Interpretable N-BEATS deep networks of multistep forecasting for the ground-based geomagnetic Dst index

The importance of geomagnetic disturbances represented by ground earth activities based on the disturbance storm time (Dst index) entails an early forecast of geomagnetic storm occurrence, which could potentially disrupt the system operations. Often, the forecast outcome serves as an essential indic...

Full description

Bibliographic Details
Main Authors: Mashohor, Syamsiah, Khirul Ashar, Nur Dalila, Sali, Aduwati, Jusoh, Mohamad Huzaimy, Yoshikawa, Akimasa, Abdul Latiff, Zatul Iffah, Hairuddin, Muhammad Asraf
Format: Article
Language:English
Published: I C I C International 2024
Online Access:http://psasir.upm.edu.my/id/eprint/117849/
http://psasir.upm.edu.my/id/eprint/117849/1/117849.pdf
_version_ 1848867359815630848
author Mashohor, Syamsiah
Khirul Ashar, Nur Dalila
Sali, Aduwati
Jusoh, Mohamad Huzaimy
Yoshikawa, Akimasa
Abdul Latiff, Zatul Iffah
Hairuddin, Muhammad Asraf
author_facet Mashohor, Syamsiah
Khirul Ashar, Nur Dalila
Sali, Aduwati
Jusoh, Mohamad Huzaimy
Yoshikawa, Akimasa
Abdul Latiff, Zatul Iffah
Hairuddin, Muhammad Asraf
author_sort Mashohor, Syamsiah
building UPM Institutional Repository
collection Online Access
description The importance of geomagnetic disturbances represented by ground earth activities based on the disturbance storm time (Dst index) entails an early forecast of geomagnetic storm occurrence, which could potentially disrupt the system operations. Often, the forecast outcome serves as an essential indicator for operational users who not only require early forecasting prior to incoming geomagnetic storms but also intend to obtain explainable insight and understanding of the generated forecast results. Therefore, a new model architecture, namely neural-basis expansion analysis for interpretable time series (N-BEATS), is proposed that incorporates a more transparent architecture of the deep learning model into producing the multiple steps ahead forecasting of the Dst index. Extensive comparisons among several deep learning models, namely long short-term memory (LSTM), gated recurrent units (GRU), and bidirectional GRU(Bi-GRU) network architectures, will be assessed, considering the model performances, and the impact of forecast variability will be discussed. The superiority of N-BEATS overcomes the state-of-the-art LSTM forecast model in terms of computational resources, and the effectiveness of learning the data of the Dst index pattern could be observed.
first_indexed 2025-11-15T14:35:15Z
format Article
id upm-117849
institution Universiti Putra Malaysia
institution_category Local University
language English
last_indexed 2025-11-15T14:35:15Z
publishDate 2024
publisher I C I C International
recordtype eprints
repository_type Digital Repository
spelling upm-1178492025-06-13T03:43:24Z http://psasir.upm.edu.my/id/eprint/117849/ Interpretable N-BEATS deep networks of multistep forecasting for the ground-based geomagnetic Dst index Mashohor, Syamsiah Khirul Ashar, Nur Dalila Sali, Aduwati Jusoh, Mohamad Huzaimy Yoshikawa, Akimasa Abdul Latiff, Zatul Iffah Hairuddin, Muhammad Asraf The importance of geomagnetic disturbances represented by ground earth activities based on the disturbance storm time (Dst index) entails an early forecast of geomagnetic storm occurrence, which could potentially disrupt the system operations. Often, the forecast outcome serves as an essential indicator for operational users who not only require early forecasting prior to incoming geomagnetic storms but also intend to obtain explainable insight and understanding of the generated forecast results. Therefore, a new model architecture, namely neural-basis expansion analysis for interpretable time series (N-BEATS), is proposed that incorporates a more transparent architecture of the deep learning model into producing the multiple steps ahead forecasting of the Dst index. Extensive comparisons among several deep learning models, namely long short-term memory (LSTM), gated recurrent units (GRU), and bidirectional GRU(Bi-GRU) network architectures, will be assessed, considering the model performances, and the impact of forecast variability will be discussed. The superiority of N-BEATS overcomes the state-of-the-art LSTM forecast model in terms of computational resources, and the effectiveness of learning the data of the Dst index pattern could be observed. I C I C International 2024 Article PeerReviewed text en http://psasir.upm.edu.my/id/eprint/117849/1/117849.pdf Mashohor, Syamsiah and Khirul Ashar, Nur Dalila and Sali, Aduwati and Jusoh, Mohamad Huzaimy and Yoshikawa, Akimasa and Abdul Latiff, Zatul Iffah and Hairuddin, Muhammad Asraf (2024) Interpretable N-BEATS deep networks of multistep forecasting for the ground-based geomagnetic Dst index. ICIC Express Letters, 19 (5). pp. 485-496. ISSN 1881-803X http://www.icicel.org/ell/contents/2025/5/el-19-05-02.pdf
spellingShingle Mashohor, Syamsiah
Khirul Ashar, Nur Dalila
Sali, Aduwati
Jusoh, Mohamad Huzaimy
Yoshikawa, Akimasa
Abdul Latiff, Zatul Iffah
Hairuddin, Muhammad Asraf
Interpretable N-BEATS deep networks of multistep forecasting for the ground-based geomagnetic Dst index
title Interpretable N-BEATS deep networks of multistep forecasting for the ground-based geomagnetic Dst index
title_full Interpretable N-BEATS deep networks of multistep forecasting for the ground-based geomagnetic Dst index
title_fullStr Interpretable N-BEATS deep networks of multistep forecasting for the ground-based geomagnetic Dst index
title_full_unstemmed Interpretable N-BEATS deep networks of multistep forecasting for the ground-based geomagnetic Dst index
title_short Interpretable N-BEATS deep networks of multistep forecasting for the ground-based geomagnetic Dst index
title_sort interpretable n-beats deep networks of multistep forecasting for the ground-based geomagnetic dst index
url http://psasir.upm.edu.my/id/eprint/117849/
http://psasir.upm.edu.my/id/eprint/117849/
http://psasir.upm.edu.my/id/eprint/117849/1/117849.pdf