Application of Neural Network Modeling in Problems of Predicting the Level of River Floods
https://doi.org/10.25205/1818-7900-2023-21-2-39-50
Abstract
The purpose of this article is to consider the theoretical and practical issues of developing neural network models for river flood forecasting (in case of the Belaya River near Ufa), as well as to implement the corresponding neural network in Python. To build a training sample, archival data from meteorological services and meteorological observation sites for the flood periods of the Belaya (Agidel) River in 2018–2022 were used. The following indicators were collected and analyzed: water level, water temperature, day and night air temperature, precipitation, snow depth, including information about the pre-flood condition of the snow cover. The software implementation of the neural network was performed using the PyTorch deep learning library; in addition, modules from the Matplotlib and Pandas libraries were used. The stability of the operation of this neural network was studied when the following parameters were changed: the optimizers used (Adam, Adamax and Rprop); learning rate coefficient; the number of neurons in the hidden layer; number of learning epochs. It is concluded that the developed neural network can be used to model the flood level when creating short-term forecasts. In order to move to longer-term forecasts in the future, it is planned to further expand the size of the factors in the training sample.
About the Author
T. M. Shamsutdinova
Bashkir State Agrarian University
Russian Federation
Russian Federation
Tatyana M. Shamsutdinova, Candidate of Sciences (Physics and Mathematics), Docent of the Department of Digital Technologies and Applied Informatics
Ufa
References
1. Afonin L. A. Problems of forecasting floods and flooding. Science // Innovation. Technologies. 2014. No. 1. Pp. 145–152. (in Russ.)
2. Jahangir M. H., Reineh S. M. M., Abolghasemi M. Spatial predication of flood zonation mapping in Kan River Basin, Iran, using artificial neural network algorithm // Weather and Climate Extremes. 2019. Vol. 25. 100215. DOI: 10.1016/j.wace.2019.100215
3. Tkachenko P. N., Vakorin M. V. Analysis of the problem situation in case of using information flood forecasting systems by units of EMERCOM of Russia // Siberian Fire and Rescue Bulletin. 2019. No. 4(15). Pp. 49–54. (in Russ.)
4. Varshanina T. P., Matusov D. V., Plisenko O. A., Starodub I. V. Neuro-Network System of the Flood Forecast on Adygei Small Rivers // Izvestiya Rossiiskoi Akademii Nauk. Seriya Geograficheskaya. 2007. No. 6. Pp. 87–93. (in Russ.)
5. Velikanova L. I. Forecasting the Water Level at Forwarding Flood in The Mountain Streams Using Neural Network Technology and Forecast of Meteorological Service. Automation and Control Problems. 2013. No. 1(24). Pp. 66–73. (in Russ.)
6. Hag-Elsafi S. Artificial Neural Networks (ANNs) for flood forecasting at Dongola Station in the River Nile, Sudan, Alexandria // Engineering Journal. 2014. Vol. 53, iss. 3. Pp. 655–662. DOI: 10.1016/j.aej.2014.06.010
7. Larioshkin V. V. Technique of Forecasting Rain Flood in the Upper Amur Basin (by the Example of the Onon River) // Bulletin of the Tomsk Polytechnic University. Geo Аssets Engineering. 2016. Vol. 327. No. 11. Pp. 105–115. (in Russ.)
8. Grebnev Y. V., Yarovoy A. V. Control and prediction of floods on the territory of the Krasnoyarsk kray through the use of neural network algorithms // Siberian Fire and Rescue Bulletin. 2018. No. 3(10). Pp. 13–16. (in Russ.)
9. Napolitano G., See L., Calvo B., Savi F., Heppenstall A. A conceptual and neural network model for real-time flood forecasting of the Tiber River in Rome // Physics and Chemistry of the Earth, Parts A/B/C. 2010. Vol. 35. Iss. 3–5. Pp. 187–194. DOI: 10.1016/j.pce.2009.12.004
10. Castangia M., Grajales L. M. M., Aliberti A., Rossi C., Macii A., Macii E., Patti E. Transformer neural networks for interpretable flood forecasting // Environmental Modelling & Software. 2023. Vol. 160. 105581. DOI: 10.1016/j.envsoft.2022.105581
11. Buyanov D. I., Fedotov R. S., Tkachenko P. N. Prediction of the Ob’s Water Level Rise in Tomsk Region Using Regression Analysis // Scientific and educational problems of civil protection. 2015. No. 2(25). Pp. 112–118. (in Russ.)
12. Shamsutdinova T. M. Problems of neural network and regression forecasting the river flood level // Siberian Fire and Rescue Bulletin. 2021. No. 2(21). Pp. 99–105. (in Russ.) DOI: 10.34987/vestnik.sibpsa.2021.79.13.017
13. Li Z., Tanaka G. HP-ESN: Echo State Networks Combined with Hodrick-Prescott Filter for Nonlinear Time-Series Prediction // 2020 International Joint Conference on Neural Networks (IJCNN), Glasgow, UK, 2020. Pp. 1–9. DOI: 10.1109/IJCNN48605.2020.9206771
14. Kingma D. P., Ba J. Adam: A Method for Stochastic Optimization // 3rd International Conference on Learning Representations (ICLR), San Diego, 2015. DOI: 10.48550/arXiv.1412.6980
15. Igel C., Hüsken M. Empirical Evaluation of the Improved Rprop Learning Algorithms // Neurocomputing. 2003. Vol. 50. Pp. 105–123. DOI: 10.1016/S0925-2312(01)00700-7
Review
For citations:
Shamsutdinova T.M. Application of Neural Network Modeling in Problems of Predicting the Level of River Floods. Vestnik NSU. Series: Information Technologies. 2023;21(2):39-50. (In Russ.) https://doi.org/10.25205/1818-7900-2023-21-2-39-50
Views:
202
Email this article 