Comment on “Prediction of the SYM‐H Index Using a Bayesian Deep Learning Method With Uncertainty Quantification” by Abduallah et al. (2024)

Abstract Abduallah et al. (2024b, https://doi.org/10.1029/2023sw003824) proposed a novel approach using a deep neural network model, which includes a graph neural network and a bidirectional LSTM layer, named SYMHnet, to forecast the SYM‐H index one and 2 hr in advance. Additionally, the network als...

Full description

Saved in:
Bibliographic Details
Main Authors: Armando Collado‐Villaverde, Pablo Muñoz, Consuelo Cid
Format: Article
Language:English
Published: Wiley 2024-08-01
Series:Space Weather
Subjects:
Online Access:https://doi.org/10.1029/2024SW003909
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1841536446064754688
author Armando Collado‐Villaverde
Pablo Muñoz
Consuelo Cid
author_facet Armando Collado‐Villaverde
Pablo Muñoz
Consuelo Cid
author_sort Armando Collado‐Villaverde
collection DOAJ
description Abstract Abduallah et al. (2024b, https://doi.org/10.1029/2023sw003824) proposed a novel approach using a deep neural network model, which includes a graph neural network and a bidirectional LSTM layer, named SYMHnet, to forecast the SYM‐H index one and 2 hr in advance. Additionally, the network also provides an uncertainty quantification of the predictions. While the approach is innovative, there are some areas where the model's design and implementation may not align with best practices in uncertainty quantification and predictive modeling. We focus on discrepancies in the input and output of the model, which can limit the applicability in real‐world forecasting scenarios. This comment aims to clarify these issues, offering detailed insights into how such discrepancies could compromise the model's interpretability and reliability, thereby contributing to the advancement of predictive modeling in space weather research.
format Article
id doaj-art-e1bb18208aa84ad8a3aa829cddf6102c
institution Kabale University
issn 1542-7390
language English
publishDate 2024-08-01
publisher Wiley
record_format Article
series Space Weather
spelling doaj-art-e1bb18208aa84ad8a3aa829cddf6102c2025-01-14T16:27:32ZengWileySpace Weather1542-73902024-08-01228n/an/a10.1029/2024SW003909Comment on “Prediction of the SYM‐H Index Using a Bayesian Deep Learning Method With Uncertainty Quantification” by Abduallah et al. (2024)Armando Collado‐Villaverde0Pablo Muñoz1Consuelo Cid2Department of Computer Engineering Universidad de Alcalá Madrid SpainDepartment of Computer Engineering Universidad de Alcalá Madrid SpainDepartment of Physics and Mathematics Universidad de Alcalá Madrid SpainAbstract Abduallah et al. (2024b, https://doi.org/10.1029/2023sw003824) proposed a novel approach using a deep neural network model, which includes a graph neural network and a bidirectional LSTM layer, named SYMHnet, to forecast the SYM‐H index one and 2 hr in advance. Additionally, the network also provides an uncertainty quantification of the predictions. While the approach is innovative, there are some areas where the model's design and implementation may not align with best practices in uncertainty quantification and predictive modeling. We focus on discrepancies in the input and output of the model, which can limit the applicability in real‐world forecasting scenarios. This comment aims to clarify these issues, offering detailed insights into how such discrepancies could compromise the model's interpretability and reliability, thereby contributing to the advancement of predictive modeling in space weather research.https://doi.org/10.1029/2024SW003909machine learninguncertaintygeomagnetic indices forecasting
spellingShingle Armando Collado‐Villaverde
Pablo Muñoz
Consuelo Cid
Comment on “Prediction of the SYM‐H Index Using a Bayesian Deep Learning Method With Uncertainty Quantification” by Abduallah et al. (2024)
Space Weather
machine learning
uncertainty
geomagnetic indices forecasting
title Comment on “Prediction of the SYM‐H Index Using a Bayesian Deep Learning Method With Uncertainty Quantification” by Abduallah et al. (2024)
title_full Comment on “Prediction of the SYM‐H Index Using a Bayesian Deep Learning Method With Uncertainty Quantification” by Abduallah et al. (2024)
title_fullStr Comment on “Prediction of the SYM‐H Index Using a Bayesian Deep Learning Method With Uncertainty Quantification” by Abduallah et al. (2024)
title_full_unstemmed Comment on “Prediction of the SYM‐H Index Using a Bayesian Deep Learning Method With Uncertainty Quantification” by Abduallah et al. (2024)
title_short Comment on “Prediction of the SYM‐H Index Using a Bayesian Deep Learning Method With Uncertainty Quantification” by Abduallah et al. (2024)
title_sort comment on prediction of the sym h index using a bayesian deep learning method with uncertainty quantification by abduallah et al 2024
topic machine learning
uncertainty
geomagnetic indices forecasting
url https://doi.org/10.1029/2024SW003909
work_keys_str_mv AT armandocolladovillaverde commentonpredictionofthesymhindexusingabayesiandeeplearningmethodwithuncertaintyquantificationbyabduallahetal2024
AT pablomunoz commentonpredictionofthesymhindexusingabayesiandeeplearningmethodwithuncertaintyquantificationbyabduallahetal2024
AT consuelocid commentonpredictionofthesymhindexusingabayesiandeeplearningmethodwithuncertaintyquantificationbyabduallahetal2024