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

Research output: Contribution to journalArticle

View graph of relations Save citation


Research units


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.


Original languageEnglish
Pages (from-to)23-30
Number of pages8
Issue number1-4
Publication statusPublished - Jan 2000

Bibliographic note



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

Employable Graduates; Exploitable Research

Copy the text from this field...