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.

In this paper, we performed Regional Flood Frequency Analysis (RFFA) by using L-moments and Annual Maximum Series (AMS) methods. Time series of volumes and duration of floods were derived using the threshold level method for 22 hydrological stations in the Pannonian Basin. For flood definition, a threshold set at Q₁₀ was used. The aim of this research is to derive best-fit regional distribution for the four major rivers within the Pannonian Basin and to provide reliable prediction of flood quantiles. The results show that the investigated area can be considered homogeneous (V_i < 1) both for flood volumes (0.097) and durations (0.074). To determine the best-fit regional distribution, the six most commonly used distributions were used. Results obtained by L-moment ratio diagram and Z statistics show that all distributions satisfy the test criteria, but because the Log-Normal distribution has the value closest to zero, it can be selected as the best-fit distribution for the volumes (0.12) and durations (0.25) of floods.

Regional flood frequency analysis (RFFA) is a powerful method for interrogating hydrological series since it combines observational time series from several sites within a region to estimate risk-relevant statistical parameters with higher accuracy than from single-site series. Since RFFA extreme value estimates depend on the shape of the selected distribution of the data-generating stochastic process, there is need for a suitable goodness-of-distributional-fit measure in order to optimally utilize given data. Here we present a novel, least-squares-based measure to select the optimal fit from a set of five distributions, namely Generalized Extreme Value (GEV), Generalized Logistic, Gumbel, Log-Normal Type III and Log-Pearson Type III. The fit metric is applied to annual maximum discharge series from six hydrological stations along the Sava River in South-eastern Europe, spanning the years 1961 to 2020. Results reveal that (1) the Sava River basin can be assessed as hydrologically homogeneous and (2) the GEV distribution provides typically the best fit. We offer hydrological-meteorological insights into the differences among the six stations. For the period studied, almost all stations exhibit statistically insignificant trends, which renders the conclusions about flood risk as relevant for hydrological sciences and the design of regional flood protection infrastructure.

Hydrological drought poses significant challenges to water resources, ecosystems, and human activities, necessitating comprehensive investigation. Monthly streamflow data from 12 monitoring stations across the Sava River basin were utilized to compute the streamflow drought index (SDI). The Mann–Kendall test evaluated trends, and the SDI's hydrological states were classified based on cumulative streamflow volumes. The study identified an alarming 83.3% of stations exhibiting statistically significant decreases in summer streamflow, indicating a widespread and concerning trend of declining water availability in the Sava River basin. Drought severity was particularly pronounced in tributaries such as the Vrbas and Bosna rivers, emphasizing the heterogeneous nature of hydrological changes. These findings underscore the urgent need for adaptive water resource management strategies in the face of escalating hydrological drought risks, especially given the far-reaching consequences on agriculture, industry, ecosystems, and social well-being. The study provides crucial insights for developing targeted resilience measures tailored to the specific challenges presented by the diverse hydrological conditions in the Sava River basin.

Floods are one of the most common natural hazards and as such, they are causing a great loss of human life as well as great economic damages. Flood frequency analysis (FFA) is still an active...

This study examined the association between precipitation indices and atmospheric processes in Southeast Europe using ERA5 land data from 1961 to 2020. The Rx1day intensity index showed predominantly positive trends in heavy precipitation events, resulting in more intense precipitation over fewer days in various parts of Southeast Europe, particularly during autumn. These findings highlight the potential increase in extreme precipitation frequency and intensity due to ongoing climate change, leading to an elevated risk of flood events. Such insights provide valuable information for policymakers and stakeholders to adapt to the impacts of extreme precipitation events.