Structured neural network modelling of multi-valued functions for wind retrieval from scatterometer measurements

Research output: Working paperTechnical report

View graph of relations Save citation

Authors

Research units

Abstract

A conventional neural network approach to regression problems approximates the conditional mean of the output vector. For mappings which are multi-valued this approach breaks down, since the average of two solutions is not necessarily a valid solution. In this article mixture density networks, a principled method to model conditional probability density functions, are applied to retrieving Cartesian wind vector components from satellite scatterometer data. A hybrid mixture density network is implemented to incorporate prior knowledge of the predominantly bimodal function branches. An advantage of a fully probabilistic model is that more sophisticated and principled methods can be used to resolve ambiguities.

Documents

Details

Original languageEnglish
Place of PublicationBirmingham
PublisherAston University
Number of pages8
ISBN (Print)NCRG/98/022
StatePublished - 22 Oct 1998

    Keywords

  • wind vector retrieval, ERS-1 satellite, probabilistic models, mixture density networks, neural networks

Download statistics

No data available

Employable Graduates; Exploitable Research

Copy the text from this field...