Keywords: simulation of rain flow, artificial neural network, activation functions, training and test samples

Timely forecasting of rain floods on rivers allows you to avoid the negative consequences that they can cause by destroying structures and communications located in their channels or on floodplains. It is relevant for the Stryi River, as catastrophic rain floods occur in its basin from time to time. The article is devoted to the use of an artificial neural network (ANN) for modeling the rain runoff of the Stryi River near the Verkhnie Synyovydne village for the period 2005-2012. Using the 'nnet' package in RStudio (version 2024.12.0 Build 467), a direct-connection ANN model was developed. In addition, the classical linear multiple regression model (CLMRM) was also used. The model based on ANN has an advantage over the CLMRM, as its statistical indicators of modeling quality are higher. Thus, the Nash-Sutcliffe efficiency coefficient of the ANN model for the training sample was 91.6%, and for the test sample was 92.5%, which classifies it as excellent. However, for CLMRM these indicators were 81.5% and 89.4%, respectively. Graphical analysis also demonstrated the advantage of the ANN model, since it was for it that a better match between the simulated and historical values was obtained, which is confirmed by higher of determination coefficients (0.92 ANN and 0.82 CLMRM for the training sample and 0.93 ANN and 0.89 CLMRM for the test sample). The statistic indicators RMSE of the CLMRM model turned out to be greater than the ANN model for both the training (29.8 m3/s and 20.1 m3/s) and test (25.2 m3/s and 21.1 m3/s) samples. The advantage of the ANN model over the CLMRM model is that it takes into account the nonlinearity of 'rainfall-runoff' relationship due to the parallelism of its architecture. In Ukraine, river flow modeling by ANNs was caried out for the first time. This approach may be particularly relevant for transboundary rivers of the country, for which there are significant problems with the availability of observation data.

1. Aoulmi, Y., Marouf, N., & Amireche, M. (2021). The assessment of artificial neural network rainfall-runoff models under different input meteorological parameters. Case study: Seybouse basin, Northeast Algeria. Journal of water and land development, 50(VI–IX), 38–47. https://doi.org/10.24425/jwld.2021.138158

2. Belchikov, V.A., & Koren, V.I. (1979). Model of the formation of melting and rain runoff for forest catchments. Proceedings of the Hydrometeorological Center of the USSR, 218, 3–21. [in Russian]

3. Chakravarti, A., Joshi, N., & Panjiar, H. (2015). Rainfall Runoff Analysis Using Artificial Neural Network. Indian Journal of Science and Technology, 8(14), 1–7. https://doi.org/10.17485/ijst/2015/v8i14/54370

4. Cigizoglu, H.K. (2003). Estimation, forecasting and extrapolation of river flows by artificial neural networks. Hydrological Science Journal, 48(3), 349–361. https://doi.org/10.1623/hysj.48.3.349.45288

5. Ghumman, A.R., Ghazaw, Y.M., Sohail, A.R., & Watanabe K. (2011). Runoff forecasting by artificial neural network and conventional model. Alexandria Engineering Journal, 50, 345–350. https://doi.org/10.1016/j.aej.2012.01.005

6. Gopchenko, E.D., & Goptsiy, M.V. (2015). Maximum runoff of rain floods in the Carpathian Mountains: monograph. Odesa: TES. [in Ukrainian]

7. Guide to Hydrological Practices (2009). Management of Water Resources and Application of Hydrological Practices. Vol. II. Sixth edition. WMO-No. 168. Geneva: World Meteorological Organization.

8. Hornik, K., Stinchcombe, M., & White, H. (1989). Multilayer feedforward networks are universal approximators. Neural Networks, 2(5), 359–366. https://doi.org/10.1016/0893-6080(89)90020-8

9. Khrystiuk, B., Gorbachova, L., & Shpyg, V. (2022). Verification of the automated flood forecasting system on the Stryi River. Acta Hydrologica Slovaca, 23(2), 234–240. https://doi.org/10.31577/ahs-2022-0023.02.0026

10. McCulloch, W.S., & Pitts W. (1943). A Logical Calculus of the Ideas Imminent in Neural Activity. Bulletin of Mathematical Biophysics, 5, 115–133. https://doi.org/10.1007/BF02478259

11. Minns, A.W., & Hall, M.J. (1996). Artificial neural networks as rainfall-runoff models. Hydrological Science Journal, 41(3), 399–417. https://doi.org/10.1080/02626669609491511

12. Mohseni, U.; Muskula, S.B. (2023). Rainfall-Runoff Modeling Using Artificial Neural Network–A Case Study of Purna Sub-Catchment of Upper Tapi Basin, India. Environmental Sciences Proceedings, 25, 1. https://doi.org/10.3390/ECWS-7-14232

13. Nash, J.E., & Sutcliffe, J.V. (1970). River flow forecasting through conceptual models, part1 – a discussion of principles. Journal of Hydrology, 10(3), 282–290. https://doi.org/10.1016/0022-1694(70)90255-6

14. Operational Hydrology Manual (2012). Forecasts of the Land Water Regime. Hydrological Support and Maintenance. Kyiv: Verlan Publishing House. [in Ukrainian]

15. Pryimachenko, N.V. (2010). Substantiation of the system for calculating flood characteristics on mountain rivers of the Dniester basin based on mathematical modeling of rain runoff formation processes. Аvtoref. dys. ...kand. geogr. nauk: 11.00.07. Taras Shevchenko National University of Kyiv. [in Ukrainian]

16. R Core Team (2017). A language and environment for statistical computing. R Foundation for Statistical Computing. Vienna, Austria. Available at: https://www.r-project.org

17. Riad, S., Mania, J., Bouchaou, L., Najjar, Y. (2004). Rainfall-runoff model usingan artificial neural network approach. Mathematical and Computer Modelling, 40(7-8), 839–846. https://doi.org/10.1016/j.mcm.2004.10.012

18. Ripley, B.D. (1996). Pattern Recognition and Neural Networks. Cambridge University Press.

19. Rosenblatt, R. (1959). Principles of Neurodynamics. New York: Spartan Books.

20. Shamseldin, A.Y. (1997). Application of a neural network technique to rainfall–runoff modeling. Journal of Hydrology, 199(3-4), 272–294. http://dx.doi.org/10.1016/S0022-1694(96)03330-6

21. Sosedko, M.N. (1976). Forecast of the course of rain runoff on the mountain rivers of the Dniester basin, taking into account the unevenness of the inflow. Proceedings of UkrNIHMA, 143, 132–147. [in Russian]

22. Sosedko, M.N. (1984). Develop recommendations and requirements for the flood forecasting subsystem project of ASUB Stryi: report on research. Kyiv: Ukrainian Regional Research Institute. [in Russian]

23. Susidko, М.М. (2000). Mathematical modeling of runoff formation processes as a basis of forecasting systems. Hydrology, Hydrochemistry and Hydroecology, 1, 32–40. [in Ukrainian]

24. Tayfur, G. (2002). Artificial neural networks for sheet sediment transport. Hydrological Science Journal, 47(6), 879–892. https://doi.org/10.1080/02626660209492997