Accurate real-time water quality prediction is of great significance for local environmental managers to deal with upcoming events and emergencies to develop best management practices. In this study, the performances in real-time water quality forecasting based on different deep learning (DL) models with different input data pre-processing methods were compared. There were three popular DL models concerned, including the convolutional neural network (CNN), long short-term memory neural network (LSTM), and hybrid CNN–LSTM. Two types of input data were applied, including the original one-dimensional time series and the two-dimensional grey image based on the complete ensemble empirical mode decomposition algorithm with adaptive noise (CEEMDAN) decomposition. Each type of input data was used in each DL model to forecast the real-time monitoring water quality parameters of dissolved oxygen (DO) and total nitrogen (TN). The results showed that (1) the performances of CNN–LSTM were superior to the standalone model CNN and LSTM; (2) the models used CEEMDAN-based input data performed much better than the models used the original input data, while the improvements for non-periodic parameter TN were much greater than that for periodic parameter DO; and (3) the model accuracies gradually decreased with the increase of prediction steps, while the original input data decayed faster than the CEEMDAN-based input data and the non-periodic parameter TN decayed faster than the periodic parameter DO. Overall, the input data preprocessed by the CEEMDAN method could effectively improve the forecasting performances of deep learning models, and this improvement was especially significant for non-periodic parameters of TN.

The impacts of future climate changes on watershed hydrochemical processes were assessed based on the newest Shared Socioeconomic Pathways (SSP) scenarios in Coupled Model Intercomparison Project Phase 6 (CMIP6) in the Tianhe River in the middle area of China. The monthly spatial downscaled outputs of General Circulation Models (GCMs) were used, and a new Python procedure was developed to batch pick up site-scale climate change information. A combined modeling approach was proposed to estimate the responses of the streamflow and Total Dissolved Nitrogen (TDN) fluxes to four climate change scenarios during four future periods. The Long Ashton Research Station Weather Generator (LARS-WG) was used to generate synthetic daily weather series, which were further used in the Regional Nutrient Management (ReNuMa) model for scenario analyses of watershed hydrochemical process responses. The results showed that there would be 2–3% decreases in annual streamflow by the end of this century for most scenarios except SSP 1-26. More streamflow is expected in the summer months, responding to most climate change scenarios. The annual TDN fluxes would continue to increase in the future under the uncontrolled climate scenarios, with more non-point source contributions during the high-flow periods in the summer. The intensities of the TDN flux increasing under the emission-controlled climate scenarios would be relatively moderate, with a turning point around the 2070s, indicating that positive climate policies could be effective for mitigating the impacts of future climate changes on watershed hydrochemical processes.

This study concerned the sediment issue of the Yellow River basin. The responses of hydrological and sedimental processes to future climate change in two upland watersheds with different dominant landscapes were estimated. Four Representative Concentration Pathway (RCP) scenarios with different radiative forcing levels were considered. The outputs of eleven Global Climate Models (GCMs) were used to represent the future climate status of the 2050s and 2070s, and an ensemble means was achieved to avoid uncertainty. The Long Ashton Research Station Weather Generator (LARS-WG) was employed to downscale the outputs of GCMs for future site-scale daily weather data estimations. The Generalized Watershed Loading Functions (GWLF) model was employed to model the streamflow and sediment yields under various scenarios and periods. The results showed that there would be generally hotter and wetter weather conditions in the future. Increased erosion and sediment yields could be found in the study area, with lesser increments in sediment in woodland than in cultivated field. The peak of sediment would appear in the 2050s, and integrated measures for sediment control should be implemented to reduce erosion and block delivery. The multi-model approach proposed in this study had reliable performance and could be applied in other similar areas with modest data conditions.

This study focuses on the impacts of climate change on hydrological processes in watersheds and proposes an integrated approach combining a weather generator with a multi-site conditional generative adversarial network (McGAN) model. The weather generator incorporates ensemble GCM predictions to generate regional average synthetic weather series, while McGAN transforms these regional averages into spatially consistent multi-site data. By addressing the spatial consistency problem in generating multi-site synthetic weather series, this approach tackles a key challenge in site-scale climate change impact assessment. Applied to the Jinghe River Basin in west-central China, the approach generated synthetic daily temperature and precipitation data for four stations under different shared socioeconomic pathways (SSP1-26, SSP2-45, SSP3-70, SSP5-85) up to 2100. These data were then used with a long short-term memory (LSTM) network, trained on historical data, to simulate daily river flow from 2021 to 2100. The results show that (1) the approach effectively addresses the spatial correlation problem in multi-site weather data generation; (2) future climate change is likely to increase river flow, particularly under high-emission scenarios; and (3) while the frequency of extreme events may increase, proactive climate policies can mitigate flood and drought risks. This approach offers a new tool for hydrologic–climatic impact assessment in climate change studies.