Comparison of Different Neural Network Approaches for the Tropospheric Profiling over the Inter-tropical lands Using GPS Radio Occultation Data

In this study different approaches based on multilayer perceptron neural networks are proposed and evaluated with the aim to retrieve tropospheric profiles by using GPS radio occultation data. We employed a data set of 445 occultations covering the land surface within the Tropics, split into desert...

Full description

Bibliographic Details
Main Authors: Stefania Bonafoni, Fabrizio Pelliccia, Roberta Anniballe
Format: Article
Language:English
Published: MDPI AG 2009-01-01
Series:Algorithms
Subjects:
Online Access:http://www.mdpi.com/1999-4893/2/1/31/
_version_ 1818437649455644672
author Stefania Bonafoni
Fabrizio Pelliccia
Roberta Anniballe
author_facet Stefania Bonafoni
Fabrizio Pelliccia
Roberta Anniballe
author_sort Stefania Bonafoni
collection DOAJ
description In this study different approaches based on multilayer perceptron neural networks are proposed and evaluated with the aim to retrieve tropospheric profiles by using GPS radio occultation data. We employed a data set of 445 occultations covering the land surface within the Tropics, split into desert and vegetation zone. The neural networks were trained with refractivity profiles as input computed from geometrical occultation parameters provided by the FORMOSAT-3/COSMIC satellites, while the targets were the dry and wet refractivity profiles and the dry pressure profiles obtained from the contemporary European Centre for Medium-Range Weather Forecast data. Such a new retrieval algorithm was chosen to solve the atmospheric profiling problem without the constraint of an independent knowledge of one atmospheric parameter at each GPS occultation.
first_indexed 2024-12-14T17:28:02Z
format Article
id doaj.art-5d02e7230afb4d3f9de5f780816d099d
institution Directory Open Access Journal
issn 1999-4893
language English
last_indexed 2024-12-14T17:28:02Z
publishDate 2009-01-01
publisher MDPI AG
record_format Article
series Algorithms
spelling doaj.art-5d02e7230afb4d3f9de5f780816d099d2022-12-21T22:53:10ZengMDPI AGAlgorithms1999-48932009-01-0121314510.3390/a2010031Comparison of Different Neural Network Approaches for the Tropospheric Profiling over the Inter-tropical lands Using GPS Radio Occultation DataStefania BonafoniFabrizio PellicciaRoberta AnniballeIn this study different approaches based on multilayer perceptron neural networks are proposed and evaluated with the aim to retrieve tropospheric profiles by using GPS radio occultation data. We employed a data set of 445 occultations covering the land surface within the Tropics, split into desert and vegetation zone. The neural networks were trained with refractivity profiles as input computed from geometrical occultation parameters provided by the FORMOSAT-3/COSMIC satellites, while the targets were the dry and wet refractivity profiles and the dry pressure profiles obtained from the contemporary European Centre for Medium-Range Weather Forecast data. Such a new retrieval algorithm was chosen to solve the atmospheric profiling problem without the constraint of an independent knowledge of one atmospheric parameter at each GPS occultation.http://www.mdpi.com/1999-4893/2/1/31/Neural networksGPSradio occultationstropospheric profiles
spellingShingle Stefania Bonafoni
Fabrizio Pelliccia
Roberta Anniballe
Comparison of Different Neural Network Approaches for the Tropospheric Profiling over the Inter-tropical lands Using GPS Radio Occultation Data
Algorithms
Neural networks
GPS
radio occultations
tropospheric profiles
title Comparison of Different Neural Network Approaches for the Tropospheric Profiling over the Inter-tropical lands Using GPS Radio Occultation Data
title_full Comparison of Different Neural Network Approaches for the Tropospheric Profiling over the Inter-tropical lands Using GPS Radio Occultation Data
title_fullStr Comparison of Different Neural Network Approaches for the Tropospheric Profiling over the Inter-tropical lands Using GPS Radio Occultation Data
title_full_unstemmed Comparison of Different Neural Network Approaches for the Tropospheric Profiling over the Inter-tropical lands Using GPS Radio Occultation Data
title_short Comparison of Different Neural Network Approaches for the Tropospheric Profiling over the Inter-tropical lands Using GPS Radio Occultation Data
title_sort comparison of different neural network approaches for the tropospheric profiling over the inter tropical lands using gps radio occultation data
topic Neural networks
GPS
radio occultations
tropospheric profiles
url http://www.mdpi.com/1999-4893/2/1/31/
work_keys_str_mv AT stefaniabonafoni comparisonofdifferentneuralnetworkapproachesforthetroposphericprofilingovertheintertropicallandsusinggpsradiooccultationdata
AT fabriziopelliccia comparisonofdifferentneuralnetworkapproachesforthetroposphericprofilingovertheintertropicallandsusinggpsradiooccultationdata
AT robertaanniballe comparisonofdifferentneuralnetworkapproachesforthetroposphericprofilingovertheintertropicallandsusinggpsradiooccultationdata