COMPARATIVE ANALYSIS OF MACHINE LEARNING MODELS FOR DISCHARGE PREDICTION: A CASE STUDY AT THE BRATISLAVA STATION ON THE DANUBE RIVER
DOI:
https://doi.org/10.2298/IJGI251106012LKeywords:
river discharge forecasting, machine learning models, hydrological prediction, time series analysis, Danube RiverAbstract
This study investigates the prediction of river flows for water resource management, flood and drought protection and hydropower planning, focusing on the limitations of traditional hydrological models due to complex data requirements. Machine learning (ML) models offer a solution by capturing non-linear relationships to improve prediction accuracy. We compare the performance of three data-driven models: Random Forest (RF), Gradient Boosting (GB), and Seasonal Autoregressive Integrated Moving Average (SARIMA), with a simple Linear Regression (LR) benchmark for monthly discharge forecasting at the Bratislava station on the Danube River. RF model performed best, with an MAE of 165.84 and an R² of 0.89. GB achieved moderate results (MAE = 335.15; R² = 0.60), while SARIMA performed below average (MAE= 550.78; R² = 0.01). Results are valid within a univariate autoregressive framework; multivariate extensions incorporating meteorological drivers are recommended for operational deployment. These results underline the potential of machine learning models, especially RF, for forecasting monthly river discharge up to 24 months in advance at the Bratislava gauging station on the Danube River. While these findings are based on a single-station, univariate analysis, they contribute to the growing body of evidence supporting the use of ensemble machine learning methods in operational hydrology for large regulated river systems. Transferability to other stations or basins would require further validation.
Article metrics
References
Aghakhani, A., Robertson, D. E., & Pauwels, V. R. N. (2025). Uncovering a Key Predictors for Enhancing Daily Streamflow Simulation Using Machine Learning. EGUsphere. https://doi.org/10.5194/egusphere-2025-553
Ahmadpour, A., Mirhashemi, S., Haghighat jou, P., & Foroughi, F. (2023). Correction: Comparison of the monthly streamflow forecasting in Maroon dam using HEC-HMS and SARIMA models. Sustainable Water Resources Management, 9(4), Article 99. https://doi.org/10.1007/s40899-023-00862-x
Ali, M., Prasad, R., Xiang, Y., & Yaseen, Z. M. (2020). Complete ensemble empirical mode decomposition hybridized with random forest and kernel ridge regression model for monthly rainfall forecasts. Journal of Hydrology, 584, Article 124647. https://doi.org/10.1016/j.jhydrol.2020.124647
Blöschl, G., Hall, J., Viglione, A., Perdigão, R. A. P., Parajka, J., Merz, B., Lun, D., Arheimer, B., Aronica, G. T., Bilibashi, A., Boháč, M., Bonacci, O., Borga, M., Čanjevac, I., Castellarin, A., Chirico, G. B., Claps, P., Frolova, N., Ganora, D., . . . Živković, N. (2019). Changing climate both increases and decreases European river floods. Nature, 573(7772), 108–111. https://doi.org/10.1038/s41586-019-1495-6
Chen, S., Feng, Y., Li, H., Ma, D., Mao, Q., Zhao, Y., & Liu, J. (2024). Enhancing runoff predictions in data-sparse regions through hybrid deep learning and hydrologic modeling. Scientific Reports, 14(1), Article 26450. https://doi.org/10.1038/s41598-024-77678-y
Cheng, M., Fang, F., Kinouchi, T., Navon, I. M., & Pain, C. C. (2020). Long lead-time daily and monthly streamflow forecasting using machine learning methods. Journal of Hydrology, 590, Article 125376. https://doi.org/10.1016/j.jhydrol.2020.125376
Clark, S. R., & Jaffrés, J. B. D. (2025). Associations between deep learning runoff predictions and hydrogeological conditions in Australia. Journal of Hydrology, 651, Article 132569. https://doi.org/10.1016/j.jhydrol.2024.132569
Defontaine, T. (2024). Extending Flood Forecast Lead Time Using Machine Learning on Limited and Heterogeneous Datasets [Doctoral dissertation, Institut National Polytechnique de Toulouse]. https://cnrs.hal.science/tel-04749435
Dikshit, A., Pradhan, B., & Alamri, A. M. (2020). Temporal Hydrological Drought Index Forecasting for New South Wales, Australia Using Machine Learning Approaches. Atmosphere, 11(6), Article 585. https://doi.org/10.3390/atmos11060585
Fang, W., Ren, K., Liu, T., Shang, J., Jia, S., Jiang, X., & Zhang, J. (2024). An evaluation of random forest based input variable selection methods for one month ahead streamflow forecasting. Scientific Reports, 14(1), Article 29766. https://doi.org/10.1038/s41598-024-81502-y
Farfán-Durán, J. F., & Cea, L. (2024). Streamflow forecasting with deep learning models: A side-by-side comparison in Northwest Spain. Earth Science Informatics, 17(6), 5289–5315. https://doi.org/10.1007/s12145-024-01454-9
Fernández-Delgado, M., Sirsat, M. S., Cernadas, E., Alawadi, S., Barro, S., & Febrero-Bande, M. (2019). An extensive experimental survey of regression methods. Neural Networks, 111, 11–34. https://doi.org/10.1016/j.neunet.2018.12.010
Firat, M., Dikbas, F., Koc, A. C., & Gungor, M. (2012). Analysis of temperature series: Estimation of missing data and homogeneity test. Meteorological Applications, 19(4), 397–406. https://doi.org/10.1002/met.271
Friedman, J. (2001). Greedy function approximation: A gradient boosting machine. Annals of Statistics, 29(5), 1189–1232. https://doi.org/10.1214/AOS/1013203451
Galdelli, A., Fronzi, D., Narang, G., Mancini, A., & Tazioli, A. (2025). Groundwater level forecasting using data-driven models and vadose zone: A comparative analysis of ARIMA, SARIMAX, Prophet, and NeuralProphet. Applied Computing and Geosciences, 28, Article 100304. https://doi.org/10.1016/j.acags.2025.100304
Grenier, M., Boudreault, J., Raymond, S., & Boudreault, M. (2024). Projected seasonal flooding in Canada under climate change with statistical and machine learning. Journal of Hydrology: Regional Studies, 53, Article 101754. https://doi.org/10.1016/j.ejrh.2024.101754
Gupta, H. V., Kling, H., Yilmaz, K. K., & Martinez, G. F. (2009). Decomposition of the mean squared error and NSE performance criteria: Implications for improving hydrological modelling. Journal of Hydrology, 377(1), 80–91. https://doi.org/10.1016/j.jhydrol.2009.08.003
Haghdoost, M., & Md Azamathulla, H. (2024). Predicting the drag coefficient of coastal trees using Support Vector Machines and boosting ensemble models. Discover Water, 4(1), Article 102. https://doi.org/10.1007/s43832-024-00162-1
Halmová, D., Pekárová, P., Pekár, J., Miklánek, P., & Bačová Mitková, V. (2021). Identification of the historical drought occurrence on the Danube River and its tributaries. Acta Hydrologica Slovaca, 22(2), 237–247. https://doi.org/10.31577/ahs-2021-0022.02.0027
Hansen, J. V., & Nelson, R. D. (2003). Time-series analysis with neural networks and ARIMA-neural network hybrids. Journal of Experimental & Theoretical Artificial Intelligence, 15(3), 315–330. https://doi.org/10.1080/0952813031000116488
Hauswirth, S. M., Bierkens, M. F. P., Beijk, V., & Wanders, N. (2021). The potential of data driven approaches for quantifying hydrological extremes. Advances in Water Resources, 155, Article 104017. https://doi.org/10.1016/j.advwatres.2021.104017
Ikeagwuani, C. C. (2021). Estimation of modified expansive soil CBR with multivariate adaptive regression splines, random forest and gradient boosting machine. Innovative Infrastructure Solutions, 6(4), 1–16. https://doi.org/10.1007/s41062-021-00568-z
Jahanshahi, A., Asadi, H., & Gupta, H. (2025). A data fusion approach to enhancing runoff simulation in a semi-arid river basin. Environmental Modelling & Software, 190, Article 106468. https://doi.org/10.1016/j.envsoft.2025.106468
Ji, Y., Lim, Y., Kim, D., Sung, J., & Kang, B. (2025). Effects of Forecasted Rainfall on Direct and Recursive LSTM-Based River Water Level Predictions. Journal of Flood Risk Management, 18(4), Article e70147. https://doi.org/10.1111/jfr3.70147
Kabbilawsh, P., Kumar, D. S., & Chithra, N. R. (2022). Forecasting long-term monthly precipitation using SARIMA models. Journal of Earth System Science, 131(3), 1–11. https://doi.org/10.1007/s12040-022-01927-9
Kedam, N., Tiwari, D. K., Kumar, V., Khedher, M. K., & Salem, M. A. (2024). River stream flow prediction through advanced machine learning models for enhanced accuracy. Results in Engineering, 22, Article 102215. https://doi.org/10.1016/j.rineng.2024.102215
Khodakhah, H., Aghelpour, P., & Hamedi, Z. (2022). Comparing linear and non-linear data-driven approaches in monthly river flow prediction, based on the models SARIMA, LSSVM, ANFIS, and GMDH. Environmental Science and Pollution Research, 29(15), 21935–21954. https://doi.org/10.1007/s11356-021-17443-0
Khozani, Z. S., Precht, E., & Ionita, M. (2025). Weekly streamflow forecasting of Rhine river based on machine learning approaches. Natural Hazards, 121(4), 4135–4153. https://doi.org/10.1007/s11069-024-06962-x
Kilinc, H. C., Ahmadianfar, I., Demir, V., Heddam, S., Al-Areeq, A. M., Abba, S. I., Tan, M. L., Halder, B., Marhoon, H. A., & Yaseen, Z. M. (2023). Daily scale river flow forecasting using hybrid gradient boosting model with genetic algorithm optimization. Water Resources Management, 37(9), 3699–3714. https://doi.org/10.1007/s11269-023-03522-z
Konapala, G., Kao, S.-C., Painter, S. L., & Lu, D. (2020). Machine learning assisted hybrid models can improve streamflow simulation in diverse catchments across the conterminous US. Environmental Research Letters, 15(10), Article 104022. https://doi.org/10.1088/1748-9326/aba927
Kron, W., Eichner, J., & Kundzewicz, Z. W. (2019). Reduction of flood risk in Europe – Reflections from a reinsurance perspective. Journal of Hydrology, 576, 197–209. https://doi.org/10.1016/j.jhydrol.2019.06.050
Kumar, V., Kedam, N., Sharma, K. V., Mehta, D. J., & Caloiero, T. (2023). Advanced Machine Learning Techniques to Improve Hydrological Prediction: A Comparative Analysis of Streamflow Prediction Models. Water, 15(14), Article 2572. https://doi.org/10.3390/w15142572
Kurian, C., Sudheer, K. P., Vema, V. K., & Sahoo, D. (2020). Effective flood forecasting at higher lead times through hybrid modelling framework. Journal of Hydrology, 587, Article 124945. https://doi.org/10.1016/j.jhydrol.2020.124945
Leščešen, I., Pekárová, P., & Bajtek, Z. (2025). Navigating hydrological extremes: SARIMA forecasting of minimum Danube River discharges. Journal of the Bulgarian Geographical Society 53, 29–47. https://doi.org/10.3897/jbgs.e159722
Leščešen, I., Tanhapour, M., Pekárová, P., Miklánek, P., & Bajtek, Z. (2025). Long Short-Term Memory (LSTM) Networks for Accurate River Flow Forecasting: A Case Study on the Morava River Basin (Serbia). Water, 17(6), Article 907. https://doi.org/10.3390/w17060907
Liu, Z., Zhou, J., Yang, X., Zhao, Z., & Lv, Y. (2024). Research on water resource modeling based on machine learning technologies. Water, 16(3), 1–26. https://doi.org/10.3390/w16030472
Maulud, D., & Abdulazeez, A. M. (2020). A review on linear regression comprehensive in machine learning. Journal of Applied Science and Technology Trends, 1(2), 140–147. https://doi.org/10.38094/jastt1457
Mehta, D., Dhabuwala, J., Yadav, S. M., Kumar, V., & Azamathulla, H. M. (2023). Improving flood forecasting in Narmada river basin using hierarchical clustering and hydrological modelling. Results in Engineering, 20, Article 101571. https://doi.org/10.1016/j.rineng.2023.101571
Mosavi, A., Ozturk, P., & Chau, K.-W. (2018). Flood Prediction Using Machine Learning Models: Literature Review. Water, 10(11), Article 1536. https://doi.org/10.3390/w10111536
Nash, J. E., & Sutcliffe, J. V. (1970). River flow forecasting through conceptual models part I — A discussion of principles. Journal of Hydrology, 10(3), 282–290. https://doi.org/10.1016/0022-1694(70)90255-6
Ni, L., Wang, D., Wu, J., Wang, Y., Tao, Y., Zhang, J., & Liu, J. (2020). Streamflow forecasting using extreme gradient boosting model coupled with Gaussian mixture model. Journal of Hydrology, 586, Article 124901. https://doi.org/10.1016/j.jhydrol.2020.124901
Pham, L. T., Luo, L., & Finley, A. (2021). Evaluation of random forests for short-term daily streamflow forecasting in rainfall- and snowmelt-driven watersheds. Hydrology and Earth System Sciences, 25(6), 2997–3015. https://doi.org/10.5194/hess-25-2997-2021
Rahimzad, M., Moghaddam Nia, A., Zolfonoon, H., Soltani, J., Danandeh Mehr, A., & Kwon, H. H. (2021). Performance comparison of an LSTM-based deep learning model versus conventional machine learning algorithms for streamflow forecasting. Water Resources Management, 35(12), 4167–4187. https://doi.org/10.1007/s11269-021-02937-w
Saleh, Md. A., Rasel, H. M., & Ray, B. (2024). A comprehensive review towards resilient rainfall forecasting models using artificial intelligence techniques. Green Technologies and Sustainability, 2(3), Article 100104. https://doi.org/10.1016/j.grets.2024.100104
Salman, H. A., Kalakech, A., & Steiti, A. (2024). Random Forest Algorithm Overview. Babylonian Journal of Machine Learning, 2024, 69–79. https://doi.org/10.58496/BJML/2024/007
Schneider, T., Ruby Leung, L., & Wills, R. C. J. (2024). Opinion: Optimizing climate models with process knowledge, resolution, and artificial intelligence. Atmospheric Chemistry and Physics, 24(12), 7041–7062. https://doi.org/10.5194/acp-24-7041-2024
Schoppa, L., Disse, M., & Bachmair, S. (2020). Evaluating the performance of random forest for large-scale flood discharge simulation. Journal of Hydrology, 590, Article 125531. https://doi.org/10.1016/j.jhydrol.2020.125531
Sîrbu, N., & Rugină, A.-M. (2026). Short-Term Streamflow Forecasting for River Management, Using ARIMA Models and Recurrent Neural Networks. Hydrology, 13(3), Article 82. https://doi.org/10.3390/hydrology13030082
Talukdar, S., Pal, S., Shahfahad, Naikoo, M. W., Parvez, A., & Rahman, A. (2022). Trend analysis and forecasting of streamflow using random forest in the Punarbhaba River basin. Environmental Monitoring and Assessment, 195(1), Article 153. https://doi.org/10.1007/s10661-022-10696-3
Tramblay, Y., Rutkowska, A., Sauquet, E., Sefton, C., Laaha, G., Osuch, M., Albuquerque, T., Alves, M. H., Banasik, K., Beaufort, A., Brocca, L., Camici, S., Csabai, Z., Dakhlaoui, H., DeGirolamo, A. M., Dörflinger, G., Gallart, F., Gauster, T., Hanich, L., … & Datry, T. (2021). Trends in flow intermittence for European rivers. Hydrological Sciences Journal, 66(1), 37–49. https://doi.org/10.1080/02626667.2020.1849708
Valipour, M. (2015). Long-term runoff study using SARIMA and ARIMA models in the United States. Meteorological Applications, 22(3), 592–598. https://doi.org/10.1002/met.1491
Viero, D. P., Roder, G., Matticchio, B., Defina, A., & Tarolli, P. (2019). Floods, landscape modifications and population dynamics in anthropogenic coastal lowlands: The Polesine (northern Italy) case study. Science of the Total Environment, 651, 1435–1450. https://doi.org/10.1016/j.scitotenv.2018.09.121
Vilaseca, F., Castro, A., Chreties, C., & Gorgoglione, A. (2023). Assessing influential rainfall–runoff variables to simulate daily streamflow using random forest. Hydrological Sciences Journal, 68(12), 1738–1753. https://doi.org/10.1080/02626667.2023.2232356
Wan, X., Wang, W., Liu, J., & Tong, T. (2014). Estimating the sample mean and standard deviation from the sample size, median, range and/or interquartile range. BMC Medical Research Methodology, 14, Article 135. http://www.biomedcentral.com/1471-2288/14/135
Wang, K., Song, Z., Yin, Z., Xu, J., & Cheng, S. (2026). Streamflow reconstruction at the source of the Yangtze River using ensemble machine learning. Journal of Hydrology: Regional Studies, 64, Article 103247. https://doi.org/10.1016/j.ejrh.2026.103247
Wang, X., Jiang, B., & Liu, J. S. (2017). Generalized R-squared for detecting dependence. Biometrika, 104(1), 129–139. https://doi.org/10.1093/biomet/asw071
Yao, S., Chen, C., Chen, Q., Zhang, J., & He, M. (2023). Combining process-based model and machine learning to predict hydrological regimes in floodplain wetlands under climate change. Journal of Hydrology, 626, Article 130193. https://doi.org/10.1016/j.jhydrol.2023.130193
Yaseen, Z. M. (2023). A new benchmark on machine learning methodologies for hydrological processes modelling: A comprehensive review for limitations and future research directions. Knowledge-Based Engineering and Sciences, 4(3), 65–103. https://doi.org/10.51526/kbes.2023.4.3.65-103
Yaseen, Z. M., Kisi, O., & Demir, V. (2016). Enhancing Long-Term Streamflow Forecasting and Predicting using Periodicity Data Component: Application of Artificial Intelligence. Water Resources Management, 30(12), 4125–4151. https://doi.org/10.1007/s11269-016-1408-5
Zhang, X., Wu, X., Zhu, G., Lu, X., & Wang, K. (2022). A seasonal ARIMA model based on the gravitational search algorithm (GSA) for runoff prediction. Water Supply, 22(8), 6959–6977. https://doi.org/10.2166/ws.2022.263
Zhu, Z., Zhou, Y., Chen, G., Zhao, X., Li, Q., & Zhang, W. (2025). Daily runoff prediction modelling using machine learning methods based on meteorological parameters. Hydrology Research, 56(12), 1241–1255. https://doi.org/10.2166/nh.2025.069
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Journal of the Geographical Institute “Jovan Cvijić” SASA
This work is licensed under a Creative Commons Attribution 4.0 International License.
