A scatterometer neural network sensor model with input noise

Dan Cornford, Guillaume Ramage, Ian T. Nabney

Research output: Working paperTechnical report

Abstract

The ERS-1 satellite carries a scatterometer which measures the amount of radiation scattered back toward the satellite by the ocean's surface. These measurements can be used to infer wind vectors. The implementation of a neural network based forward model which maps wind vectors to radar backscatter is addressed. Input noise cannot be neglected. To account for this noise, a Bayesian framework is adopted. However, Markov Chain Monte Carlo sampling is too computationally expensive. Instead, gradient information is used with a non-linear optimisation algorithm to find the maximum em a posteriori probability values of the unknown variables. The resulting models are shown to compare well with the current operational model when visualised in the target space.
Original languageEnglish
Place of PublicationBirmingham
PublisherAston University
Number of pages8
ISBN (Print)NCRG/98/021
Publication statusPublished - 22 Oct 1998

Fingerprint

Neural networks
Sensors
Satellites
Markov processes
Radar
Sampling
Radiation

Keywords

  • non-linear regression
  • input uncertainty
  • wind retrieval
  • scatterometer

Cite this

Cornford, D., Ramage, G., & Nabney, I. T. (1998). A scatterometer neural network sensor model with input noise. Birmingham: Aston University.
Cornford, Dan ; Ramage, Guillaume ; Nabney, Ian T. / A scatterometer neural network sensor model with input noise. Birmingham : Aston University, 1998.
@techreport{d10d6310e69b4c218b1ac1132dd5bb4e,
title = "A scatterometer neural network sensor model with input noise",
abstract = "The ERS-1 satellite carries a scatterometer which measures the amount of radiation scattered back toward the satellite by the ocean's surface. These measurements can be used to infer wind vectors. The implementation of a neural network based forward model which maps wind vectors to radar backscatter is addressed. Input noise cannot be neglected. To account for this noise, a Bayesian framework is adopted. However, Markov Chain Monte Carlo sampling is too computationally expensive. Instead, gradient information is used with a non-linear optimisation algorithm to find the maximum em a posteriori probability values of the unknown variables. The resulting models are shown to compare well with the current operational model when visualised in the target space.",
keywords = "non-linear regression, input uncertainty, wind retrieval, scatterometer",
author = "Dan Cornford and Guillaume Ramage and Nabney, {Ian T.}",
year = "1998",
month = "10",
day = "22",
language = "English",
isbn = "NCRG/98/021",
publisher = "Aston University",
type = "WorkingPaper",
institution = "Aston University",

}

Cornford, D, Ramage, G & Nabney, IT 1998 'A scatterometer neural network sensor model with input noise' Aston University, Birmingham.

A scatterometer neural network sensor model with input noise. / Cornford, Dan; Ramage, Guillaume; Nabney, Ian T.

Birmingham : Aston University, 1998.

Research output: Working paperTechnical report

TY - UNPB

T1 - A scatterometer neural network sensor model with input noise

AU - Cornford, Dan

AU - Ramage, Guillaume

AU - Nabney, Ian T.

PY - 1998/10/22

Y1 - 1998/10/22

N2 - The ERS-1 satellite carries a scatterometer which measures the amount of radiation scattered back toward the satellite by the ocean's surface. These measurements can be used to infer wind vectors. The implementation of a neural network based forward model which maps wind vectors to radar backscatter is addressed. Input noise cannot be neglected. To account for this noise, a Bayesian framework is adopted. However, Markov Chain Monte Carlo sampling is too computationally expensive. Instead, gradient information is used with a non-linear optimisation algorithm to find the maximum em a posteriori probability values of the unknown variables. The resulting models are shown to compare well with the current operational model when visualised in the target space.

AB - The ERS-1 satellite carries a scatterometer which measures the amount of radiation scattered back toward the satellite by the ocean's surface. These measurements can be used to infer wind vectors. The implementation of a neural network based forward model which maps wind vectors to radar backscatter is addressed. Input noise cannot be neglected. To account for this noise, a Bayesian framework is adopted. However, Markov Chain Monte Carlo sampling is too computationally expensive. Instead, gradient information is used with a non-linear optimisation algorithm to find the maximum em a posteriori probability values of the unknown variables. The resulting models are shown to compare well with the current operational model when visualised in the target space.

KW - non-linear regression

KW - input uncertainty

KW - wind retrieval

KW - scatterometer

M3 - Technical report

SN - NCRG/98/021

BT - A scatterometer neural network sensor model with input noise

PB - Aston University

CY - Birmingham

ER -

Cornford D, Ramage G, Nabney IT. A scatterometer neural network sensor model with input noise. Birmingham: Aston University. 1998 Oct 22.