Intercomparing the robustness of machine learning models in simulation and forecasting of streamflow

The intercomparison of streamflow simulation and the prediction of discharge using various renowned machine learning techniques were performed. The daily streamflow discharge model was developed for 35 observation stations located in a large-scale river basin named Cauvery. Various hydrological indices were calculated for observed and predicted discharges for comparing and evaluating the replicability of local hydrological conditions. The model variance and bias observed from the proposed extreme gradient boosting decision tree model were less than 15%, which is compared with other machine learning techniques considered in this study. The model Nash–Sutcliffe efficiency and coefficient of determination values are above 0.7 for both the training and testing phases which demonstrate the effectiveness of model performance. The comparison of monthly observed and model-predicted discharges during the validation period illustrates the model's ability in representing the peaks and fall in high-, medium-, and low-flow zones. The assessment and comparison of hydrological indices between observed and predicted discharges illustrate the model's ability in representing the baseflow, high-spell, and low-spell statistics. Simulating streamflow and predicting discharge are essential for water resource planning and management, especially in large-scale river basins. The proposed machine learning technique demonstrates significant improvement in model efficiency by dropping variance and bias which, in turn, improves the replicability of local-scale hydrology.

Application of Methodologies for Environmental Flow Determination in an Andean and a Mediterranean Basin

The demand for sustainable water management has promoted the development of methodologies for estimating environmental flows (EF). In this paper, the EF in an Andean river (Pance, Colombia) for conservation and a Mediterranean river (Wadi-Zomar, Palestine) for restoration purposes is made. Different methodologies are applied given the objectives for each river. The authors used hydrological indices proposed for watersheds with different water regimes and adaptations and validations were made to the local context. These methods allow for estimating the EF at various points in the river and the assessment of disruption scenarios for decision-making. In the Wadi Zomar River, three sampling points were selected. The water samples were then examined for the presence of pathogens. No one indicator or simple hydrological parameter is entirely suitable for all environmental systems and pathogens. In the base flow conditions, the amount of pollutant load varied temporally according to the amount of load from point sources along the Wadi, and spatially with distance from the same sources. Significant variation was observed in response to the hydrological behavior of the catchment. The assessment for the water quality in the Zomar reflects a potentially serious threat to the environment. The results emphasize the need for regulating the seepage effluent from industries and sewage system along the stream.

Application of Methodologies for Environmental Flow Determination in an Andean and a Mediterranean Basin

The demand for sustainable water management has promoted the development of methodologies for estimating environmental flows (EF). In this paper, the EF in an Andean river (Pance, Colombia) for conservation and a Mediterranean river (Wadi-Zomar, Palestine) for restoration purposes is made. Different methodologies are applied given the objectives for each river. The authors used hydrological indices proposed for watersheds with different water regimes and adaptations and validations were made to the local context. These methods allow for estimating the EF at various points in the river and the assessment of disruption scenarios for decision-making. In the Wadi Zomar River, three sampling points were selected. The water samples were then examined for the presence of pathogens. No one indicator or simple hydrological parameter is entirely suitable for all environmental systems and pathogens. In the base flow conditions, the amount of pollutant load varied temporally according to the amount of load from point sources along the Wadi, and spatially with distance from the same sources. Significant variation was observed in response to the hydrological behavior of the catchment. The assessment for the water quality in the Zomar reflects a potentially serious threat to the environment. The results emphasize the need for regulating the seepage effluent from industries and sewage system along the stream.