dynamics of coastal upwelling , 1983 .

[6]  W. Eifler.  A hypothesis on momentum and heat transfer near the sea-atmosphere interface and a related simple model , 1993 .

[7]  Geoffrey E. Hinton,et al.  Adaptive Mixtures of Local Experts , 1991, Neural Computation.

[8]  Martin Casdagli,et al.  Nonlinear prediction of chaotic time series , 1989 .

[9]  Gwilym M. Jenkins,et al.  Time series analysis, forecasting and control , 1972 .

[10]  Rose,et al.  Statistical mechanics and phase transitions in clustering. , 1990, Physical review letters.

[11]  L. V. Camp,et al.  Seasonal and interannual variability of coastal upwelling along northwest Africa and Portugal from 1981 to 1991 , 1994 .

[12]  Prediction of the upwelling phenomenon at the northwest African Atlantic coast-a connectionist approach , 1997, IGARSS'97. 1997 IEEE International Geoscience and Remote Sensing Symposium Proceedings. Remote Sensing - A Scientific Vision for Sustainable Development.

[13]  Yoshua Bengio,et al.  Pattern Recognition and Neural Networks , 1995 .

[14]  Peter D. Killworth,et al.  A free surface Bryan-Cox-Semtner model , 1989 .

[15]  George E. P. Box,et al.  Time Series Analysis: Forecasting and Control , 1977 .

[16]  Robert L. Smith,et al.  Temporal variation observed in the hydrographic regime near Cabo Corveiro in the northwest African upwelling region, February to April 1974 , 1977 .

[17]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[18]  P. T. Szymanski,et al.  Adaptive mixtures of local experts are source coding solutions , 1993, IEEE International Conference on Neural Networks.

[19]  F. Takens.  Detecting strange attractors in turbulence , 1981 .

[20]  Akio Arakawa,et al.  Computational Design of the Basic Dynamical Processes of the UCLA General Circulation Model , 1977 .