A neural network approach for modeling nonlinear transfer functions: Application for wind retrieval from spaceborne scatterometer data

The present paper shows that a wide class of complex transfer functions encountered in geophysics can be efficiently modeled using neural networks. Neural networks can approximate numerical and nonnumerical transfer functions. They provide an optimum basis of nonlinear functions allowing a uniform approximation of any continuous function. Neural networks can also realize classification tasks. It is shown that the classifier mode is related to Bayes discriminant functions, which give the minimum error risk classification. This mode is useful for extracting information from an unknown process. These properties are applied to the ERS1 simulated scatterometer data. Compared to other methods, neural network solutions are the most skillful.

[1]  Richard O. Duda,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[2]  John C. Price The nature of multiple solutions for surface wind speed over the oceans from scatterometer measurements , 1976 .

[3]  Michael H. Freilich,et al.  Wavenumber Spectra of Pacific Winds Measured by the Seasat Scatterometer , 1986 .

[4]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[5]  Richard P. Lippmann,et al.  An introduction to computing with neural nets , 1987 .

[6]  Fuk K. Li,et al.  A comparative study of several wind estimation algorithms for spaceborne scatterometers , 1988 .

[7]  H. Roquet,et al.  Towards Direct Variational Assimilation Of Scatiterometer Backscatter Measurements Into Numerical Weather Prediction Models , 1988, International Geoscience and Remote Sensing Symposium, 'Remote Sensing: Moving Toward the 21st Century'..

[8]  Richard Lippmann,et al.  Review of Neural Networks for Speech Recognition , 1989, Neural Computation.

[9]  Ken-ichi Funahashi,et al.  On the approximate realization of continuous mappings by neural networks , 1989, Neural Networks.

[10]  Halbert White,et al.  Learning in Artificial Neural Networks: A Statistical Perspective , 1989, Neural Computation.

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

[12]  H. Gish,et al.  A probabilistic approach to the understanding and training of neural network classifiers , 1990, International Conference on Acoustics, Speech, and Signal Processing.

[13]  H. Schultz A circular median filter approach for resolving directional ambiguities in wind fields retrieved from spaceborne scatterometer data , 1990 .

[14]  H. Bourlard,et al.  Links Between Markov Models and Multilayer Perceptrons , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[15]  S. Thiria,et al.  Wind ambiguity removal by the use of neural network techniques , 1991 .

[16]  Fouad Badran,et al.  Multimodular Architecture for Remote Sensing Operations. , 1991, NIPS 1991.

[17]  Edward K. Blum,et al.  Approximation theory and feedforward networks , 1991, Neural Networks.

[18]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

[19]  Elie Bienenstock,et al.  Neural Networks and the Bias/Variance Dilemma , 1992, Neural Computation.

[20]  Roberto Battiti,et al.  First- and Second-Order Methods for Learning: Between Steepest Descent and Newton's Method , 1992, Neural Computation.