Seismic Foresight: A Novel Multi-Input 1D Convolutional Mixer Model for Earthquake Prediction Using Ionospheric Signals

This study proposes a novel deep learning approach for predicting significant earthquakes (Mw <inline-formula> <tex-math notation="LaTeX">$\ge 5.0$ </tex-math></inline-formula>) in Turkey using ionospheric Total Electron Content (TEC) data and space weather indices....

Full description

Saved in:
Bibliographic Details
Main Authors: Hakan Uyanik, Mehmet Kokum, Erman Senturk, Mohamed Freeshah, Salih T. A. Ozcelik, Muhammed Halil Akpinar, Serenay Celik, Abdulkadir Sengur
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11053753/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849321328104964096
author Hakan Uyanik
Mehmet Kokum
Erman Senturk
Mohamed Freeshah
Salih T. A. Ozcelik
Muhammed Halil Akpinar
Serenay Celik
Abdulkadir Sengur
author_facet Hakan Uyanik
Mehmet Kokum
Erman Senturk
Mohamed Freeshah
Salih T. A. Ozcelik
Muhammed Halil Akpinar
Serenay Celik
Abdulkadir Sengur
author_sort Hakan Uyanik
collection DOAJ
description This study proposes a novel deep learning approach for predicting significant earthquakes (Mw <inline-formula> <tex-math notation="LaTeX">$\ge 5.0$ </tex-math></inline-formula>) in Turkey using ionospheric Total Electron Content (TEC) data and space weather indices. ConvMixer is a lightweight CNN architecture that blends spatial and channel information using depthwise convolutions and pointwise layers. Inspired by vision transformers, it offers efficient image classification with fewer parameters and high performance. We developed a multi-input one-dimensional convolutional mixer (MI-1D-ConvMixer) model to classify TEC data from the preceding five consecutive days as either precursory to an earthquake on the 6th day or normal. The model incorporates six inputs: five 1D TEC signals and one 1D space-weather index array, including the global geomagnetic index (Kp), storm duration distribution (Dst), sunspot number (R), geomagnetic storm index (Ap-index), solar wind speed (Vsw), and solar activity index (F10.7) are also utilized to reveal non-seismic related pre-earthquake ionospheric variations. Our methodology involves two stages: 1) a preprocessing stage to enhance TEC signals and 2) an end-to-end training of the MI-1D-ConvMixer model. The model architecture features depth-wise and point-wise convolutions with patch embedding, utilizing uses four tunable hyperparameters: network depth, hidden dimension size, kernel size, and patch size. We used 196 earthquakes data from Turkey from 2010-2023, and TEC data from the TNPGN-Active GNSS stations. The dataset was split into 75% for training and 25% for testing. Performance metrics, including classification accuracy, sensitivity, specificity, and F1-score, are used for evaluation. Our model achieved a classification accuracy of 97.49%, demonstrating its potential for earthquake prediction systems. This research contributes to the field by introducing a novel deep learning architecture specifically designed for integrating TEC and space weather data for earthquake prediction. Future work should focus on validating the model&#x2019;s performance in different geographical regions and investigating its limitations.
format Article
id doaj-art-663cb68e76994431bd60656e9ce0f9b4
institution Kabale University
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-663cb68e76994431bd60656e9ce0f9b42025-08-20T03:49:46ZengIEEEIEEE Access2169-35362025-01-011311620011621010.1109/ACCESS.2025.358374911053753Seismic Foresight: A Novel Multi-Input 1D Convolutional Mixer Model for Earthquake Prediction Using Ionospheric SignalsHakan Uyanik0https://orcid.org/0000-0002-6870-7569Mehmet Kokum1https://orcid.org/0000-0001-5149-3931Erman Senturk2Mohamed Freeshah3https://orcid.org/0000-0003-3539-7450Salih T. A. Ozcelik4https://orcid.org/0000-0002-7929-7542Muhammed Halil Akpinar5https://orcid.org/0000-0001-7563-0937Serenay Celik6Abdulkadir Sengur7https://orcid.org/0000-0003-1614-2639Electrical-Electronics Engineering Department, Engineering Faculty, Munzur University, Tunceli, T&#x00FC;rkiyeGeological Engineering Department, Engineering Faculty, F&#x0131;rat University, El&#x00E2;z&#x011F;, T&#x00FC;rkiyeDepartment of Geomatics, Kocaeli University, &#x0130;zmit, T&#x00FC;rkiyeCivil and Environmental Engineering Department, College of Engineering, UAE University, Al Ain, United Arab EmiratesElectrical-Electronics Engineering Department, Engineering Faculty, Bingol University, Bing&#x00F6;l, T&#x00FC;rkiyeDepartment of Electronics and Automation, Vocational School of Technical Sciences, Istanbul University-Cerrahpa&#x015F;a, Istanbul, T&#x00FC;rkiyeElectrical-Electronics Engineering Department, Technology Faculty, F&#x0131;rat University, El&#x00E2;z&#x011F;, T&#x00FC;rkiyeElectrical-Electronics Engineering Department, Technology Faculty, F&#x0131;rat University, El&#x00E2;z&#x011F;, T&#x00FC;rkiyeThis study proposes a novel deep learning approach for predicting significant earthquakes (Mw <inline-formula> <tex-math notation="LaTeX">$\ge 5.0$ </tex-math></inline-formula>) in Turkey using ionospheric Total Electron Content (TEC) data and space weather indices. ConvMixer is a lightweight CNN architecture that blends spatial and channel information using depthwise convolutions and pointwise layers. Inspired by vision transformers, it offers efficient image classification with fewer parameters and high performance. We developed a multi-input one-dimensional convolutional mixer (MI-1D-ConvMixer) model to classify TEC data from the preceding five consecutive days as either precursory to an earthquake on the 6th day or normal. The model incorporates six inputs: five 1D TEC signals and one 1D space-weather index array, including the global geomagnetic index (Kp), storm duration distribution (Dst), sunspot number (R), geomagnetic storm index (Ap-index), solar wind speed (Vsw), and solar activity index (F10.7) are also utilized to reveal non-seismic related pre-earthquake ionospheric variations. Our methodology involves two stages: 1) a preprocessing stage to enhance TEC signals and 2) an end-to-end training of the MI-1D-ConvMixer model. The model architecture features depth-wise and point-wise convolutions with patch embedding, utilizing uses four tunable hyperparameters: network depth, hidden dimension size, kernel size, and patch size. We used 196 earthquakes data from Turkey from 2010-2023, and TEC data from the TNPGN-Active GNSS stations. The dataset was split into 75% for training and 25% for testing. Performance metrics, including classification accuracy, sensitivity, specificity, and F1-score, are used for evaluation. Our model achieved a classification accuracy of 97.49%, demonstrating its potential for earthquake prediction systems. This research contributes to the field by introducing a novel deep learning architecture specifically designed for integrating TEC and space weather data for earthquake prediction. Future work should focus on validating the model&#x2019;s performance in different geographical regions and investigating its limitations.https://ieeexplore.ieee.org/document/11053753/TEC signalsEarthquake precursorspace-weather indicesmulti-input deep networksConvMixers
spellingShingle Hakan Uyanik
Mehmet Kokum
Erman Senturk
Mohamed Freeshah
Salih T. A. Ozcelik
Muhammed Halil Akpinar
Serenay Celik
Abdulkadir Sengur
Seismic Foresight: A Novel Multi-Input 1D Convolutional Mixer Model for Earthquake Prediction Using Ionospheric Signals
IEEE Access
TEC signals
Earthquake precursor
space-weather indices
multi-input deep networks
ConvMixers
title Seismic Foresight: A Novel Multi-Input 1D Convolutional Mixer Model for Earthquake Prediction Using Ionospheric Signals
title_full Seismic Foresight: A Novel Multi-Input 1D Convolutional Mixer Model for Earthquake Prediction Using Ionospheric Signals
title_fullStr Seismic Foresight: A Novel Multi-Input 1D Convolutional Mixer Model for Earthquake Prediction Using Ionospheric Signals
title_full_unstemmed Seismic Foresight: A Novel Multi-Input 1D Convolutional Mixer Model for Earthquake Prediction Using Ionospheric Signals
title_short Seismic Foresight: A Novel Multi-Input 1D Convolutional Mixer Model for Earthquake Prediction Using Ionospheric Signals
title_sort seismic foresight a novel multi input 1d convolutional mixer model for earthquake prediction using ionospheric signals
topic TEC signals
Earthquake precursor
space-weather indices
multi-input deep networks
ConvMixers
url https://ieeexplore.ieee.org/document/11053753/
work_keys_str_mv AT hakanuyanik seismicforesightanovelmultiinput1dconvolutionalmixermodelforearthquakepredictionusingionosphericsignals
AT mehmetkokum seismicforesightanovelmultiinput1dconvolutionalmixermodelforearthquakepredictionusingionosphericsignals
AT ermansenturk seismicforesightanovelmultiinput1dconvolutionalmixermodelforearthquakepredictionusingionosphericsignals
AT mohamedfreeshah seismicforesightanovelmultiinput1dconvolutionalmixermodelforearthquakepredictionusingionosphericsignals
AT salihtaozcelik seismicforesightanovelmultiinput1dconvolutionalmixermodelforearthquakepredictionusingionosphericsignals
AT muhammedhalilakpinar seismicforesightanovelmultiinput1dconvolutionalmixermodelforearthquakepredictionusingionosphericsignals
AT serenaycelik seismicforesightanovelmultiinput1dconvolutionalmixermodelforearthquakepredictionusingionosphericsignals
AT abdulkadirsengur seismicforesightanovelmultiinput1dconvolutionalmixermodelforearthquakepredictionusingionosphericsignals