No abstract

Introduction 2 The Glinščica River Catchment 3 Model Simulations 4 Cost-Benefit Analysis 4.1 Cost of Afforestation 4.2 Benefits of Flood Protection Measures 4.3 Biodiversity 4.4 Carbon 4.5 Recreation 4.6 Water Quality 5 Results and Discussion 6 Conclusion References

It is not clear how projected climate change will impact the hydrological functioning of complex catchments that have significant karst characteristics. Therefore, in this paper we focused on the investigation of the low- and high-flow characteristics of the karst Ljubljanica River catchment. One smaller (51 km2) and one larger (1135 km2) catchment were selected in order to investigate the projected climate change impact on the hydrological conditions. For the investigation of the hydrological situation in the future, we used a lumped conceptual hydrological model. The model was calibrated using past measured daily data. Using the calibrated model, we investigated the impact of five different climate models outputs for the moderately optimistic scenario (RCP4.5). We investigated the situation in next 30-years periods: 2011–2040, 2041–2070, and 2071–2100. Several low and high-flow indices were calculated and compared. The results indicate that a summer precipitation decrease (i.e., 2011–2070) could lead to lower low-flow values for the investigated areas, which could increase the vulnerability of karst areas. Thus, additional focus should be given to water resource management in karst areas. On the other hand, mean flow could increase in the future. The same also applies for the high-flows where flood frequency analysis results indicate that a climate adaptation factor could be used for the hydrotechnical engineering design. However, differences among investigated models are large and show large variability among investigated cases.

Reservoir inflow forecasting is extremely important for the management of a reservoir. In practice, accurate forecasting depends on the feature learning performance. To better address this issue, this paper proposed a feature-enhanced regression model (FER), which combined stack autoencoder (SAE) with long short-term memory (LSTM). This model had two constituents: (1) The SAE was constructed to learn a representation as close as possible to the original inputs. Through deep learning, the enhanced feature could be captured sufficiently. (2) The LSTM was established to simulate the mapping between the enhanced features and the outputs. Under recursive modeling, the patterns of correlation in the short term and dependence in the long term were considered comprehensively. To estimate the performance of the FER model, two historical daily discharge series were investigated, i.e., the Yangtze River in China and the Sava Dolinka River in Slovenia. The proposed model was compared with other machine-learning methods (i.e., the LSTM, SAE-based neural network, and traditional neural network). The results demonstrated that the proposed FER model yields the best forecasting performance in terms of six evaluation criteria. The proposed model integrates the deep learning and recursive modeling, and thus being beneficial to exploring complex features in the reservoir inflow forecasting. Moreover, for smaller catchments with significant torrential characteristics, more data are needed (e.g., at least 20 years) to effectively train the model and to obtain accurate flood-forecasting results.