Accurate forecasting of river flows is essential for effective water resource management, flood risk reduction and environmental protection. The ongoing effects of climate change, in particular the shift in precipitation patterns and the increasing frequency of extreme weather events, necessitate the development of advanced forecasting models. This study investigates the application of long short-term memory (LSTM) neural networks in predicting river runoff in the Velika Morava catchment in Serbia, representing a pioneering application of LSTM in this region. The study uses daily runoff, precipitation and temperature data from 1961 to 2020, interpolated using the inverse distance weighting method. The LSTM model, which was optimized using a trial-and-error approach, showed a high prediction accuracy. For the Velika Morava station, the model showed a mean square error (MSE) of 2936.55 and an R² of 0.85 in the test phase. The findings highlight the effectiveness of LSTM networks in capturing nonlinear hydrological dynamics, temporal dependencies and regional variations. This study underlines the potential of LSTM models to improve river forecasting and water management strategies in the Western Balkans.

Hydrological drought projections are crucial for climate-resilient water management; however, many basins lack calibrated process-based models that can readily be forced with climate scenarios. This study develops a purely data-driven framework to forecast the Streamflow Drought Index (SDI) from standardized meteorological indices and to assess future drought regimes under different emission pathways. We used a 60-year monthly record (1961–2020) of the Standardized Precipitation Index (SPI), the Standardized Temperature Index (STI), the Standardized Precipitation–Evapotranspiration Index (SPEI), and the SDI for the Sava River Basin. Correlation analysis showed that the SDI is primarily controlled by the short-lag SPI (0–1 months), whereas the STI and SPEI play a minor role. Several machine learning models were tested for one-month-ahead SDI prediction; a Random Forest (RF) with hyperparameters optimized by TimeSeriesSplit cross-validation, combined with linear-scaling bias correction, clearly outperformed XGBoost, Elastic Net, support vector regression, and a multilayer perceptron. On the independent test period (2009–2020), the RF achieved MAE ≈ 0.62, RMSE ≈ 0.83, NSE ≈ 0.49, and KGE ≈ 0.65. Using SPI/STI/SPEI projections from RCP2.6, RCP4.5, and RCP8.5, the RF produced monthly SDI projections for 2021–2050, revealing increasingly frequent, severe, and persistent streamflow droughts with higher emissions. The results demonstrate that carefully tuned ensemble tree models driven solely by standardized climate indices can provide skilful and interpretable SDI projections for drought risk assessment, supporting sustainable, climate-resilient water resources planning and adaptation in this transboundary basin.

Accurate forecasting of river discharge is critical for the sustainable management of water resources, influencing applications such as irrigation planning, flood and drought mitigation, and infrastructure development. This study investigates the application of the Seasonal Autoregressive Integrated Moving Average (SARIMA) model to forecast minimum monthly discharges of the Danube River, addressing challenges posed by nonlinear and time-dependent hydrological processes. The study utilizes an extensive dataset comprising daily discharge records from ten stations across seven countries, spanning over a century. Monthly minimum discharges were computed and analyzed to identify long-term trends and seasonal patterns. The SARIMA model was selected for its proven ability to capture seasonal variations and optimize forecasting accuracy in da-ta-limited environments. Model performance was evaluated using statistical measures such as mean absolute error and root mean square error with results indicating robust predictive capabilities across the studied stations. The findings reveal significant vari-ability in discharge trends, with notable decreasing trends in minimum flows at several upstream and midstream stations, highlighting potential impacts of climate change and anthropogenic influences. In contrast, downstream stations exhibited relatively stable discharge patterns. These insights underscore the need for adaptive water manage-ment strategies to mitigate the risks associated with decreasing low flows. The study demonstrates the utility of SARIMA models in hydrological forecasting and provides a foundation for future research exploring hybrid modeling approaches incorporating climate variables. The results offer valuable inputs for policymakers and stakeholders in managing water resources under evolving climatic conditions.

This study integrates 90 years of hydrometeorological observations (1930/31–2019/20) with end-century projections (2080–2099) to evaluate climate-driven changes in the water balance of the Nitra River basin (2094 km²), Slovakia. Despite a modest 2–3% increase in annual precipitation from 1930/31–1959/60 to 1990/91–2019/20, mean annual runoff declined from 229 mm to 201 mm (≈−12%), primarily due to enhanced evapotranspiration stemming from a +1.08 °C basin-wide temperature increase. An empirical regression from 90 hydrological years shows that +100 mm in precipitation boosts runoff by ≈41 mm, while +1 °C in temperature reduces it by ≈13 mm. The BILAN monthly water balance model was calibrated for 1930/31–2019/20 to decompose runoff components. Over the 90-year period, the modeled annual runoff averaged 222 mm, comprising a 112 mm baseflow (50.4%), a 91 mm interflow (41.0%), and a 19 mm direct runoff (8.6%), underscoring the key role of groundwater and subsurface flows in sustaining streamflow. In the second part of our study, the monthly water balance model BILAN was recalibrated for 1995–2014 to simulate future runoff under three CMIP6 Shared Socioeconomic Pathways. Under the sustainability pathway SSP1-1.9 (+0.88 °C; +1.1% precipitation), annual runoff decreases by 8.9%. The middle-of-the-road scenario SSP2-4.5 (+2.6 °C; +3.1% precipitation) projects a 17.5% decline in annual runoff, with particularly severe reductions in autumn months (September −32.3%, October −35.8%, December −40.4%). The high-emission pathway SSP5-8.5 (+5.1 °C; +0.4% precipitation) yields the most dramatic impact with a 35.2% decrease in annual runoff and summer deficits exceeding 45%. These results underline the extreme sensitivity of a mid-sized Central European basin to temperature-driven evapotranspiration and the critical importance of emission mitigation, emphasizing the urgent need for adaptive water management strategies, including new storage infrastructure to address both winter floods and intensifying summer droughts.

Reliable projections of hydrological drought are essential for climate-resilient water management; however, many basins lack calibrated, process-based models. Here, we develop and test a purely data‑driven framework to forecast the Streamflow Drought Index (SDI) for the Sava River basin, using only widely available meteorological drought indices, and apply it to project future drought conditions under different climate scenarios. We assembled a monthly dataset for 1961–2020 comprising the Standardized Precipitation Index (SPI), a standardised temperature index (STI), the Standardised Precipitation–Evapotranspiration Index (SPEI), and SDI derived from observed streamflow. All indices are approximately standardised and show frequent negative excursions, indicating recurrent meteorological and hydrological droughts. Correlation analysis revealed that short-term precipitation anomalies significantly influence the linear control of SDI. Specifically, SPI at a one-month lag exhibits the strongest association (r ≈ 0.50), followed by contemporaneous SPI (r ≈ 0.44) and a two-month lag (r ≈ 0.24). By contrast, STI and SPEI lags exhibit negligible correlations, indicating that temperature-driven evaporative demand plays a secondary role in the initial onset of drought in this temperate, precipitation-dominated basin. We evaluated several machine-learning models for one-month-ahead SDI prediction, including Random Forest (RF), XGBoost, Elastic Net, Support Vector Regression (SVR), and a Multilayer Perceptron. Models were trained on the first 80% of the record and evaluated on the remaining 20% using a strictly chronological split. For RF, key hyperparameters (number of trees, maximum depth, leaf size and feature subsampling) were tuned using Randomized Search with Time Series Split cross‑validation. A linear‑scaling bias correction was applied to align the mean and variance of predicted SDI with observations in the training period. Random Forest clearly outperformed the alternative models. In the independent test period (2009–2020), the bias‑corrected RF achieved MAE ≈ 0.62, RMSE ≈ 0.83, and NSE ≈ 0.49, explaining almost half the variance in SDI. KGE ≈ 0.65 indicates good joint reproduction of correlation, variability and bias. The model accurately captured the timing and sign of most wet and dry episodes, while moderately underestimating the most extreme peaks. Other algorithms exhibited similar or larger errors and substantially lower KGE, confirming RF as the most suitable SDI forecasting approach in this index‑only setting. Finally, we drove the optimised RF with SPI/STI/SPEI projections from RCP2.6, RCP4.5 and RCP8.5 to generate monthly SDI projections for 2021–2050. Hydrostripes and distributions show clear scenario‑dependent changes: RCP2.6 maintains mainly mild, short‑lived droughts; RCP4.5 produces more persistent and clustered deficits; and RCP8.5 yields the most frequent and severe hydrological droughts. The framework demonstrates that a carefully tuned Random Forest, using only standardised meteorological indices, can provide skilful and interpretable SDI projections to support climate‑informed drought risk management.Acknowledgment: This research was supported by the “Streamflow Drought Through Time” project funded by the EU NextGenerationEU through the Recovery and Resilience Plan of the Slovak Republic within the framework of project no. 09I03-03-V04-00186.