Keywords: underground flow, modelling, forecast, groundwater, factors, neural networks, regression equations, statistical methods, simulation forecasting, monitoring

The most reliable forecasts can be obtained for hydrogeological objects that have signs of determinism in regime changes. First of all, these include systems with an undisturbed mode. However in the network of state hydrogeological monitoring of groundwater, there are no objects with an undisturbed regime due to the spread of direct anthropogenic influence and indirect - due to the changes in climatic conditions caused by it. Significant variability and unpredictability of changes in traditional regime-forming factors (air temperature and precipitation) over the last decades proves the low efficiency of forecasting the level and flow of groundwater using empirical regression equations built on data from the 1980s - early 2000s. It was possible to obtain more reliable results with the help of neural network modelling, which involves working with significant series of contradictory data that change according to an unknown algorithm. The forecast was made for the specific underground flow to the South Bug River in the area of Khmilnyk. The advantages of simulated forecasting over time series forecasting are shown.

1. Konoplyantsev, A.A., Semenov, S.M. (1974). Forecastingandmappingofthegroundwaterregime. Moscow: Nedra, 93-100. [In Russian]

2. Ruban, S.A., Shinkarevskyi, M.A. (2005). Hydrogeological assessments and forecasts of the underground water regime of Ukraine.Кyiv, 311-326. [In Ukrainian]

3. Shevchenko, A.L., Charnyi, D.V., Osadchyi, V.I., Ilchenko, A.O. (2021). GroundwaterflowintheSouthernBugRiverbasinunderconditionsofglobalwarming. Geologicaljournal, 3, 3-16.[In Ukrainian]

4. Shufranovych, M.A. (2014).A system of intellectual support for decision-making in conditions of uncertainty in the management of natural resources. Diss. can. technical scien.: 05.13.07. Ivano-Frankivsk, 199.[In Ukrainian]

5. Adamowski, J., Hiu Fung Chan, Prasher, S., Ozga-Zielinski, B., Sliusarieva, A. (2012). Comparison of multiple linear and nonlinear regression, autoregressive integrated moving average , artificial neural network and wavelet artificial neural network methods for urban water demand forecasting in Montreal, Canada.” Water resources research,48, # W01528.

6. Bailey, R.,Bieger, K., Arnold, J., Bosch, D. (2020). A new physically-based spatially-distributed groundwater flow module for SWAT+. Hydrology,7,75.

7. Bennett, C., Stewart, R.A., Beal, C.D. (2012). ANN-Based residential water end-use demand forecasting model. Expert Systems with Application, Vol. 40, 4, 1014-1023.

8. Bougadis, J., Adamowski, K., Diduch, R. (2005). Short-Term Municipal Water Demand Forecasting. Hydrological Processes, 19, 1, 137–48.

9. Ghiassi, M., Fa’al, F., Abrishamchi, A. (2017). Large Metropolitan Water Demand Forecasting Using DAN2, FTDNN, and KNN Models: A Case Study of the City of Tehran, Iran. Urban Water Journal, 14, 6,655–59. https://doi.org/10.1080/1573062X.2016.1223858.

10. Grossmann, A., Morlet, J. (1984). Decomposition of Hardy functions intosquare integrable wavelets of constant shape. SIAM. J. Math. Anal. 15,723-736.

11. Li,B., Rodell, M., Kumar, S., Beaudoing, H.K., Getirana, A., Zaitchik, B.F., deGoncalves, L.G., Cossetin, C. etal. (2019). Global GRACE data assimilation for groundwater and drought monitoring: Advances and challenges. Water Resour. Res.55, 7564–7586.

12. Pahlavan, R., Omid, M., Akram, A. (2012). Application of data envelopment analysis for performance assessment and energy efficiency improvement opportunities in greenhouses cucumber production. J. Agr. Sci. Tech. 14, 1465–75.

13. Perez-Valdivia, C., Sauchyn, D., Vanstone, J. (2012). Groundwater levels and teleconnection patterns in the Canadian Prairies. Water Resour. Search, 48(7).

14. Ram, A.P. (2022). Unsupervised Representation Learning of GRACE Improves Groundwater Predictions. Water, 14, 2947.

15. Rodriguez, R.H., Puig, V., Farias, R.L., Flores, J.J.(2017). Short-term demand forecast using a bank of Neural Network Models Trained Using Genetic Algorithms for the Optimal Management of Drinking Water Networks. J. Hydroinform,19. 1-16.

16. Rojas, R., Castilla-Rho, J., Bennison, G., Bridgart, R., Prats, C., Claro, E. (2022). Participatory and Integrated Modelling under Contentious Water Use in Semiarid Basins. Hydrology, 9, 49.

17. Rust, W., Holman, I., Bloomfield, J., Cuthbert, M., Corstanje, R. (2019). Understanding the potential of climate teleconnections to projectfuture groundwater drought. Hydrology and Earth System Sciences Discussions, 1–35.

18. Schumacher, M., Forootan, E., vanDijk, A.I., Schmied, H.M., Crosbie, R.S., Kusche,J., Döll,P. (2018). Improvingdroughtsimulationswithin the Murray-Darling Basin by combined calibration/assimilation of GRACE data into the WaterGAP Global HydrologyModel. Remote Sens. Environ.204, 212–228.

19. Shevchenko, O., Skorbun, A., Osadchyi, V., Osadcha, N., Grebin, V., Osypov, V. (2022). Cyclicities in the regime of groundwater and of meteorological factors in the basin of the Southern Bug River. Water,14(14), 2228.

20. Shin, M., Moon, S., Kang, K., Moon, D., Koh, H. (2020). Analysis of Groundwater Level Variations Caused by the Changesin Groundwater Withdrawals Using Long Short-Term Memory Network. Hydrology, 7,64.

21. Tiwari, Mukesh K., Adamowski, J. (2013). Urban water demand forecasting and uncertainty assessment using ensemble wavelet-Bootstrap-Neuralnet work models. Water resources research, 49. 6486–6507.

22. Van Loon, A.F. Hydrological drought explained. WIREs Water. (2015). Vol. 2, 4, 359-392.