The spatially distributed hydrologic model WetSpa working on a daily or hourly time scale combines elevation, soil and landuse data within GIS, to predict flood hydrographs and spatial distribution of hydrologic characteristics in a watershed. The model is applied to the Margecany-Hornad river basin (1,131 km 2 ) located in Slovakia. Daily hydrometeorological data from 1991 to 2000, including precipitation data from nine stations, temperature data from four stations and evaporation data measured at one station are used as input to the model. Three base maps, i.e., DEM, landuse and soil types are prepared in GIS form, using 100×100 m cell size. Results of the simulations show good agreement between calculated and measured hydrographs at the outlet of the basin. The model predicts the daily/hourly hydrographs with good accuracy, between 75-80% according to the Nash-Sutcliff criteria. For assessing the impact of forests on floods, the calibrated model is applied for a reforestation scenario using the hourly data of the summer of 2001. The scenario considers a 50% increase of forest areas. The model results show that the reforestation scenario decreases the peak discharge by 12%. Investigation of peak discharges from the whole simulation period, shows that the scenario results are reduced by 18% on average. Also, the time to peak of the simulated hydrograph of the reforestation scenario is 14 h longer than for the present landuse. The results show that the effect of land cover on flood is strongly related to storm characteristics and antecedent soil moisture.

The spatially distributed hydrologic model WetSpa combines elevation, soil and land use data within GIS, to predict flood hydrographs and spatial distribution of hydrologic characteristics in a watershed. The model is applied to the Margecany-Hornad river basin (1131 km2) in Slovakia. Daily hydrometeorological data from 1991-2000, including precipitation data from nine stations, temperature data from four stations and evaporation data measured at one station are used as input to the model. Three base maps, i.e. DEM, land use and soil type are prepared in GIS form, using 100 x 100 m cell size. Results of the simulations show good agreement between calculated and measured hydrographs. The model predicts the daily/hourly hydrographs with 75-80% accuracy according to the Nash-Sutcliff criteria. For assessing the impact of land use changes on floods, the calibrated model is applied for a reforestation scenario, which considers a 50% increase of forest areas. The model results show that the reforestation scenario decreases the peak discharge by 12%. Investigation of peak discharges from the whole simulation period, shows that the scenario results are reduced by 18% on average, while for small discharges the reduction is even about 34%. The time to peak of the simulated hydrograph of the reforestation scenario is 20 hours longer than for the present land use.

A comprehensive, GIS-based modelling approach is developed to estimate runoff and phosphorus transport within a watershed at a daily time step. The approach relies on the use of GIS data for deriving major critical model parameters that exhibit distinct spatial variability over the catchment. Surface runoff is calculated by a modified rational method, which depends upon rainfall intensity, soil moisture status, slope, land-use and soil characteristics. Phosphorus loading is estimated as a function of the runoff volume and the event mean concentration for different land use categories. A diffusive approximation method is used to trace runoff and phosphorus transport to the basin outlet. The modelling approach is tested in the Margecany catchment, Hornad River basin, Slovakia, to simulate runoff, phosphorus loading, and its transport on a daily time scale using data observed between 1995 and 2000. Satisfactory results of the hydrographs and phosphorus concentration at the basin outlet are obtained, though more efforts regarding the phosphorus cycling and its biochemical reactions need to be clarified by further research. Figure 4. Unit response functions with l ¼ 0.0003/s: (a) IUHs for a fixed travel time of 3600 s and different standard deviations, and (b) IUHs for a fixed standard deviation of 3600 s and different travel times

<p>The summers of 2017 to 2020 were characterized by exceptional dry spells throughout Europe. Climate models show that such periods of drought could occur more frequently and become even more extreme in the future. The recent periods of intense droughts lead to significant ecological, economic and even societal damages in Flanders (Belgium). During these summers, receding groundwater levels were observed throughout Flanders that reached historical low levels. To monitor low ground water levels and to support a proactive drought management, the Flemish government developed an operational ground water indicator. This indicator gives an overview of the current phreatic ground water levels combined with a prediction for the next month for a selected number of phreatic wells. To increase the spatial resolution of the indicator, we developed a novel data driven regional ground water model for phreatic aquifers.</p><p>The ML model combines a gradient boosting decision tree model (CatBoost) with a Long Short Term Memory (LSTM) network. CatBoost is used to model the average ground water depth at each location. This value is passed to the LSTM network that predicts the temporal evolution of the groundwater at each location around its average. The training dataset for the CatBoost model contains the average groundwater depth of 5.673 wells spread across Flanders and a large set of explanatory variables related to soil texture, distance to a drainage, geology, topography, meteorology and land use. The model performance is evaluated using cross-validation which showed the model generalizes well with a mean absolute error of 69cm. The most important explanatory variables for the model are the thickness of the phreatic aquifer, the vertical distance to closest drain, the topographic index and the precipitation surplus.</p><p>The training dataset for the LSTM model contains 408 wells that have sufficiently long and reliable observations for training. The input data to the LSTM consists of rainfall and evapotranspiration up to 10 years prior to each observation, combined with the same explanatory variables as the CatBoost model. A single regional LSTM model is trained on all 408 wells simultaneously. The resulting model is accurate with a median RMSE of 20cm for the validation data, outperforming the currently used SWAP models [1]. The ML model is however less performant in simulating the higher ground water depths during summer and shows a consistent bias towards lower ground water depths during long dry spells.</p><p>[1] Kroes, J.G., J.C. van Dam, R.P. Bartholomeus, P. Groenendijk, M. Heinen, R.F.A. Hendriks, H.M. Mulder, I. Supit, P.E.V. van Walsum, 2017. SWAP version 4; Theory description and user manual. Wageningen, Wageningen Environmental Research, Report 2780</p>