The article presents an approach to predicting the water level at three points of the hydraulic posts of the Bolshoy Yenisei River basin (Biy-Khem). The forecast model is based on the available time series of ground-based data obtained from three hydro posts, using satellite reanalysis data from the ERA5_LAND collection (European Center for Medium-term Forecasting ECMWF), collections of watershed boundaries and river networks HydroSHEDS, WWF World Wildlife Center (USA), and datasets of water bodies MERIT Hydro (Japan). Regression methods implemented in the Matlab package, including the regression and stepwisefit functions, were used to build forecast models. The satellite data was exported as tables using JavaScript code in the Google Earth Engine (GEE) environment. In the course of the work, matrices of paired correlations between ERA5-Land parameters and ground data, relief maps, river network, and time series graphs were constructed. The constructed models demonstrated good accuracy in predicting the Kara-Haak water level: forecast errors (MAPE) were 19,1 %, and the coefficient of determination (R2) was 0,92, which indicates that the predicted values correspond well to the actual data. The other two showed satisfactory accuracy, i.e.: MAPE=39,5 %, R2=0,95; Sevi: MAPE=26,2 %, R2=0,95. The matrix of paired correlations revealed a strong dependence of the water level on such parameters as solar radiation, volumetric soil moisture, and total evaporation of moisture. The results of the study clearly demonstrate the effectiveness of the proposed approach to forecasting water levels in river basins.

Anatoly F. Chuldum
Researcher
Tuvinian Institute for Exploration of Natural Resources SB RAS
117a, Internatsionalnaya Str., Kyzyl, 667007, Russia
е-mail: tajkinol@gmail.com
ORCID: 0000-0003-2771-3863
Researcher ID: A-3489-2014
SPIN-code: 9253-9560
AuthorID: 159601

Svetlana A. Chupikova
Candidate of Geographic Sciences, Senior Researcher
Tuvinian Institute for Exploration of Natural Resources SB RAS
117a, Internatsionalnaya Str., Kyzyl, 667007, Russia
е-mail: s_fom@inbox.ru
ORCID ID: 0000-0002-7904-5847
ResearcherID: R-6738-2016
Scopus ID: 57194128480
SPIN-code: 8367-9071
AuthorID: 160182

1. Anashechkin A.D., Trophimets E.N. The question of building a short-term predictive models of water levels on stretches of the rivers. Vestnik Saint-Petersburg University of State Fire Service of Emercom of Russia. 2019;(1):36–43.
2. Andreev D.V. Application of GIS technologies to determine flooding in the Republic of Sakha (Yakutia). Advances in current natural sciences. 2019;(11):43–47.
3. Batmazova A.A., Khaustov V.A. Analysis and testing of methods for forecasting maximum mountain rivers flow. Proceedings of the YSU C: Geological and Geographical Sciences. 2023:57(3):196–203. DOI: 10.46991/PYSU:C/2023.57.3.196
4. Belyakova P.A., Moreido V.M., Amerbaev A.N., Tsyplenkov A.S., Grechishnikova D.A., Kurochkina L.S., Filippov V.A., Makeev M.S. Forecasting water levels in Krasnodar krai rivers with the use of machine learning. Water resources. 2022;49(1):10–22. DOI: 10.1134/S0097807822010043
5. Buyanov D., Fedotov R., Tkachenko P. Prediction of the Ob’s water level rise in Tomsk region using regression analysis. Nauchnye i obrazovatel’nye problemy grazhdanskoi zashchity. 2015;(2):112–118.
6. Gaidukova E.V., Yanovskaya A.O., Dregval’ M.S., Batmazova A.A. Dolgosrochnyi prognoz stoka rek AZRF s ispol’zovaniem regressionnykh zavisimostei [Long-term forecast of river runoff in the Arctic Zone of the Russian Federation using regression dependencies]. In: Sovremennye tendentsii i perspektivy razvitiya gidrometeorologii v Rossii: materialy V Vserossiiskoi nauchno-prakticheskoi konferentsii (Irkutsk, 23–25 November 2022). Sutyrina E.N., ed. Irkutsk: IGU; 2023. pp. 59–67.
7. Kosheleva E.D., Kudishin A.V. Short-term forecast of Ob river water level near Barnaul city during flood 2018. Bulletin of the Altay branch of the Russian Geographical Society. 2018;(3):27–37.
8. Noskov S.I., Aksenov I.D., Sapozhnikov Y.M. Forecasting flood inundations on the rivers of Siberia using the example of forecasting the water level in the Iya river (Eastern Siberia) based on a multifactor regression model. Ingineering journal of Don. 2024;(4):99–107.
9. Noskov S.I., Aksenov I.D., Sapozhnikov Y.M. The regression modieling the level of Ia river, Irkutsk state. Ingineering journal of Don. 2023;(11):293–308.
10. Vizi Z., Batki B., Rátki L., Szalánci S., Fehérváry I., Kozák P., Kiss T. Water level prediction using long short term memory neural network model for a lowland river: a case study on the Tisza River, Central Europe. Environmental Science Europe. 2023;35:92. DOI: 10.1186/s12302-023-00796-3.
11. Yuan Z., Liu J., Liu Y., Zhang Q., Li Y., Li Z. A two stage modelling method for multi-station daily water level prediction. Environmental Modelling & Software. 2022;156:105468. DOI: 10.1016/j.envsoft.2022.105468.
12. Gorelick N., Hancher M., Dixon M., Ilyuschenko S., Thau D., Moore R. Google Earth Engine: Planetary-scale geospatial analysis for everyone. Remote Sensing of Environment. 2017;202:18–27. DOI: 10.1016/j.rse.2017.06.031.
13. Hersbach H., Bell B., Berrisford P. et al. The ERA5 global reanalysis. Quarterly Journal of the Royal Meteorological Society. 2020;146(730):1999–2049. DOI: 10.1002/qj.3803.
14. Muñoz-Sabater J. ERA5-Land monthly averaged data from 1981 to present. Copernicus Climate Change Service (C3S) Climate Data Store (CDS). 2019. Available at: https://cds.climate.copernicus.eu/datasets/reanalysis-era5-land?tab=overview (accessed 11.06.2025). DOI: 10.24381/cds.e2161bac.
15. Lehner B., Grill G. Global river hydrography and network routing: baseline data and new approaches to study the world’s large river systems. Hydrological Processes. 2013;27(15):2171–2186. DOI: 10.1002/hyp.9740.
16. Yamazaki D., Ikeshima D., Sosa J., Bates P.D., Allen G., Pavelsky T.M. MERIT Hydro: A high-resolution global hydrography map based on the latest topography dataset. Water Resources Research. 2019;55(6):5053–5073. DOI: 10.1029/2019WR024873.
17. NASA JPL. NASADEM Merged DEM Global 1 arc second V001 [Data set]. NASA EOSDIS Land Processes DAAC. Accessed 2020-12-30 from https//doi:10.5067/MEaSUREs/NASADEM/NASADEM_HGT.001.
18. D’yakonov V.P. Spravochnik po primeneniyu sistemy PC MatLAB [Handbook of application of PC MatLAB system]. Moscow: Nauka: Fiz.-mat. lit.; 1993. 109 p.
19. Bidyuk P.I., Zvorygina T.F. Strukturnyi analiz metodik postroeniya regressionnykh modelei po vremennym ryadam nablyudenii. Control Systems and Computers. 2003;(2):93–99.