DOI: 10.17587/prin.15.265-272

Method of Data Preprocessing on the Basis of Pulse Neural Network to Improve the Accuracy of Water Level Forecast on the Example of Ufa City of the Republic of Bashkortostan

E. V. Palchevsky, Senior Lecturer, teelxp@inbox.ru, Financial University under the Government of the Russian Federation, Moscow, 109456, Russian Federation, V. V. Antonov, D. Sc. (Technical), Head of Department, antonov.v@bashkortostan.ru, E. A. Makarova, D. Sc. (Technical), Professor of Department, ea-makarova@mail.ru, N. A. Kononov, Graduate Student, kononov.nick.pi@yandex.ru, Ya. S. Voyakovskaya, Senior Lecturer, in.edem@yandex.ru, Institute of Informatics, Mathematics and Robotics, Ufa University of Science and Technology, Ufa, 450008, Russian Federation

Corresponding author: Evgeny V. Palchevsky, Senior Lecturer, Financial University under the Government of the Russian Federation, Moscow, 109456, Russian Federation, E-mail: teelxp@inbox.ru

The developed method of data preprocessing based on impulse neural network is considered. The essence of this method is to improve the quality of the initial dataset by minimising data noise. The peculiarity is to improve the accuracy of the predicted values of the time series of water levels obtained at the output of the pulse neural network. Retrospective data were obtained from hydrological posts (river gauge) and automatic stations with the help of FSUE «Centre of Register and Cadastre» from 01.01.1997 to 30.06.2023. On the example of hydrological post 76289 (Ufa) the experiment on forecasting of water levels with the help of the developed system «Flood 2.0» was carried out. The experiment proves the efficiency of the data preprocessing method developed in this study to improve the accuracy of water level forecasts.

Keywords: pulse neural network, water level forecasting, neural networks, intelligent forecasting system, forecast accuracy improvement

pp. 265–272

For citation:
Palchevsky E. V., Antonov V. V., Makarova E. A., Kononov N. A., Voyakovskaya Ya. S. Method of Data Preprocessing on the Basis of Pulse Neural Network to Improve the Accuracy of Water Level Forecast on the Example of Ufa City of the Republic of Bashkortostan, Programmnaya Ingeneria, 2024, vol. 15, no. 5, pp. 265—272. DOI: 10.17587/prin.15.265-272.

The research is carried out with the financial support of the Ministry of Education and Science of the Russian Federation as part of the basic part of the state task for higher education institutions

References:

• Kasuni E. A., Sangam S. D., Ratnayake T. et al. Evaluation of artificial intelligence models for flood and drought forecasting in arid and tropical regions, Environmental Modelling & Software, 2021, vol. 144, article 105136. DOI: 10.1016/j.envsoft.2021.105136.
• Yalcın S., Eşit M., Coban O. A new deep learning method for meteorological drought estimation based-on standard precipitation evapotranspiration index, Engineering Applications of Artificial Intelligence, 2023, vol. 124, pp. 106550. DOI: 10.1016/j.engappai.2023.106550.
• Palchevsky E. V., Antonov V. V. Decision support system based on application of the second generation neural network, Programmnaya Ingeneria, 2022, vol. 13, no. 6, pp. 301—308. DOI: 10.17587/prin.13.301-308.
• Palchevsky E. V., Antonov V. V., Rodionova L. A. et al. Intelligent forecasting of electricity consumption in managing energy enterprises in order to carry out energy-saving measures, Mekhatronika, Avtomatizatsiya, Upravlenie, 2023, vol. 24, no. 6, pp. 307—316. DOI: 10.17587/mau.24.307-316.
• Oyounalsoud M. S., Abdallah M., Yilmaz A. G. et al. A new meteorological drought index based on fuzzy logic: Development and comparative assessment with conventional drought indices, Journal of Hydrology, 2023, vol. 619, article 129306. DOI: 10.1016/j.jhydrol.2023.129306.
• Shatha A., Hossam F., Hazem H. EvoImputer: An evolutionary approach for Missing Data Imputation and feature selection in the context of supervised learning, Knowledge-Based Systems, 2022, vol. 236, article 107734. DOI: https://linkkk.org/10.1016/j.knosys.2021.107734.
• Gideon A. L., Mohd Z., Anoop Krishman N. M., Sumanta D. Prediction of concrete strengths enabled by missing data imputation and interpretable machine learning. Cement and Concrete Composites, 2022, vol. 128, article 104414. DOI: 10.1016/j.cemconcomp.2022.104414.
• "Flood 2.0" system. Year of implementation: 2023, available at: https://elforecasting.com/?lang=ru (date of access 03.01.2024).
• Cron, available at: https://ru.wikipedia.org/wiki/Cron (date of access 08.01. 2024).
• Zhu K. A new generalized exponentially weighted moving average quantile model and its statistical inference, Journal of Econometrics, 2023, vol. 237, article 105510. DOI: 10.1016/j.jeconom.2023.105510.
• KNNimputer, available at: https://scikit-learn.org/stable/ modules/generated/sklearn.impute.KNNImputer.html (date of access 18.02.2024).
• Simplelmputer, available at: https://scikit-learn.org/stable/ modules/generated/sklearn.impute.SimpleImputer.html (date of access 18.02.2024).
• RLEAKY SNN, available at: https://snntorch.readthedocs. io/en/latest/snn.neurons_rleaky.html (date of access 10.01.2024).
• PyTorch, available at: https://pytorch.org/ (15 Jan 2024).
• SNNTorch, available at: https://snntorch.readthedocs.io/en/latest/ (date of access 16.01.2024).
• Palchevsky E. V., Antonov V. V., Enikeev R. R., Breikin T. A system based on an artificial neural network of the second generation for decision support in especially significant situations, Journal of Hydrology, 2023, vol. 616, article 128844. DOI: 10.1016/j.jhydrol.2022.128844.
---