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...

Full description

Saved in:
Bibliographic Details
Published in:Entropy (Basel, Switzerland) Switzerland), 2018-03, Vol.20 (3), p.207
Main Authors: Foroozand, Hossein, Radić, Valentina, Weijs, Steven V
Format: Article
Language:English
Subjects:
Bagging
Bayesian analysis
bootstrap aggregating
bootstrap neural networks
Computational efficiency
Computing time
EEF method
El Nino
El Niño
ensemble model simulation criterion
ENSO
Entropy
entropy ensemble filter
Lead time
neural network forecast
Neural networks
Ocean currents
Production methods
Regression models
Regularization
Sea surface temperature
Southern Oscillation
Training
tropical Pacific
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:1099-4300
1099-4300
DOI:10.3390/e20030207