Research Article
BibTex RIS Cite

LSTM-Based Deep Learning Methods for Prediction of Earthquakes Using Ionospheric Data

Year 2022, Volume: 35 Issue: 4, 1417 - 1431, 01.12.2022
https://doi.org/10.35378/gujs.950387

Abstract

The ionosphere may play an essential role in the atmosphere and earth. Solar flares due to coronal mass ejection, seismic movements, and geomagnetic activity cause deviations in the ionosphere. The main parameter for investigating the structure of the ionosphere is Total Electron Content (TEC). TEC values obtained from GPS stations are a powerful technique for analyzing the ionospheric response to earthquakes and solar storms. This article analyzes the relations between earthquakes and TEC data to detect earthquakes. Our goal is to propose a prediction model to detect earthquakes in previous days. The ionospheric variability during moderate and severe earthquake events of varying strengths for 2012-2019 is discussed in this paper. The proposed models use LSTM-based (Long Short-Term Memory) deep learning models to classify earthquake days by analyzing TEC values of the last days. The LSTM-Based prediction models are compared against the SVM (Support Vector Machine), LDA (Linear Discriminant Analysis) classifier and Random Forest classifier to evaluate the proposed models based on earthquake prediction. The results reveal that the proposed models improve in detecting the earthquakes at an accuracy rate of about 0.82 and can be used as a successful tool for detecting earthquakes based on the previous days. 

Supporting Institution

TUBITAK IONOLAB

Thanks

TUBITAK IONOLAB

References

  • [1] Arikan, F., Erol, C., Arikan, O., “Regularized estimation of vertical total electron content from global positioning system data”, Journal of Geophysical Research Space Physics, A12, (2003).
  • [2] Nayir, H., Arikan, F., Arikan, O., Erol, C., “Total electron content estimation with Reg-Est”, Journal of Geophysical Research Space Physics, A11, (2007).
  • [3] Rishbeth, H., Garriott, K., “Introduction to ionospheric physics”, New York Academic Press, 14: 345-379, (1969).
  • [4] Pulinets, S., Ouzounov, D., Karelin, A., Davi-denko, D., “Lithosphere atmosphere ionosphere magnetosphere coupling a concept for pre-earthquake signals generation”, Pre-Earthquake Processes: A Multidisciplinary Approach to Earthquake Prediction Studies, 3: 79-99, (2018).
  • [5] Pulinets, S., Contreras, L., Bisiacchi-Giraldi, G., Ciraolo, L., “Total electron content variations in the ionosphere before the Colima, Mexico, earthquake of 21 January 2003”, Geofisica Internacional, 4: 369–377, (2005).
  • [6] Tao, D., Jinbin, C., Battiston, R., Li, L., Yuduan, M., Wenlong, L., Wang, L., Dunlop, W., “Seismo-ionospheric anomalies in ionospheric TEC and plasma density before the 17 July 2006 M7. 7 south of Java earthquake”, Annales Geophysicae, 35(3): 589-598, (2017).
  • [7] Arslan, T., Munawar, M., Pajares, H., Iqbal, T., “Pre-earthquake ionospheric anomalies before three major earthquakes by GPS-TEC and GIM-TEC data during 2015–2017”, Advances in Space Research, 7: 2088-2099, (2019).
  • [8] Biqiang, Z., Weixing, W., Libo, L., Tian, M., “Morphology in the total electron content under geomagnetic disturbed conditions: results from global ionosphere maps”, Annales Geophysicae, 7: 1555-1568, (2007).
  • [9] Trigunait, A., Parrot, M., Pulinets, S., Feng, L., “Variations of the ionospheric electron density during the Bhuj seismic event”, Annales Geophysicae, 12: 4123-4131, (2004).
  • [10] Liu, J., Chen, Y., Chuo, J., Chen, C., “A statistical investigation of pre-earthquake ionospheric anomaly”, Journal of Geophysical Research Space Physics, A5, (2006).
  • [11] Lopez-Paz, D., Sra, S., Smola, A., Ghahramani, Z., Scholkopf, B., “Randomized nonlinear component analysis”, International Conference on Machine Learning, 10: 1359-1367, (2014).
  • [12] Oikonomou, C., Haralambous, H., Muslim, B., “Investigation of ionospheric TEC precursors related to the M7. 8 Nepal and M8. 3 Chile earthquakes in 2015 based on spectral and statistical analysis”, Natural Hazards, 11: 97-116, (2016).
  • [13] Pundhir, D., Singh, B., Kumar, S., Gupta, S., Pathak, K., “Study of ionospheric precursors using GPS and GIM-TEC data related to earthquakes occurred on 16 April and 24 September 2013 in the Pakistan region”, Advances in Space Research, 9: 1978-1987, (2017).
  • [14] Huijun, L., Liu, J., Liu, L., “A statistical analysis of ionospheric anomalies before 736 M6. 0+ earthquakes during 2002–2010”, Journal of Geophysical Research Space Physics, 3: 87-102, (2011).
  • [15] Enlu, L., Chen, Q., Xiaoming, Q., “Deep reinforcement learning for imbalanced classification”, Applied Intelligence, 21: 1-15, (2020).
  • [16] Liu, J., Chuo, Y., Shan, S., Tsai, Y., Chen, I., Pulinets, A., Yu, S., “Pre-earthquake ionospheric anomalies registered by continuous GPS TEC measurements”, Annales Geophysicae, 22(5): 1585-1593, (2004).
  • [17] Liu, J., Chen, C., Chen, Y., Yang, W., Oyama, I., Kuo, W., “A statis-tical study of ionospheric earthquake precursors monitored by using equatorial ionization anomaly of GPS TEC in Taiwan during 2001–2007”, Journal of Asian Earth Sciences, 2: 76-80, (2010).
  • [18] Bendick, R., Bilham, R., “Do weak global stresses synchronize earthquakes?”, Geophysical Research Letters, 44(16): 8320-8327, (2017).
  • [19] Asencio-Cortes, G., “Improving earthquake prediction with principal component analysis: application to Chile”, International Conference on Hybrid Artificial Intelligence Systems, 3: 393-404, (2015).
  • [20] Mahmoudi, J., Arjomand, M., Rezaei, M., Mohammadi, M., “Predicting the earthquake magnitude using the multilayer perceptron neural network with two hidden layers”, Civil Engineering Journal, 2(1): 1-12, (2016).
  • [21] Moustra, M., Avraamides, M., Christodoulou, C., “Artificial neural networks for earthquake prediction using time series magnitude data or seismic electric signals”, Expert Systems with Applications, 38(12): 15032-15039, (2011).
  • [22] Gulyaeva, L., Arikan F., Stanislawska, I., “Persistent long-term (1944–2015) ionosphere-magnetosphere associations at the area of intense seismic activity and beyond”, Advances in Space Research, 59(4): 1033-1040, (2017).
  • [23] Oyama, K., Devi, M., Kwangsun Ryu, C., Chen, C., Liu, J., Bankov, L., Kodama, T., “Modifications of the ionosphere prior to large earthquakes: report from the Ionosphere Precursor Study Group”, Geoscience Letters, 3(1): 1-10, (2016).
  • [24] Fidani, C., “The earthquake lights (EQL) of the 6 April 2009 Aquila earthquake, in Central Italy”, Natural Hazards and Earth System Sciences, 10(5): 967-978, (2010).
  • [25] Grant, A., Halliday, T., “Predicting the unpredictable; evidence of pre‐seismic anticipatory behaviour in the common toad”, Journal of Zoology, 281(4): 263-271, (2010).
  • [26] Akhoondzadeh, M., “Decision Tree, Bagging and Random Forest methods detect TEC seismo-ionospheric anomalies around the time of Chile, (Mw= 8.8) earthquake of 27 February 2010”, Advances in Space Research, 57(12): 2464-2469, (2016).
  • [27] Davidenko, V., Pulinets, S., “Deterministic variability of the ionosphere on the eve of strong (M≥ 6) earthquakes in the regions of Greece and Italy according to long-term measurements data”, Geomagnetism and Aeronomy, 59(4): 493-508, (2019).
  • [28] Li, W., Jinyun, G., Jianping, Y., Yang, Y., Zhen, L., Deikai, L., “Contrastive research of ionospheric precursor anomalies between Calbuco volcanic eruption on April 23 and Nepal earthquake on April 25, 2015”, Advances in Space Research, 57(10): 2141-2153, (2016).
  • [29] Akyol, A., Arikan, O., Arikan, F., Deviren, M., “Investigation on the reliability of earthquake prediction based on ionospheric electron content variation”, 16th International Conference on Information Fusion, 1658-1663, (2013).
  • [30] Arikan, O., Arikan, F., Akyol, A., “Machine learning based detection of earthquake precursors using ionospheric data”, 42nd COSPAR Scientific Assembly, 42, (2018).
  • [31] Aji, B., Houw, L., Buldan, M., “Detection precursor of sumatra earthquake based on ionospheric total electron content anomalies using N-Model Articial Neural Network”, International Conference on Advanced Computer Science and Information Systems (ICACSIS), 269-276, (2017).
  • [32] Nowakowski, A., Chris, S., Lorenzo, T., Floberghagen, R., Kilbane-Dawe, I., “A machine learning approach to investigate possible signals in the ionosphere related to earthquake activity”, Geophysical Research Abstracts, 21, (2019).
  • [33] Muslim, B., “Examination of Correlation Technique for Detecting The influence Of Great Earthquake Activities on Ionosphere”, Jurnal Sains Dirgantara, 12(2): (2015).
  • [34] Akhoondzadeh, M., “Genetic algorithm for TEC seismo-ionospheric anomalies detection around the time of the Solomon (Mw= 8.0) earthquake of 06 February 2013”, Advances in Space Research, 52(4): 581-590, (2013).
  • [35] Akhoondzadeh, M., “Investigation of GPS-TEC measurements using ANN method indicating seismo-ionospheric anomalies around the time of the Chile (Mw= 8.2) earthquake of 01 April 2014”, Advances in Space Research, 54(9): 1768-1772, (2014).
  • [36] Reid, J., Jeffrey, L., Bhavani, A., “QuakeCast, an Earthquake Forecasting System Using Ionospheric Anomalies and Machine Learning”, AGU Fall Meeting Abstracts, NH007-0016, (2020).
  • [37] Schuster, M., Paliwal, K., “Bidirectional recurrent neural networks”, IEEE Transactions on Signal Processing, 45(11): 2673-2681, (1997).
  • [38] Pascanu, R., Gulcehre C., Kyunghyun, C., Bengio, Y., “How to construct deep recurrent neural networks”, ArXiv Preprint ArXiv:1312.6026, (2013).
  • [39] Munawar, S., Shuanggen, J., “Statistical characteristics of seismo-ionospheric GPS TEC disturbances prior to global Mw≥5.0 earthquakes (1998–2014)”, Journal of Geodynamics, 5: 42-49, (2015).
  • [40] Sharma, A., Paliwal, K., “Linear discriminant analysis for the small sample size problem: an overview”, International Journal of Machine Learning and Cybernetics, 3: 443-454, (2015).
  • [41] Tharwat, A., Gaber, T., Ibrahim, A., Hassanien, A., “Linear discriminant analysis: A detailed tutorial”, AI communications, 30(2): 169-190, (2017).
  • [42] Abri, R., "Modeling of the ionosphere's disturbance using deep learning techniques”, PhD. Thesis, Hacettepe University, Graduate School of Science and Engineering, Ankara, (2021).
Year 2022, Volume: 35 Issue: 4, 1417 - 1431, 01.12.2022
https://doi.org/10.35378/gujs.950387

Abstract

References

  • [1] Arikan, F., Erol, C., Arikan, O., “Regularized estimation of vertical total electron content from global positioning system data”, Journal of Geophysical Research Space Physics, A12, (2003).
  • [2] Nayir, H., Arikan, F., Arikan, O., Erol, C., “Total electron content estimation with Reg-Est”, Journal of Geophysical Research Space Physics, A11, (2007).
  • [3] Rishbeth, H., Garriott, K., “Introduction to ionospheric physics”, New York Academic Press, 14: 345-379, (1969).
  • [4] Pulinets, S., Ouzounov, D., Karelin, A., Davi-denko, D., “Lithosphere atmosphere ionosphere magnetosphere coupling a concept for pre-earthquake signals generation”, Pre-Earthquake Processes: A Multidisciplinary Approach to Earthquake Prediction Studies, 3: 79-99, (2018).
  • [5] Pulinets, S., Contreras, L., Bisiacchi-Giraldi, G., Ciraolo, L., “Total electron content variations in the ionosphere before the Colima, Mexico, earthquake of 21 January 2003”, Geofisica Internacional, 4: 369–377, (2005).
  • [6] Tao, D., Jinbin, C., Battiston, R., Li, L., Yuduan, M., Wenlong, L., Wang, L., Dunlop, W., “Seismo-ionospheric anomalies in ionospheric TEC and plasma density before the 17 July 2006 M7. 7 south of Java earthquake”, Annales Geophysicae, 35(3): 589-598, (2017).
  • [7] Arslan, T., Munawar, M., Pajares, H., Iqbal, T., “Pre-earthquake ionospheric anomalies before three major earthquakes by GPS-TEC and GIM-TEC data during 2015–2017”, Advances in Space Research, 7: 2088-2099, (2019).
  • [8] Biqiang, Z., Weixing, W., Libo, L., Tian, M., “Morphology in the total electron content under geomagnetic disturbed conditions: results from global ionosphere maps”, Annales Geophysicae, 7: 1555-1568, (2007).
  • [9] Trigunait, A., Parrot, M., Pulinets, S., Feng, L., “Variations of the ionospheric electron density during the Bhuj seismic event”, Annales Geophysicae, 12: 4123-4131, (2004).
  • [10] Liu, J., Chen, Y., Chuo, J., Chen, C., “A statistical investigation of pre-earthquake ionospheric anomaly”, Journal of Geophysical Research Space Physics, A5, (2006).
  • [11] Lopez-Paz, D., Sra, S., Smola, A., Ghahramani, Z., Scholkopf, B., “Randomized nonlinear component analysis”, International Conference on Machine Learning, 10: 1359-1367, (2014).
  • [12] Oikonomou, C., Haralambous, H., Muslim, B., “Investigation of ionospheric TEC precursors related to the M7. 8 Nepal and M8. 3 Chile earthquakes in 2015 based on spectral and statistical analysis”, Natural Hazards, 11: 97-116, (2016).
  • [13] Pundhir, D., Singh, B., Kumar, S., Gupta, S., Pathak, K., “Study of ionospheric precursors using GPS and GIM-TEC data related to earthquakes occurred on 16 April and 24 September 2013 in the Pakistan region”, Advances in Space Research, 9: 1978-1987, (2017).
  • [14] Huijun, L., Liu, J., Liu, L., “A statistical analysis of ionospheric anomalies before 736 M6. 0+ earthquakes during 2002–2010”, Journal of Geophysical Research Space Physics, 3: 87-102, (2011).
  • [15] Enlu, L., Chen, Q., Xiaoming, Q., “Deep reinforcement learning for imbalanced classification”, Applied Intelligence, 21: 1-15, (2020).
  • [16] Liu, J., Chuo, Y., Shan, S., Tsai, Y., Chen, I., Pulinets, A., Yu, S., “Pre-earthquake ionospheric anomalies registered by continuous GPS TEC measurements”, Annales Geophysicae, 22(5): 1585-1593, (2004).
  • [17] Liu, J., Chen, C., Chen, Y., Yang, W., Oyama, I., Kuo, W., “A statis-tical study of ionospheric earthquake precursors monitored by using equatorial ionization anomaly of GPS TEC in Taiwan during 2001–2007”, Journal of Asian Earth Sciences, 2: 76-80, (2010).
  • [18] Bendick, R., Bilham, R., “Do weak global stresses synchronize earthquakes?”, Geophysical Research Letters, 44(16): 8320-8327, (2017).
  • [19] Asencio-Cortes, G., “Improving earthquake prediction with principal component analysis: application to Chile”, International Conference on Hybrid Artificial Intelligence Systems, 3: 393-404, (2015).
  • [20] Mahmoudi, J., Arjomand, M., Rezaei, M., Mohammadi, M., “Predicting the earthquake magnitude using the multilayer perceptron neural network with two hidden layers”, Civil Engineering Journal, 2(1): 1-12, (2016).
  • [21] Moustra, M., Avraamides, M., Christodoulou, C., “Artificial neural networks for earthquake prediction using time series magnitude data or seismic electric signals”, Expert Systems with Applications, 38(12): 15032-15039, (2011).
  • [22] Gulyaeva, L., Arikan F., Stanislawska, I., “Persistent long-term (1944–2015) ionosphere-magnetosphere associations at the area of intense seismic activity and beyond”, Advances in Space Research, 59(4): 1033-1040, (2017).
  • [23] Oyama, K., Devi, M., Kwangsun Ryu, C., Chen, C., Liu, J., Bankov, L., Kodama, T., “Modifications of the ionosphere prior to large earthquakes: report from the Ionosphere Precursor Study Group”, Geoscience Letters, 3(1): 1-10, (2016).
  • [24] Fidani, C., “The earthquake lights (EQL) of the 6 April 2009 Aquila earthquake, in Central Italy”, Natural Hazards and Earth System Sciences, 10(5): 967-978, (2010).
  • [25] Grant, A., Halliday, T., “Predicting the unpredictable; evidence of pre‐seismic anticipatory behaviour in the common toad”, Journal of Zoology, 281(4): 263-271, (2010).
  • [26] Akhoondzadeh, M., “Decision Tree, Bagging and Random Forest methods detect TEC seismo-ionospheric anomalies around the time of Chile, (Mw= 8.8) earthquake of 27 February 2010”, Advances in Space Research, 57(12): 2464-2469, (2016).
  • [27] Davidenko, V., Pulinets, S., “Deterministic variability of the ionosphere on the eve of strong (M≥ 6) earthquakes in the regions of Greece and Italy according to long-term measurements data”, Geomagnetism and Aeronomy, 59(4): 493-508, (2019).
  • [28] Li, W., Jinyun, G., Jianping, Y., Yang, Y., Zhen, L., Deikai, L., “Contrastive research of ionospheric precursor anomalies between Calbuco volcanic eruption on April 23 and Nepal earthquake on April 25, 2015”, Advances in Space Research, 57(10): 2141-2153, (2016).
  • [29] Akyol, A., Arikan, O., Arikan, F., Deviren, M., “Investigation on the reliability of earthquake prediction based on ionospheric electron content variation”, 16th International Conference on Information Fusion, 1658-1663, (2013).
  • [30] Arikan, O., Arikan, F., Akyol, A., “Machine learning based detection of earthquake precursors using ionospheric data”, 42nd COSPAR Scientific Assembly, 42, (2018).
  • [31] Aji, B., Houw, L., Buldan, M., “Detection precursor of sumatra earthquake based on ionospheric total electron content anomalies using N-Model Articial Neural Network”, International Conference on Advanced Computer Science and Information Systems (ICACSIS), 269-276, (2017).
  • [32] Nowakowski, A., Chris, S., Lorenzo, T., Floberghagen, R., Kilbane-Dawe, I., “A machine learning approach to investigate possible signals in the ionosphere related to earthquake activity”, Geophysical Research Abstracts, 21, (2019).
  • [33] Muslim, B., “Examination of Correlation Technique for Detecting The influence Of Great Earthquake Activities on Ionosphere”, Jurnal Sains Dirgantara, 12(2): (2015).
  • [34] Akhoondzadeh, M., “Genetic algorithm for TEC seismo-ionospheric anomalies detection around the time of the Solomon (Mw= 8.0) earthquake of 06 February 2013”, Advances in Space Research, 52(4): 581-590, (2013).
  • [35] Akhoondzadeh, M., “Investigation of GPS-TEC measurements using ANN method indicating seismo-ionospheric anomalies around the time of the Chile (Mw= 8.2) earthquake of 01 April 2014”, Advances in Space Research, 54(9): 1768-1772, (2014).
  • [36] Reid, J., Jeffrey, L., Bhavani, A., “QuakeCast, an Earthquake Forecasting System Using Ionospheric Anomalies and Machine Learning”, AGU Fall Meeting Abstracts, NH007-0016, (2020).
  • [37] Schuster, M., Paliwal, K., “Bidirectional recurrent neural networks”, IEEE Transactions on Signal Processing, 45(11): 2673-2681, (1997).
  • [38] Pascanu, R., Gulcehre C., Kyunghyun, C., Bengio, Y., “How to construct deep recurrent neural networks”, ArXiv Preprint ArXiv:1312.6026, (2013).
  • [39] Munawar, S., Shuanggen, J., “Statistical characteristics of seismo-ionospheric GPS TEC disturbances prior to global Mw≥5.0 earthquakes (1998–2014)”, Journal of Geodynamics, 5: 42-49, (2015).
  • [40] Sharma, A., Paliwal, K., “Linear discriminant analysis for the small sample size problem: an overview”, International Journal of Machine Learning and Cybernetics, 3: 443-454, (2015).
  • [41] Tharwat, A., Gaber, T., Ibrahim, A., Hassanien, A., “Linear discriminant analysis: A detailed tutorial”, AI communications, 30(2): 169-190, (2017).
  • [42] Abri, R., "Modeling of the ionosphere's disturbance using deep learning techniques”, PhD. Thesis, Hacettepe University, Graduate School of Science and Engineering, Ankara, (2021).
There are 42 citations in total.

Details

Primary Language English
Subjects Engineering
Journal Section Electrical & Electronics Engineering
Authors

Rayan Abri 0000-0002-2787-2832

Harun Artuner

Publication Date December 1, 2022
Published in Issue Year 2022 Volume: 35 Issue: 4

Cite

APA Abri, R., & Artuner, H. (2022). LSTM-Based Deep Learning Methods for Prediction of Earthquakes Using Ionospheric Data. Gazi University Journal of Science, 35(4), 1417-1431. https://doi.org/10.35378/gujs.950387
AMA Abri R, Artuner H. LSTM-Based Deep Learning Methods for Prediction of Earthquakes Using Ionospheric Data. Gazi University Journal of Science. December 2022;35(4):1417-1431. doi:10.35378/gujs.950387
Chicago Abri, Rayan, and Harun Artuner. “LSTM-Based Deep Learning Methods for Prediction of Earthquakes Using Ionospheric Data”. Gazi University Journal of Science 35, no. 4 (December 2022): 1417-31. https://doi.org/10.35378/gujs.950387.
EndNote Abri R, Artuner H (December 1, 2022) LSTM-Based Deep Learning Methods for Prediction of Earthquakes Using Ionospheric Data. Gazi University Journal of Science 35 4 1417–1431.
IEEE R. Abri and H. Artuner, “LSTM-Based Deep Learning Methods for Prediction of Earthquakes Using Ionospheric Data”, Gazi University Journal of Science, vol. 35, no. 4, pp. 1417–1431, 2022, doi: 10.35378/gujs.950387.
ISNAD Abri, Rayan - Artuner, Harun. “LSTM-Based Deep Learning Methods for Prediction of Earthquakes Using Ionospheric Data”. Gazi University Journal of Science 35/4 (December 2022), 1417-1431. https://doi.org/10.35378/gujs.950387.
JAMA Abri R, Artuner H. LSTM-Based Deep Learning Methods for Prediction of Earthquakes Using Ionospheric Data. Gazi University Journal of Science. 2022;35:1417–1431.
MLA Abri, Rayan and Harun Artuner. “LSTM-Based Deep Learning Methods for Prediction of Earthquakes Using Ionospheric Data”. Gazi University Journal of Science, vol. 35, no. 4, 2022, pp. 1417-31, doi:10.35378/gujs.950387.
Vancouver Abri R, Artuner H. LSTM-Based Deep Learning Methods for Prediction of Earthquakes Using Ionospheric Data. Gazi University Journal of Science. 2022;35(4):1417-31.