Hydrological modelling, essential for water resources management, can be very complex in karst catchments with different climatic and geologic characteristics. In this study, three combined ...conceptual models incorporating the snow module with machine learning models were used for hourly rainfall-runoff modelling in the mostly karst Ljubljanica River catchment, Slovenia. Wavelet-based Extreme Learning Machine (WELM) and Wavelet-based Regression Tree (WRT) machine learning models were integrated into the conceptual CemaNeige Génie Rural à 4 paramètres Horaires (CemaNeige GR4H). In this regard, the performance of the hybrid models was compared with stand-alone conceptual and machine learning models. The stand-alone WELM and WRT models using only meteorological variables performed poorly for hourly runoff forecasting. The CemaNeige GR4H model as stand-alone model yielded good performance; however, it overestimated low flows. The hybrid CemaNeige GR4H-WELM and CemaNeige-WRT models provided better simulation results than the stand-alone models, especially regarding the extreme flows. The results of the study demonstrated that using different variables from the conceptual model, including the snow module, in the machine learning models as input data can significantly affect the performance of rainfall-runoff modelling. The hybrid modelling approach can potentially improve runoff simulation performance in karst catchments with diversified geological formations where the rainfall-runoff process is more complex.
The karst aquifer of the Ljubljanica River catchment, which has numerous springs and sinks, presents an interesting environment for studying hydrogeological processes. This study aims to explore the ...behavior of U isotopes and to evaluate their use as tracers of hydrogeochemical processes as an alternative to classical geochemical tracers (i.e., physicochemical parameters, elemental ratios, and alkalinity) involved in water–rock interactions and water flow in this karst water system. Basic hydrochemical parameters, as well as the spatiotemporal variations of total U concentrations, 234U/238U activity ratios, and δ238U values, were monitored in water samples from springs and sinks under different hydrological conditions. The bedrock as the source of dissolved and detrital U was also analyzed. Multi-collector inductively couple plasma-mass spectrometry results reveal variations of the 234U/238U activity ratios, which are consistently negatively correlated with the discharge at most analyzed sites. Large 238U/235U isotope fractionation occurred during bedrock weathering, and the large variability of the measured δ238U values is seemingly unrelated to the lithological characteristics of the bedrock or discharge. Our results confirm that 234U/238U activity ratios in water can be used as a tracer for studying changes in groundwater flows and the mixing of waters of different origins under different hydrological conditions.