Rainfall–runoff modeling has been of great importance for flood control and water resource management. However, the selection of hydrological models is challenging to obtain superior simulation performance especially with the rapid development of machine learning techniques. Three models under different categories of machine learning methods, including support vector regression (SVR), extreme gradient boosting (XGBoost), and the long-short term memory neural network (LSTM), were assessed for simulating daily runoff over a mountainous river catchment. The performances with different input scenarios were compared. Additionally, the joint multifractal spectra (JMS) method was implemented to evaluate the simulation performances during wet and dry seasons. The results show that: (1) LSTM always obtained a higher accuracy than XGBoost and SVR; (2) the impacts of the input variables were different for different machine learning methods, such as antecedent streamflow for XGBoost and rainfall for LSTM; (3) XGBoost showed a relatively high performance during dry seasons, and the classification of wet and dry seasons improved the simulation performance, especially for LSTM during dry seasons; (4) the JMS analysis indicated the advantages of a hybrid model combined with LSTM trained with wet-season data and XGBoost trained with dry-season data.

Revealing the mechanism of hydrological and agricultural drought has been challenging and vital in the environment under extreme weather and water resource shortages. To explore the evolution process from meteorological to hydrological and agricultural drought further, multi-source remote sensing data, including the Gravity Recovery and Climate Experiment (GRACE) product, were collected in the Huaihe River basin of China during 2002–2020. Three machine learning methods, including long short-term memory neural network (LSTM), convolutional neural network (CNN), and categorical boosting (CatBoost), were constructed for hydrological and agricultural drought forecasting. The propagation time from meteorological drought to surface water storage and terrestrial water storage drought, evaluated by the standardized precipitation evapotranspiration index, was 8 and 11 months with Pearson correlation coefficients (R) of 0.68 and 0.48, respectively. Groundwater storage drought was correlated with evapotranspiration and vegetation growth with a 12-month lag time, respectively. In addition, vegetation growth was affected by the drought of soil moisture at depths ranging from 100 to 200 cm with an 8-month lag time with an R of −0.39. Although the forecasting performances of terrestrial water storage drought were better than those of groundwater storage drought and agricultural drought, CNN always performed better than LSTM and CatBoost models, with Nash–Sutclife efficiency values during testing ranging from 0.28 to 0.70, 0.26 to 0.33, and −0.10 to −0.40 for terrestrial water storage drought, groundwater storage drought, and agricultural drought at lead times of 0–3 months, respectively. Furthermore, splitting training and testing data at random significantly improved the performances of CNN and CatBoost methods for drought forecasting rather than in chronological order splitting for non-stationary data.

Sustainable water resources management is facing a rigorous challenge due to global climate change. Nowadays, improving streamflow predictions based on uneven precipitation is an important task. The main purpose of this study is to integrate the ensemble technique concept into artificial neural networks for reducing model uncertainty in hourly streamflow predictions. The ensemble streamflow predictions are built following two steps: (1) Generating the ensemble members through disturbance of initial weights, data resampling, and alteration of model structure; (2) consolidating the model outputs through the arithmetic average, stacking, and Bayesian model average. This study investigates various ensemble strategies on two study sites, where the watershed size and hydrological conditions are different. The results help to realize whether the ensemble methods are sensitive to hydrological or physiographical conditions. Additionally, the applicability and availability of the ensemble strategies can be easily evaluated in this study. Among various ensemble strategies, the best ESP is produced by the combination of boosting (data resampling) and Bayesian model average. The results demonstrate that the ensemble neural networks greatly improved the accuracy of streamflow predictions as compared to a single neural network, and the improvement made by the ensemble neural network is about 19–37% and 20–30% in Longquan Creek and Jinhua River watersheds, respectively, for 1–3 h ahead streamflow prediction. Moreover, the results obtained from different ensemble strategies are quite consistent in both watersheds, indicating that the ensemble strategies are insensitive to hydrological and physiographical factors. Finally, the output intervals of ensemble streamflow prediction may also reflect the possible peak flow, which is valuable information for flood prevention.

The streamflow recession analysis, always following a power law, depicts the storage-release relation in catchments. However, the understanding of hydrological recession dynamics is still insufficient. Here, a total of 80 nearly natural catchments from the reference hydrologic networks (RHNs) in the UK were selected to explore the changes and the controlling factors of recession slope curve parameters by utilizing trend analysis methods, the self-organizing map, and k-means clustering algorithms. The results demonstrated that (i) the estimation of event-scale recession parameters was sensitive to different combinations of recession extraction and fitting methods. Particularly, the combination of Brutsaert extraction and the linear regression method always obtained robust estimations of recession parameters. (ii) Changes of annual median recession parameters showed a clear spatial distribution pattern, indicating the climate-driven impact on recession processes. Up to 17 catchments in Scotland showed significant changes in recession processes, always displaying increasing trends in the recession coefficient and decreasing trends in the recession exponent. (iii) The recession exponent strongly depended on the base-flow index, rock permeability, arable area, and temporal distribution of rainfall. Additionally, the spatial patterning of recession processes further provided some insights for facilitating the understanding of the hydrological recession process.