A Multi-Input Convolutional Neural Networks Model for Earthquake Precursor Detection Based on Ionospheric Total Electron Content
Earthquakes occur all around the world, causing varying degrees of damage and destruction. Earthquakes are by their very nature a sudden phenomenon and predicting them with a precise time range is difficult. Some phenomena may be indicators of physical conditions favorable for large earthquakes (e.g...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-12-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/24/5690 |
| _version_ | 1797379495882129408 |
|---|---|
| author | Hakan Uyanık Erman Şentürk Muhammed Halil Akpınar Salih T. A. Ozcelik Mehmet Kokum Mohamed Freeshah Abdulkadir Sengur |
| author_facet | Hakan Uyanık Erman Şentürk Muhammed Halil Akpınar Salih T. A. Ozcelik Mehmet Kokum Mohamed Freeshah Abdulkadir Sengur |
| author_sort | Hakan Uyanık |
| collection | DOAJ |
| description | Earthquakes occur all around the world, causing varying degrees of damage and destruction. Earthquakes are by their very nature a sudden phenomenon and predicting them with a precise time range is difficult. Some phenomena may be indicators of physical conditions favorable for large earthquakes (e.g., the ionospheric Total Electron Content (TEC)). The TEC is an important parameter used to detect pre-earthquake changes by measuring ionospheric disturbances and space weather indices, such as the global geomagnetic index (Kp), the storm duration distribution (Dst), the sunspot number (R), the geomagnetic storm index (Ap-index), the solar wind speed (Vsw), and the solar activity index (F10.7), have also been used to detect pre-earthquake ionospheric changes. In this study, the feasibility of the 6th-day earthquake prediction by the deep neural network technique using the previous five consecutive days is investigated. For this purpose, a two-staged approach is developed. In the first stage, various preprocessing steps, namely TEC signal improvement and time-frequency representation-based TEC image construction, are performed. In the second stage, a multi-input convolutional neural network (CNN) model is designed and trained in an end-to-end fashion. This multi-input CNN model has a total of six inputs, and five of the inputs are designed as 2D and the sixth is a 1D vector. The 2D inputs to the multi-input CNN model are TEC images and the vector input is concatenated space weather indices. The network branches with the 2D inputs contain convolution, batch normalization, and Rectified Linear Unit (ReLU) activation layers, and the branch with the 1D input contains a ReLU activation layer. The ReLU activation outputs of all the branches are flattened and then concatenated. And the classification is performed via fully connected, softmax, and classification layers, respectively. In the experimental work, earthquakes with a magnitude of M<sub>w</sub>5.0 and above that occurred in Turkey between 2012 and 2019 are used as the dataset. The TEC data were recorded by the Turkey National Permanent GNSS Network-Active (TNPGN-Active) Global Navigation Satellite System (GNSS) stations. The TEC data five days before the earthquake were marked as “precursor days” and the TEC data five days after the earthquake were marked as “normal days”. In total, 75% of the dataset is used to train the proposed method and 25% of the dataset is used for testing. The classification accuracy, sensitivity, specificity, and F1-score values are obtained for performance evaluations. The results are promising, and an 89.31% classification accuracy is obtained. |
| first_indexed | 2024-03-08T20:24:07Z |
| format | Article |
| id | doaj.art-6ae3f8874d544595b7a0f5af8b2bd589 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-08T20:24:07Z |
| publishDate | 2023-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-6ae3f8874d544595b7a0f5af8b2bd5892023-12-22T14:39:01ZengMDPI AGRemote Sensing2072-42922023-12-011524569010.3390/rs15245690A Multi-Input Convolutional Neural Networks Model for Earthquake Precursor Detection Based on Ionospheric Total Electron ContentHakan Uyanık0Erman Şentürk1Muhammed Halil Akpınar2Salih T. A. Ozcelik3Mehmet Kokum4Mohamed Freeshah5Abdulkadir Sengur6Electrical-Electronics Engineering Department, Engineering Faculty, Munzur University, Tunceli 62000, TurkeyDepartment of Geomatics Engineering, Kocaeli University, Kocaeli 41001, TurkeyDepartment of Electronics and Automation, Vocational School of Technical Sciences, Istanbul University-Cerrahpasa, Istanbul 34098, TurkeyElectrical-Electronics Engineering Department, Engineering Faculty, Bingol University, Bingol 12000, TurkeyGeological Engineering Department, Engineering Faculty, Firat University, Elazig 23119, TurkeySchool of Geodesy and Geomatics, Wuhan University, 129 Luoyu Road, Wuhan 430079, ChinaElectrical-Electronics Engineering Department, Technology Faculty, Firat University, Elazig 23119, TurkeyEarthquakes occur all around the world, causing varying degrees of damage and destruction. Earthquakes are by their very nature a sudden phenomenon and predicting them with a precise time range is difficult. Some phenomena may be indicators of physical conditions favorable for large earthquakes (e.g., the ionospheric Total Electron Content (TEC)). The TEC is an important parameter used to detect pre-earthquake changes by measuring ionospheric disturbances and space weather indices, such as the global geomagnetic index (Kp), the storm duration distribution (Dst), the sunspot number (R), the geomagnetic storm index (Ap-index), the solar wind speed (Vsw), and the solar activity index (F10.7), have also been used to detect pre-earthquake ionospheric changes. In this study, the feasibility of the 6th-day earthquake prediction by the deep neural network technique using the previous five consecutive days is investigated. For this purpose, a two-staged approach is developed. In the first stage, various preprocessing steps, namely TEC signal improvement and time-frequency representation-based TEC image construction, are performed. In the second stage, a multi-input convolutional neural network (CNN) model is designed and trained in an end-to-end fashion. This multi-input CNN model has a total of six inputs, and five of the inputs are designed as 2D and the sixth is a 1D vector. The 2D inputs to the multi-input CNN model are TEC images and the vector input is concatenated space weather indices. The network branches with the 2D inputs contain convolution, batch normalization, and Rectified Linear Unit (ReLU) activation layers, and the branch with the 1D input contains a ReLU activation layer. The ReLU activation outputs of all the branches are flattened and then concatenated. And the classification is performed via fully connected, softmax, and classification layers, respectively. In the experimental work, earthquakes with a magnitude of M<sub>w</sub>5.0 and above that occurred in Turkey between 2012 and 2019 are used as the dataset. The TEC data were recorded by the Turkey National Permanent GNSS Network-Active (TNPGN-Active) Global Navigation Satellite System (GNSS) stations. The TEC data five days before the earthquake were marked as “precursor days” and the TEC data five days after the earthquake were marked as “normal days”. In total, 75% of the dataset is used to train the proposed method and 25% of the dataset is used for testing. The classification accuracy, sensitivity, specificity, and F1-score values are obtained for performance evaluations. The results are promising, and an 89.31% classification accuracy is obtained.https://www.mdpi.com/2072-4292/15/24/5690TECspace weather indicesmulti-input CNNearthquake precursor predictionGNSS |
| spellingShingle | Hakan Uyanık Erman Şentürk Muhammed Halil Akpınar Salih T. A. Ozcelik Mehmet Kokum Mohamed Freeshah Abdulkadir Sengur A Multi-Input Convolutional Neural Networks Model for Earthquake Precursor Detection Based on Ionospheric Total Electron Content Remote Sensing TEC space weather indices multi-input CNN earthquake precursor prediction GNSS |
| title | A Multi-Input Convolutional Neural Networks Model for Earthquake Precursor Detection Based on Ionospheric Total Electron Content |
| title_full | A Multi-Input Convolutional Neural Networks Model for Earthquake Precursor Detection Based on Ionospheric Total Electron Content |
| title_fullStr | A Multi-Input Convolutional Neural Networks Model for Earthquake Precursor Detection Based on Ionospheric Total Electron Content |
| title_full_unstemmed | A Multi-Input Convolutional Neural Networks Model for Earthquake Precursor Detection Based on Ionospheric Total Electron Content |
| title_short | A Multi-Input Convolutional Neural Networks Model for Earthquake Precursor Detection Based on Ionospheric Total Electron Content |
| title_sort | multi input convolutional neural networks model for earthquake precursor detection based on ionospheric total electron content |
| topic | TEC space weather indices multi-input CNN earthquake precursor prediction GNSS |
| url | https://www.mdpi.com/2072-4292/15/24/5690 |
| work_keys_str_mv | AT hakanuyanık amultiinputconvolutionalneuralnetworksmodelforearthquakeprecursordetectionbasedonionospherictotalelectroncontent AT ermansenturk amultiinputconvolutionalneuralnetworksmodelforearthquakeprecursordetectionbasedonionospherictotalelectroncontent AT muhammedhalilakpınar amultiinputconvolutionalneuralnetworksmodelforearthquakeprecursordetectionbasedonionospherictotalelectroncontent AT salihtaozcelik amultiinputconvolutionalneuralnetworksmodelforearthquakeprecursordetectionbasedonionospherictotalelectroncontent AT mehmetkokum amultiinputconvolutionalneuralnetworksmodelforearthquakeprecursordetectionbasedonionospherictotalelectroncontent AT mohamedfreeshah amultiinputconvolutionalneuralnetworksmodelforearthquakeprecursordetectionbasedonionospherictotalelectroncontent AT abdulkadirsengur amultiinputconvolutionalneuralnetworksmodelforearthquakeprecursordetectionbasedonionospherictotalelectroncontent AT hakanuyanık multiinputconvolutionalneuralnetworksmodelforearthquakeprecursordetectionbasedonionospherictotalelectroncontent AT ermansenturk multiinputconvolutionalneuralnetworksmodelforearthquakeprecursordetectionbasedonionospherictotalelectroncontent AT muhammedhalilakpınar multiinputconvolutionalneuralnetworksmodelforearthquakeprecursordetectionbasedonionospherictotalelectroncontent AT salihtaozcelik multiinputconvolutionalneuralnetworksmodelforearthquakeprecursordetectionbasedonionospherictotalelectroncontent AT mehmetkokum multiinputconvolutionalneuralnetworksmodelforearthquakeprecursordetectionbasedonionospherictotalelectroncontent AT mohamedfreeshah multiinputconvolutionalneuralnetworksmodelforearthquakeprecursordetectionbasedonionospherictotalelectroncontent AT abdulkadirsengur multiinputconvolutionalneuralnetworksmodelforearthquakeprecursordetectionbasedonionospherictotalelectroncontent |