ABSTRACTS OF ARTICLES OF THE JOURNAL "INFORMATION TECHNOLOGIES".
No. 3. Vol. 29. 2023

DOI: 10.17587/it.29.149-156

R. A. Korotchenko, Ph.D., Senior Researcher, A. V. Kosheleva, Research Scientist,
V. I. irichev Pacific Oceanological Institute of Far Eastern Branch of Russian Academy of Sciences,
Vladivostok, Russian Federation

Integrated Method for Moderation of Hydrological Data Using Singular Spectrum Analysis and Neural Networks

The paper considers a method for preprocessing (moderating) in situ hydrological data, which allows us to effectivety identify and eliminate noises of various nature. Registered data sometimes can contain abrupt surges and high-frequency pickup, caused by technology-related factors (operation nuances of the equipment used). They contradict the physical and space-time scales of hydrological wave processes, but at the same time they are not always obvious to a human operator conducting primary control. For the procedure of automatic moderation, the use of neural networks in combination with the methods of singular spectrum analysis (SSA) is proposed and the results of its practical application are demonstrated.
Keywords: singular spectrum analysis, neural network, data recovery temperature field, hydrology, in situ measurements

P. 149–156

References

1. Leontyev A. P., Yaroshchuk I. O., Smirmov S. V., Kosheleva A. V., Pivovarov À. À., Samchenko À. N., Shvyrev A. N. A spatially distributed measuring complex for monitoring hydro-physical processes on the ocean shelf, instruments and Experimental Techniques, 2017, vol. 60, no. 1, pp. 130—136, DOI: 10.1134/ S0020441216060191.
2. Kosheleva A. V., Yaroshchuk I. O., Khrapchenkov F. F., Pivovarov A. A., Samchenko A. N., Shvyrev A. N., Korotchenko R. A. Upwelling on the Narrow Shelf of the Sea of Japan in 2011, Fundamental and Applied Hydrophysics, 2021, vol. 14, no. 1, pp. 31—42, DOI: 10.7868/S2073667321010032.
3. Kosheleva A. V., Lazaryuk A. Yu., Yaroshchuk I. O. Estimation of acoustic and oceanological seawater characteristics by temperature measurements in the Sea of Japan shelf zone, Proceedings of Meetings on Acoustics, 2015, vol. 24, no. 1, 005001. P. 005001, DOI: 10.1121/2.0000109.
4. Yaroshchuk I. O., Leont'ev A. P., Kosheleva A. V., Pivovarov A. A., Samchenko A. N., Stepanov D. V., Shvyryov A. N. On intense internal waves in the coastal zone of the Peter the Great Bay (the Sea of Japan), Russian Meteorology and Hydrology, 2016, vol. 41, no. 9, pp. 629—634, DOI: 10.3103/S1068373916090053.
5. Kosheleva A. V., lazaryuk A. Yu., Yaroshchuk I. O., Ko-rotchenko R. A., Gulin O. E., Samchenko A. N., Pivovarov A. A., Shvyrev A. N. Acoustic-oceanological simulation of seawater hydrophysical parameters on temperature measurements in the Sea of Japan shelf zone, Vestnik of Far Eastern Branch of Russian Academy of Sciences, 2018, vol. 197, no. 1, pp. 25—30 (in Russian).
6. Elsner J. B., Tsonis A. A. Singular Spectrum Analysis: A New Tool in Time Series Analysis, New York, Plenum Press, 1996, 164 p.
7. Golyandina N., Nekrutkin V., Zhigljavsky À. A. Analysis of Time Series Structure: SSA and Related Techniques, Boca Raton: Chapman & Hall/CRC, 2001, 305 p.
8. Golyandina N. E. Caterpillar-SSA Method: Time Series Analysis: Tutorial, Saint Petersburg, St. Petersburg State University Publishing House, 2004. 76 p. (in Russian).
9. Osovsky S. Neural networks for information processing, Moscow, Finance and statistics, 2002, 344 p. (in Russian).
10. Filatova T. V. Application of neural networks for data approximation, Vestnik of Tomsk State University, 2004, no 284, pp. 121—125 (in Russian).
11. Donskoy D. A. Modeling artificial neural networks in the MATLAB system. Part 3. Radial basic networks, Penza, Penza State University Publishing House, 2005, 33 p. (in Russian).

To the contents