An artificial neural network for analysis of ionograms obtained by ionosonde at the Ukrainian Antarctic Akademik Vernadsky station
-
Published:2020-12
Issue:2
Volume:
Page:59-67
-
ISSN:1727-7485
-
Container-title:Ukrainian Antarctic Journal
-
language:
-
Short-container-title:UAJ
Author:
Bogomaz O., ,Shulha M.,Kotov D.,Koloskov A.,Zalizovski A., , , , , , , , , ,
Abstract
The article presents the developed artificial neural network for F2 ionosphere layer traces scaling on ionograms obtained using the IPS-42 ionosonde installed at the Ukrainian Antarctic Akademik Vernadsky station. The parameters of the IPS-42 ionosonde and the features of the data obtained with it, in particular the format of the output files, are presented. The advantages of using an artificial neural network for identification of traces on ionograms are demonstrated. Usually, an automatic scaling of the ionograms requires a lot of machine time however implementation of an artificial neural network speeds up computations significantly allowing to process incoming ionograms even in the real time mode. The choice of architecture of an artificial neural network is substantiated. The U-Net architecture was chosen. The method of creating and training the neural network is described. The artificial neural network development process included choosing the number of layers, types of activation functions, optimization method and input layer size. Software developed was written in Python programming language with use of the Keras library. Examples of data used for training of the artificial neural network are shown. The results of testing an artificial neural network are presented. The data obtained with the artificial neural network are compared with the results of manual processing of ionograms. Data for training the artificial neural network were obtained in March, 2017 using the IPS-42 ionosonde installed at the Ukrainian Antarctic Akademik Vernadsky station; data for testing were obtained in 2017 and 2020. The developed artificial neural network has minor flaws but they are easily eliminated by retraining the network on a more representative dataset (obtained in various years and seasons). The general results of testing indicate good prospects in further developing this artificial neural network and software for working with it.
Publisher
State Institution National Antarctic Scientific Center, Ministry of Education and Science of Ukraine
Reference21 articles.
1. Bogomaz, O. V., Kotov, D. V., Shulha, M. O., & Gorobets, M. V. (2019b). Comparison of the F2 layer peak height variations obtained by ionosonde and incoherent scatter radar. Bulletin of the National Technical University "KhPI", 25(1350), 58-61. Retrieved November 3, 2020, from http://iion.org.ua/article/bulletin-25/ 2. Bogomaz, O. V., Shulha, M. O., Kotov, D. V., Zhivolup, T. G., Koloskov, A. V., Zalizovski, A. V., Kashcheyev, S. B., Reznychenko, A. I., Hairston, M. R., & Truhlik, V. (2019a). Ionosphere over Ukrainian Antarctic Akademik Vernadsky station under minima of solar and magnetic activities, and daily insolation: case study for June 2019. Ukrainian Antarctic Journal, 2(19), 84-93. https://doi.org/10.33275/1727-7485.2(19).2019.154 3. Broom, S. M. (1984). A new ionosonde for Argentine Islands ionospheric observatory, Faraday Station. British Antarctic Survey Bulletin, 62, 1-6. Retrieved November 3, 2020, from http://nora.nerc.ac.uk/id/eprint/523821/ 4. Bullett, T., Malagnini, A., Pezzopane, M., & Scotto, C. (2010). Application of Autoscala to ionograms recorded by the VIPIR ionosonde. Advances in Space Research, 45(9), 1156-1172. https://doi.org/10.1016/j.asr.2010.01.024 5. Bushaev, V. (2018). Adam - latest trends in deep learning optimization. Towards Data Science. https://towardsdatascience.com/adam-latest-trends-in-deep-learning-optimization-6-be9a291375c
Cited by
2 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
|
|