Prediction of geomagnetically induced currents in low-latitude regions using deep learning

Prediction of geomagnetically induced currents in low-latitude regions using deep learning

The present study proposes a geomagnetically induced currents (GICs) prediction model for three low-latitude locations, Huancayo, Peru, Addis Ababa, Ethiopia and Guam, United States. It employs the long short-term memory (LSTM) and bidirectional long short-term memory (BiLSTM) neural networks. The m...

Full description

Bibliographic Details
Published in:Current Science
Main Author: Zainuddin A.; Hairuddin M.A.; Latiff Z.I.A.; Anuar N.M.; Benavides I.F.; Jusoh M.H.; Yassin A.I.M.
Format: Article
Language:English
Published: Indian Academy of Sciences 2024
Online Access:https://www.scopus.com/inward/record.uri?eid=2-s2.0-85204877395&doi=10.18520%2fcs%2fv127%2fi6%2f691-700&partnerID=40&md5=6513b4c6848e5436c54410d9fd840cf3
id 2-s2.0-85204877395
spelling 2-s2.0-85204877395
Zainuddin A.; Hairuddin M.A.; Latiff Z.I.A.; Anuar N.M.; Benavides I.F.; Jusoh M.H.; Yassin A.I.M.
Prediction of geomagnetically induced currents in low-latitude regions using deep learning
2024
Current Science
127
6
10.18520/cs/v127/i6/691-700
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85204877395&doi=10.18520%2fcs%2fv127%2fi6%2f691-700&partnerID=40&md5=6513b4c6848e5436c54410d9fd840cf3
The present study proposes a geomagnetically induced currents (GICs) prediction model for three low-latitude locations, Huancayo, Peru, Addis Ababa, Ethiopia and Guam, United States. It employs the long short-term memory (LSTM) and bidirectional long short-term memory (BiLSTM) neural networks. The model’s performance was accessed using the interleaving odd-even data split (IntOE) approach as a benchmark. The geomagnetic field variation (dB/dt) derived from geomagnetic disturbance event on 31 March 2001, is applied as the GICs’ proxy. Results showed that employing both models, LSTM and BiLSTM with block division data split markedly enhanced prediction accuracy by up to 66% compared to IntOE. However, IntOE proves to be more effective for event-based validation. © (2024), (Indian Academy of Sciences). All Rights Reserved.
Indian Academy of Sciences
00113891
English
Article
author Zainuddin A.; Hairuddin M.A.; Latiff Z.I.A.; Anuar N.M.; Benavides I.F.; Jusoh M.H.; Yassin A.I.M.
spellingShingle Zainuddin A.; Hairuddin M.A.; Latiff Z.I.A.; Anuar N.M.; Benavides I.F.; Jusoh M.H.; Yassin A.I.M.
Prediction of geomagnetically induced currents in low-latitude regions using deep learning
author_facet Zainuddin A.; Hairuddin M.A.; Latiff Z.I.A.; Anuar N.M.; Benavides I.F.; Jusoh M.H.; Yassin A.I.M.
author_sort Zainuddin A.; Hairuddin M.A.; Latiff Z.I.A.; Anuar N.M.; Benavides I.F.; Jusoh M.H.; Yassin A.I.M.
title Prediction of geomagnetically induced currents in low-latitude regions using deep learning
title_short Prediction of geomagnetically induced currents in low-latitude regions using deep learning
title_full Prediction of geomagnetically induced currents in low-latitude regions using deep learning
title_fullStr Prediction of geomagnetically induced currents in low-latitude regions using deep learning
title_full_unstemmed Prediction of geomagnetically induced currents in low-latitude regions using deep learning
title_sort Prediction of geomagnetically induced currents in low-latitude regions using deep learning
publishDate 2024
container_title Current Science
container_volume 127
container_issue 6
doi_str_mv 10.18520/cs/v127/i6/691-700
url https://www.scopus.com/inward/record.uri?eid=2-s2.0-85204877395&doi=10.18520%2fcs%2fv127%2fi6%2f691-700&partnerID=40&md5=6513b4c6848e5436c54410d9fd840cf3
description The present study proposes a geomagnetically induced currents (GICs) prediction model for three low-latitude locations, Huancayo, Peru, Addis Ababa, Ethiopia and Guam, United States. It employs the long short-term memory (LSTM) and bidirectional long short-term memory (BiLSTM) neural networks. The model’s performance was accessed using the interleaving odd-even data split (IntOE) approach as a benchmark. The geomagnetic field variation (dB/dt) derived from geomagnetic disturbance event on 31 March 2001, is applied as the GICs’ proxy. Results showed that employing both models, LSTM and BiLSTM with block division data split markedly enhanced prediction accuracy by up to 66% compared to IntOE. However, IntOE proves to be more effective for event-based validation. © (2024), (Indian Academy of Sciences). All Rights Reserved.
publisher Indian Academy of Sciences
issn 00113891
language English
format Article
accesstype
record_format scopus
collection Scopus
_version_ 1814778502416695296

Similar Items