Detecting Anomalies in Intermagnet Data Using Graph Neural Network
https://doi.org/10.17586/0021-3454-2024-67-10-817-821
Abstract
The use of modern digital information technologies, such as Data Mining, Data Science and Big Data, has caused an exponential growth in the volume of data, allowing to obtain new knowledge in various subject areas based on the information provided. In this regard, tasks related to pre-processing, intellectual analysis, visualization of large data sets have become especially relevant. Using the methods of intelligent analysis Unsupervised learning, the problem of detecting anomalies (outliers) in data arrays obtained from the Lycksele magnetic observatory, which is part of the international network INTERMAGNET, is solved. Since anomalies reflect changes in the Earth’s geomagnetic field, they are highly informative, which gives the solution to this problem great scientific and practical value. Anomalies in the designated data are not frequent enough, so they can be detected only in a large volume of processed information. The results of detecting anomalies using a graph neural network are presented. The MATLAB system is used as a software.
Keywords
Big Data,
Data Mining,
Datastore,
INTERMAGNET,
MATLAB,
unsupervised learning,
geomagnetic disturbances,
graph neural network
Supporting agencies: The work was supported by the Russian Science Foundation grant No. 23-27-00011.
About the Author
A. G. Korobeynikov
Pushkov Institute of Terrestrial Magnetism, Ionosphere and Radio Wave Propagation of the RAS, St. Petersburg branch;
Russian Federation
Russian Federation
Anatoly G. Korobeynikov — Dr. Sci., Professor; Deputy Director for Science
St. Petersburg
References
1. Apeltsin L. Data Science Bookcamp, Simon and Schuster, 2021, 704 р.
2. Ostroukh A.V., Nikolayev A.B. Intellektual’nyye informatsionnyye sistemy i tekhnologii (Intelligent Information Systems and Technologies), St. Petersburg, 2023, 308 р. (in Russ.)
3. Korobeynikov A.G. Journal of Instrument Engineering, 2023, no. 12(66), pp. 993–1001, DOI: 10.17586/0021-34542023-66-12-993-1001. (in Russ.)
4. Scarselli F., Gori M., Tsoi A., Hagenbuchner M. & Monfardini G. IEEE Transactions on Neural Networks, 2009, no. 1(20), pp. 61–80, https://ro.uow.edu.au/cgi/viewcontent.cgi?article=10501&context=infopapers.
5. Wu Z., Pan S., Chen F. et al. IEEE Transactions on Neural Networks and Learning Systems, 2021, no. 1(32), pp. 4–24, DOI: 10.1109/TNNLS.2020.2978386.
6. Zakoldaev D.A., Korobeynikov A.G., Shukalov A.V., Zharinov I.O. IOP Conference Series Materials Science and Engineering, 2019, no. 1(665), pp. 012015, DOI: 10.1088/1757-899X/665/1/012015.
7. Grishentsev A.Yu., Korobeinikov A.G., Dukelskiy K.V. Cybernetics and programming, 2017, no. 3, pp. 23–38. (in Russ.)
8. Korobeinikov A.G., Grishentsev A.Yu., Svyatkina M.N. Cybernetics and programming, 2013, no. 3, pp. 9–20. (in Russ.)
9. Korobeinikov A.G., Kudrin R.A., Sidorkina I.G. Vestnik of Mari State Technical University. Series: Radio Engineering and Infocommunication Systems, 2010, no. 2(9), pp. 91–98. (in Russ.)
10. Romanov P.S., Romanova I.P. Sistemy iskusstvennogo intellekta. Modelirovaniye neyronnykh setey v sisteme MATLAB. Laboratornyy praktikum (Artificial Intelligence Systems. Modeling Neural Networks in MATLAB. Laboratory Workshop), St. Petersburg, 2024, 140 р. (in Russ.)
11. Sun C., Li C., Lin X. et al. Artif. Intell. Rev., 2023, no. 2(56), pp. 2263–2310, https://doi.org/10.1007/s10462-02310577-2.
12. Nikolenko S., Kadurin A., Arkhangelskaya E. Glubokoye obucheniye. Pogruzheniye v mir neyronnykh setey (Deep Learning. Immersion into the World of Neural Networks), St. Petersburg, 2020, 480 р. (in Russ.)
Review
For citations:
Korobeynikov A.G. Detecting Anomalies in Intermagnet Data Using Graph Neural Network. Journal of Instrument Engineering. 2024;67(10):817-821. (In Russ.) https://doi.org/10.17586/0021-3454-2024-67-10-817-821
Views:
33
Email this article 