Cargando…

Application of Entropy Ensemble Filter in Neural Network Forecasts of Tropical Pacific Sea Surface Temperatures

Recently, the Entropy Ensemble Filter (EEF) method was proposed to mitigate the computational cost of the Bootstrap AGGregatING (bagging) method. This method uses the most informative training data sets in the model ensemble rather than all ensemble members created by the conventional bagging. In th...

Descripción completa

Detalles Bibliográficos
Autores principales: Foroozand, Hossein, Radić, Valentina, Weijs, Steven V.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2018
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7512722/
https://www.ncbi.nlm.nih.gov/pubmed/33265298
http://dx.doi.org/10.3390/e20030207
_version_ 1783586223523102720
author Foroozand, Hossein
Radić, Valentina
Weijs, Steven V.
author_facet Foroozand, Hossein
Radić, Valentina
Weijs, Steven V.
author_sort Foroozand, Hossein
collection PubMed
description Recently, the Entropy Ensemble Filter (EEF) method was proposed to mitigate the computational cost of the Bootstrap AGGregatING (bagging) method. This method uses the most informative training data sets in the model ensemble rather than all ensemble members created by the conventional bagging. In this study, we evaluate, for the first time, the application of the EEF method in Neural Network (NN) modeling of El Nino-southern oscillation. Specifically, we forecast the first five principal components (PCs) of sea surface temperature monthly anomaly fields over tropical Pacific, at different lead times (from 3 to 15 months, with a three-month increment) for the period 1979–2017. We apply the EEF method in a multiple-linear regression (MLR) model and two NN models, one using Bayesian regularization and one Levenberg-Marquardt algorithm for training, and evaluate their performance and computational efficiency relative to the same models with conventional bagging. All models perform equally well at the lead time of 3 and 6 months, while at higher lead times, the MLR model’s skill deteriorates faster than the nonlinear models. The neural network models with both bagging methods produce equally successful forecasts with the same computational efficiency. It remains to be shown whether this finding is sensitive to the dataset size.
format Online
Article
Text
id pubmed-7512722
institution National Center for Biotechnology Information
language English
publishDate 2018
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-75127222020-11-09 Application of Entropy Ensemble Filter in Neural Network Forecasts of Tropical Pacific Sea Surface Temperatures Foroozand, Hossein Radić, Valentina Weijs, Steven V. Entropy (Basel) Article Recently, the Entropy Ensemble Filter (EEF) method was proposed to mitigate the computational cost of the Bootstrap AGGregatING (bagging) method. This method uses the most informative training data sets in the model ensemble rather than all ensemble members created by the conventional bagging. In this study, we evaluate, for the first time, the application of the EEF method in Neural Network (NN) modeling of El Nino-southern oscillation. Specifically, we forecast the first five principal components (PCs) of sea surface temperature monthly anomaly fields over tropical Pacific, at different lead times (from 3 to 15 months, with a three-month increment) for the period 1979–2017. We apply the EEF method in a multiple-linear regression (MLR) model and two NN models, one using Bayesian regularization and one Levenberg-Marquardt algorithm for training, and evaluate their performance and computational efficiency relative to the same models with conventional bagging. All models perform equally well at the lead time of 3 and 6 months, while at higher lead times, the MLR model’s skill deteriorates faster than the nonlinear models. The neural network models with both bagging methods produce equally successful forecasts with the same computational efficiency. It remains to be shown whether this finding is sensitive to the dataset size. MDPI 2018-03-20 /pmc/articles/PMC7512722/ /pubmed/33265298 http://dx.doi.org/10.3390/e20030207 Text en © 2018 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Foroozand, Hossein
Radić, Valentina
Weijs, Steven V.
Application of Entropy Ensemble Filter in Neural Network Forecasts of Tropical Pacific Sea Surface Temperatures
title Application of Entropy Ensemble Filter in Neural Network Forecasts of Tropical Pacific Sea Surface Temperatures
title_full Application of Entropy Ensemble Filter in Neural Network Forecasts of Tropical Pacific Sea Surface Temperatures
title_fullStr Application of Entropy Ensemble Filter in Neural Network Forecasts of Tropical Pacific Sea Surface Temperatures
title_full_unstemmed Application of Entropy Ensemble Filter in Neural Network Forecasts of Tropical Pacific Sea Surface Temperatures
title_short Application of Entropy Ensemble Filter in Neural Network Forecasts of Tropical Pacific Sea Surface Temperatures
title_sort application of entropy ensemble filter in neural network forecasts of tropical pacific sea surface temperatures
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7512722/
https://www.ncbi.nlm.nih.gov/pubmed/33265298
http://dx.doi.org/10.3390/e20030207
work_keys_str_mv AT foroozandhossein applicationofentropyensemblefilterinneuralnetworkforecastsoftropicalpacificseasurfacetemperatures
AT radicvalentina applicationofentropyensemblefilterinneuralnetworkforecastsoftropicalpacificseasurfacetemperatures
AT weijsstevenv applicationofentropyensemblefilterinneuralnetworkforecastsoftropicalpacificseasurfacetemperatures