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


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.

Divisions: ?? 50811700Jl ??
College of Engineering & Physical Sciences > Systems analytics research institute (SARI)
ISBN: NCRG/98/022
Last Modified: 29 Nov 2023 14:17
Date Deposited: 29 Jul 2009 12:21
PURE Output Type: Technical report
Published Date: 1998-10-22
Authors: Evans, David J.
Cornford, Dan
Nabney, Ian T.


Export / Share Citation


Additional statistics for this record