ISSN 2070-7401 (Print), ISSN 2411-0280 (Online)
Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa
CURRENT PROBLEMS IN REMOTE SENSING OF THE EARTH FROM SPACE

  

Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2023, Vol. 20, No. 1, pp. 37-54

Application of machine learning methods for detection of covolcanic ionospheric disturbances by GNSS observations data

A.S. Ten 1 , N.V. Shestakov 2, 3 , A.А. Sorokin 1 , N.N. Titkov 4 , M. Ohzono 5 , H. Takahashi 6 
1 Computing Center FEB RAS, Khabarovsk, Russia
2 Institute of Applied Mathematics FEB RAS, Vladivostok, Russia
3 Far Eastern Federal University, Vladivostok, Russia
4 Kamchatka Branch of the Geophysical Survey RAS, Petropavlovsk-Kamchatsky, Russia
5 University of Tokyo, Tokyo, Japan
6 Hokkaido University, Sapporo, Japan
Accepted: 19.01.2023
DOI: 10.21046/2070-7401-2023-20-1-37-54
The work is devoted to the evaluation of the possibility of using artificial neural networks to detect covolcanic ionospheric disturbances in the time series of the total electronic content obtained from GNSS observations. Using the example of the Sarychev Peak volcano eruption on June 11–16, 2009, instrumental GNSS data were processed and labeled, their datasets with different sample sizes and two classes — with and without disturbances — were generated. Based on this information, five artificial neural networks of various architectures used to solve the problem of time series classification were trained and investigated. The quality metrics of classification of neural networks are calculated and their comparison is carried out. The results of testing the proposed algorithm with different classifiers — neural networks that showed the best result, namely InceptionTime and ResNet, were obtained. The analysis and comparison of these results with each other and with the results of the STA/LTA algorithm by the number of found covolcanic disturbances, false positives and the speed of operation is carried out. The disadvantages of STA/LTA regarding the application to the data under study and the possibility of overcoming them in the proposed approach are described. Conclusions are drawn about the quality of classification of neural networks and their applicability as a classifier in the universal algorithm for the detection of covolcanic disturbances. The directions of future research on the topic under consideration are proposed.
Keywords: ionosphere, covolcanic disturbances, machine learning, artificial neural networks, remote sounding, GNSS
Full text

References:

  1. Ahsan M. M., Mahmud M. A. P., Saha P. K., Gupta K. D., Siddique Z., Effect of Data Scaling Methods on Machine Learning Algorithms and Model Performance, Technologies, 2021, Vol. 9, No. 3, p. 52, DOI: 10.3390/technologies9030052.
  2. Aji B. A. S., Liong T. H., Muslim B., Detection precursor of Sumatra earthquake based on ionospheric total electron content anomalies using N-Model Artificial Neural Network, Intern. Conf. Advanced Computer Science and Information Systems (ICACSIS), 2017, pp. 269–276, DOI: 10.1109/ICACSIS.2017.8355045.
  3. Astafyeva E., Zakharenkova I. E., Förster M., Ionospheric response to the 2015 St. Patrick’s Day storm: A global multi-instrumental overview, J. Geophysical Research: Space Physics, 2015, Vol. 120, pp. 9023–9037, DOI: 10.1002/2015JA021629.
  4. Azar J., Makhoul A., Couturier R., Demerjian J., Robust IoT time series classification with data compression and deep learning, Neurocomputing, 2020, Vol. 398, pp. 222–234, DOI: 10.1016/j.neucom.2020.02.097.
  5. Breiman L., Random forests, Machine Learning, 2001, Vol. 45, No. 1, pp. 5–32, DOI: 10.1023/A:1010950718922.
  6. Brissaud Q., Astafyeva E., Near-real-time detection of co-seismic ionospheric disturbances using machine learning, Geophysical J. Intern., 2022, Vol. 230, No. 3, pp. 2117–2130, DOI: 10.1093/gji/ggac167.
  7. Faouzi J., Janati H., pyts: A python package for time series classification, J. Machine Learning Research, 2020, Vol. 21, No. 46, pp. 1–6.
  8. Galvan D. A., Komjathy A., Hickey M. P., Stephens P., Snively J., Tony Song Y., Butala M. D., Mannucci A. J., Ionospheric signatures of Tohoku-Oki tsunami of March 11, 2011: Model comparisons near the epicenter, Radio Science, 2011, Vol. 47, No. 4, DOI: 10.1029/2012RS005023.
  9. Han L., Wong J., Bancroft J., Time picking on noisy microseismograms, Proc. GeoCanada 2010 Convention — Working with the Earth, 2010, 4 p.
  10. Heki K., Explosion energy of the 2004 eruption of the Asama Volcano, central Japan, inferred from ionospheric disturbances, Geophysical Research Letters, 2006, Vol. 33, No. 14, DOI: 10.1029/2006GL026249.
  11. Fawaz I. H., Forestier G., Weber J., Idoumghar L., Muller P. A., Deep learning for time series classification: a review, Data Mining and Knowledge Discovery, 2019, Vol. 33, No. 4, pp. 917–963, DOI: 10.1007/978-3-030-88113-9_24.
  12. Fawaz I. H., Lucas B., Forestier G., Pelletier C., Schmidt D. F., Weber J., Petitjean F., InceptionTime: Finding AlexNet for time series classification, Data Mining and Knowledge Discovery, 2020, Vol. 34, No. 6, pp. 1936–1962, DOI: 10.1007/s10618-020-00710-y.
  13. Kogan M. G., Vasilenko N. F., Frolov D. I., Freymueller J. T., Steblov G. M., Prytkov A. S., Ekström G., Rapid postseismic relaxation after the great 2006–2007 Kuril earthquakes from GPS observations in 2007–2011, J. Geophysical Research: Solid Earth, 2013, Vol. 118, No. 7, pp. 3691–3706, DOI: 10.1002/jgrb.50245.
  14. Krischer L., Megies T., Barsch R., Beyreuther M., Lecocq T., Caudron C., Wassermann J., ObsPy: a bridge for seismology into the scientific Python ecosystem, Computational Science and Discovery, 2015, Vol. 8, No. 1, DOI: 10.1088/1749-4699/8/1/014003.
  15. Levin V. E., Bakhtiarov V. F., Titkov N. N., Serovetnikov S. S., Magus’kin M. A., Lander A. V., Contemporary crustal movements (CCMs) in Kamchatka, Izvestiya Physics of Solid Earth, 2014, Vol. 50, No. 6, pp. 732–751, https://doi.org/10.1134/S1069351314060044.
  16. Li H., Liu J., Yang Z., Liu R. W., Wu K., Wan Y., Adaptively constrained dynamic time warping for time series classification and clustering, Information Sciences, 2020, Vol. 534, pp. 97–116, DOI: 10.1016/j.ins.2020.04.009.
  17. Lin J., Chiou J., Detecting Total Electron Content Precursors Before Earthquakes by Examining Total Electron Content Images Based on Butterworth Filter in Convolutional Neural Networks, IEEE Access, 2020, Vol. 8, pp. 110478–110494, DOI: 10.1109/ACCESS.2020.3001337.
  18. Löning M., Bagnall A., Ganesh S., Kazakov V., Lines J., Király F., sktime: A Unified Interface for Machine Learning with Time Series, ArXiv:1909.07872, 2019, DOI: 10.48550/ARXIV.1909.07872.
  19. Middlehurst M., Large J., Flynn M., Lines J., Bostrom A., Bagnall A., HIVE-COTE 2.0: A new meta ensemble for time series classification, Machine Learning, 2021, Vol. 110, No. 11–12, pp. 3211–3243, DOI: 10.1007/s10994-021-06057-9.
  20. Muafiry I. N., Meilano I., Heki K., Wijaya D. D., Nugraha K. A., Ionospheric Disturbances after the 2022 Hunga Tonga-Hunga Ha’apai Eruption above Indonesia from GNSS-TEC Observations, Atmosphere, 2022, Vol. 13, No. 10, Art. No. 1615, DOI: 10.3390/atmos13101615.
  21. Nguyen L. H., Joshi D. R., Clay D. E., Henebry G. M., Characterizing land cover/land use from multiple years of Landsat and MODIS time series: A novel approach using land surface phenology modeling and random forest classifier, Remote Sensing of Environment, 2020, Vol. 238, Art. No. 111017, DOI: 10.1016/j.rse.2018.12.016.
  22. Shestakov N., Orlyakovskiy A., Perevalova N., Titkov N., Chebrov D., Ohzono M., Takahashi H., Investigation of Ionospheric Response to June 2009 Sarychev Peak Volcano Eruption, Remote Sensing, 2021, Vol. 13, No. 4, pp. 1–18, DOI: 10.3390/rs13040638.
  23. Shults K., Astafyeva E., Adourian S., Ionospheric detection and localization of volcano eruptions on the example of the April 2015 Calbuco events, J. Geophysical Research: Space Physics, 2016, Vol. 121, No. 10, pp. 10303–10315, DOI: 10.1002/2016JA023382.
  24. Sorokin A. A., Makogonov S. V., Korolev S. P., The Information Infrastructure for Collective Scientific Work in the Far East of Russia, Scientific and Technical Information Processing, 2017, Vol. 44, No. 4, pp. 302–304, DOI: 10.3103/S0147688217040153.
  25. Tsuji H., Hatanaka Y., Hiyama Y., Yamaguchi K., Furuya T., Kawamoto S., Fukuzaki Y., Twenty-Year Successful Operation of GEONET, Bull. Geospatial Information Authority of Japan, 2017, Vol. 65, pp. 19–44.
  26. Usmankhujaev S., Ibrokhimov B., Baydadaev S., Kwon J., Time Series Classification with InceptionFCN, Sensors, 2022, Vol. 22, No. 1, DOI: 10.3390/s22010157.
  27. Wang Z., Yan W., Oates T., Time series classification from scratch with deep neural networks: A strong baseline, Proc. Intern. Joint Conf. Neural Networks, 2017, Vol. 2017, pp. 1578–1585, DOI: 10.1109/IJCNN.2017.7966039.
  28. Withers M., Aster R. C., Young C. J., Beiriger J. I., Harris M., Moore S. G., Trujillo J. R., A comparison of select trigger algorithms for automated global seismic phase and event detection, Bull. Seismological Society of America, 1998, Vol. 88(1), pp. 95–106, DOI: 10.1785/bssa0880010095.
  29. Zerveas G., Jayaraman S., Patel D., Bhamidipaty A., Eickhoff C., A transformer-based framework for multivariate time series representation learning, Proc. ACM SIGKDD Intern. Conf. Knowledge Discovery and Data Mining, 2021, pp. 2114–2124, DOI: 10.1145/3447548.3467401.
  30. Zewdie G. K., Valladares C., Cohen M. B., Lary D. J., Ramani D., Tsidu G. M., Data-driven forecasting of low-latitude ionospheric total electron content using the random forest and LSTM machine learning methods, Space Weather, 2021, Vol. 19(6), DOI: 10.1029/2020SW002639.