Analysis of a gaussian process and feed-forward neural networks based filter for forecasting short rainfall time series

Autores
Rodriguez Rivero, C.; Pucheta, J.; Patiño, H.; Baumgartner, J.; Laboret, S.; Sauchelli, V.
Año de publicación
2013
Idioma
inglés
Tipo de recurso
documento de conferencia
Estado
versión publicada
Descripción
Fil: Rodriguez Rivero, C. Universidad Nacional de Córdoba; Argentina.
Fil: Pucheta, J. Universidad Nacional de Córdoba; Argentina.
Fil: Patiño, H. Universidad Nacional de Córdoba; Argentina.
Fil: Baumgartner, J. Universidad Nacional de Córdoba; Argentina.
Fil: Laboret, S. Universidad Nacional de Córdoba; Argentina.
Fil: Sauchelli, V. Universidad Nacional de Córdoba; Argentina.
In this paper, an analysis of kernel (GP) and feed-forward neural networks (FFNN) based filter to forecast short rainfall time series is presented. For the FFNN, the learning rule used to adjust the filter weights is based on the Levenberg-Marquardt method and Bayesian approach by the assumption of the prior distributions. In addition, a heuristic law is used to relate the time series roughness with the tuning process. The input patterns for both NN-based and kernel models are the values of rainfall time series after applying a time-delay operator. Hence, the NN´s outputs will tend to approximate the current value of the time series. The time lagged inputs of the GP and their covariance functions are both determined via a multicriteria genetic algorithm, called NSGA-II. The optimization criteria are the quantity of inputs and the filter´s performance on the known data which leads to Pareto optimal solutions. Both filters -FFNN and GP Kernel- are tested over a rainfall time series obtained from La Sevillana establishment. This work proposed a comparison of well-known filter referenced in early work where the contribution resides in the analysis of the best horizon of the forecasted rainfall time series proposed by Bayesian adjustment. The performance attained is shown by the forecast of the next 15 months values of rainfall time series from La Sevillana establishment located in (-31° 1´22.46"S, 62°40´9.57"O) Balnearia, Cordoba, Argentina.
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6706741&isnumber=6706705
Fil: Rodriguez Rivero, C. Universidad Nacional de Córdoba; Argentina.
Fil: Pucheta, J. Universidad Nacional de Córdoba; Argentina.
Fil: Patiño, H. Universidad Nacional de Córdoba; Argentina.
Fil: Baumgartner, J. Universidad Nacional de Córdoba; Argentina.
Fil: Laboret, S. Universidad Nacional de Córdoba; Argentina.
Fil: Sauchelli, V. Universidad Nacional de Córdoba; Argentina.
Sistemas de Automatización y Control
Materia
Artificial neural networks
Rainfall forecast
Hursts parameter
Analysis of kernel
Bayesian adjustment
Nivel de accesibilidad
acceso abierto
Condiciones de uso
Repositorio
Repositorio Digital Universitario (UNC)
Institución
Universidad Nacional de Córdoba
OAI Identificador
oai:rdu.unc.edu.ar:11086/29596

id RDUUNC_5375dbd52671cdbf212087073cfc0405
oai_identifier_str oai:rdu.unc.edu.ar:11086/29596
network_acronym_str RDUUNC
repository_id_str 2572
network_name_str Repositorio Digital Universitario (UNC)
spelling Analysis of a gaussian process and feed-forward neural networks based filter for forecasting short rainfall time seriesRodriguez Rivero, C.Pucheta, J.Patiño, H.Baumgartner, J.Laboret, S.Sauchelli, V.Artificial neural networksRainfall forecastHursts parameterAnalysis of kernelBayesian adjustmentFil: Rodriguez Rivero, C. Universidad Nacional de Córdoba; Argentina.Fil: Pucheta, J. Universidad Nacional de Córdoba; Argentina.Fil: Patiño, H. Universidad Nacional de Córdoba; Argentina.Fil: Baumgartner, J. Universidad Nacional de Córdoba; Argentina.Fil: Laboret, S. Universidad Nacional de Córdoba; Argentina.Fil: Sauchelli, V. Universidad Nacional de Córdoba; Argentina.In this paper, an analysis of kernel (GP) and feed-forward neural networks (FFNN) based filter to forecast short rainfall time series is presented. For the FFNN, the learning rule used to adjust the filter weights is based on the Levenberg-Marquardt method and Bayesian approach by the assumption of the prior distributions. In addition, a heuristic law is used to relate the time series roughness with the tuning process. The input patterns for both NN-based and kernel models are the values of rainfall time series after applying a time-delay operator. Hence, the NN´s outputs will tend to approximate the current value of the time series. The time lagged inputs of the GP and their covariance functions are both determined via a multicriteria genetic algorithm, called NSGA-II. The optimization criteria are the quantity of inputs and the filter´s performance on the known data which leads to Pareto optimal solutions. Both filters -FFNN and GP Kernel- are tested over a rainfall time series obtained from La Sevillana establishment. This work proposed a comparison of well-known filter referenced in early work where the contribution resides in the analysis of the best horizon of the forecasted rainfall time series proposed by Bayesian adjustment. The performance attained is shown by the forecast of the next 15 months values of rainfall time series from La Sevillana establishment located in (-31° 1´22.46"S, 62°40´9.57"O) Balnearia, Cordoba, Argentina.http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6706741&isnumber=6706705Fil: Rodriguez Rivero, C. Universidad Nacional de Córdoba; Argentina.Fil: Pucheta, J. Universidad Nacional de Córdoba; Argentina.Fil: Patiño, H. Universidad Nacional de Córdoba; Argentina.Fil: Baumgartner, J. Universidad Nacional de Córdoba; Argentina.Fil: Laboret, S. Universidad Nacional de Córdoba; Argentina.Fil: Sauchelli, V. Universidad Nacional de Córdoba; Argentina.Sistemas de Automatización y Control2013info:eu-repo/semantics/conferenceObjectinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_5794info:ar-repo/semantics/documentoDeConferenciaapplication/pdf978-1-4673-6128-6http://hdl.handle.net/11086/29596enginfo:eu-repo/semantics/openAccessreponame:Repositorio Digital Universitario (UNC)instname:Universidad Nacional de Córdobainstacron:UNC2025-09-29T13:40:55Zoai:rdu.unc.edu.ar:11086/29596Institucionalhttps://rdu.unc.edu.ar/Universidad públicaNo correspondehttp://rdu.unc.edu.ar/oai/snrdoca.unc@gmail.comArgentinaNo correspondeNo correspondeNo correspondeopendoar:25722025-09-29 13:40:55.876Repositorio Digital Universitario (UNC) - Universidad Nacional de Córdobafalse
dc.title.none.fl_str_mv Analysis of a gaussian process and feed-forward neural networks based filter for forecasting short rainfall time series
title Analysis of a gaussian process and feed-forward neural networks based filter for forecasting short rainfall time series
spellingShingle Analysis of a gaussian process and feed-forward neural networks based filter for forecasting short rainfall time series
Rodriguez Rivero, C.
Artificial neural networks
Rainfall forecast
Hursts parameter
Analysis of kernel
Bayesian adjustment
title_short Analysis of a gaussian process and feed-forward neural networks based filter for forecasting short rainfall time series
title_full Analysis of a gaussian process and feed-forward neural networks based filter for forecasting short rainfall time series
title_fullStr Analysis of a gaussian process and feed-forward neural networks based filter for forecasting short rainfall time series
title_full_unstemmed Analysis of a gaussian process and feed-forward neural networks based filter for forecasting short rainfall time series
title_sort Analysis of a gaussian process and feed-forward neural networks based filter for forecasting short rainfall time series
dc.creator.none.fl_str_mv Rodriguez Rivero, C.
Pucheta, J.
Patiño, H.
Baumgartner, J.
Laboret, S.
Sauchelli, V.
author Rodriguez Rivero, C.
author_facet Rodriguez Rivero, C.
Pucheta, J.
Patiño, H.
Baumgartner, J.
Laboret, S.
Sauchelli, V.
author_role author
author2 Pucheta, J.
Patiño, H.
Baumgartner, J.
Laboret, S.
Sauchelli, V.
author2_role author
author
author
author
author
dc.subject.none.fl_str_mv Artificial neural networks
Rainfall forecast
Hursts parameter
Analysis of kernel
Bayesian adjustment
topic Artificial neural networks
Rainfall forecast
Hursts parameter
Analysis of kernel
Bayesian adjustment
dc.description.none.fl_txt_mv Fil: Rodriguez Rivero, C. Universidad Nacional de Córdoba; Argentina.
Fil: Pucheta, J. Universidad Nacional de Córdoba; Argentina.
Fil: Patiño, H. Universidad Nacional de Córdoba; Argentina.
Fil: Baumgartner, J. Universidad Nacional de Córdoba; Argentina.
Fil: Laboret, S. Universidad Nacional de Córdoba; Argentina.
Fil: Sauchelli, V. Universidad Nacional de Córdoba; Argentina.
In this paper, an analysis of kernel (GP) and feed-forward neural networks (FFNN) based filter to forecast short rainfall time series is presented. For the FFNN, the learning rule used to adjust the filter weights is based on the Levenberg-Marquardt method and Bayesian approach by the assumption of the prior distributions. In addition, a heuristic law is used to relate the time series roughness with the tuning process. The input patterns for both NN-based and kernel models are the values of rainfall time series after applying a time-delay operator. Hence, the NN´s outputs will tend to approximate the current value of the time series. The time lagged inputs of the GP and their covariance functions are both determined via a multicriteria genetic algorithm, called NSGA-II. The optimization criteria are the quantity of inputs and the filter´s performance on the known data which leads to Pareto optimal solutions. Both filters -FFNN and GP Kernel- are tested over a rainfall time series obtained from La Sevillana establishment. This work proposed a comparison of well-known filter referenced in early work where the contribution resides in the analysis of the best horizon of the forecasted rainfall time series proposed by Bayesian adjustment. The performance attained is shown by the forecast of the next 15 months values of rainfall time series from La Sevillana establishment located in (-31° 1´22.46"S, 62°40´9.57"O) Balnearia, Cordoba, Argentina.
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6706741&isnumber=6706705
Fil: Rodriguez Rivero, C. Universidad Nacional de Córdoba; Argentina.
Fil: Pucheta, J. Universidad Nacional de Córdoba; Argentina.
Fil: Patiño, H. Universidad Nacional de Córdoba; Argentina.
Fil: Baumgartner, J. Universidad Nacional de Córdoba; Argentina.
Fil: Laboret, S. Universidad Nacional de Córdoba; Argentina.
Fil: Sauchelli, V. Universidad Nacional de Córdoba; Argentina.
Sistemas de Automatización y Control
description Fil: Rodriguez Rivero, C. Universidad Nacional de Córdoba; Argentina.
publishDate 2013
dc.date.none.fl_str_mv 2013
dc.type.none.fl_str_mv info:eu-repo/semantics/conferenceObject
info:eu-repo/semantics/publishedVersion
http://purl.org/coar/resource_type/c_5794
info:ar-repo/semantics/documentoDeConferencia
format conferenceObject
status_str publishedVersion
dc.identifier.none.fl_str_mv 978-1-4673-6128-6
http://hdl.handle.net/11086/29596
identifier_str_mv 978-1-4673-6128-6
url http://hdl.handle.net/11086/29596
dc.language.none.fl_str_mv eng
language eng
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv reponame:Repositorio Digital Universitario (UNC)
instname:Universidad Nacional de Córdoba
instacron:UNC
reponame_str Repositorio Digital Universitario (UNC)
collection Repositorio Digital Universitario (UNC)
instname_str Universidad Nacional de Córdoba
instacron_str UNC
institution UNC
repository.name.fl_str_mv Repositorio Digital Universitario (UNC) - Universidad Nacional de Córdoba
repository.mail.fl_str_mv oca.unc@gmail.com
_version_ 1844618887803437056
score 13.070432