Considering the high random and non-static property of the rainfall-runoff process, lots of models are being developed in order to learn about such a complex phenomenon. Recently, Machine learning techniques such as the Artificial Neural Network (ANN) and other networks have been extensively used by hydrologists for rainfall-runoff modelling as well as for other fields of hydrology. However, deep learning methods such as the state-of-the-art for LSTM networks are little studied in hydrological sequence time-series predictions. We deployed ANN and LSTM network models for simulating the rainfall-runoff process based on flood events from 1971 to 2013 in Fen River basin monitored through 14 rainfall stations and one hydrologic station in the catchment. The experimental data were from 98 rainfall-runoff events in this period. In between 86 rainfall-runoff events were used as training set, and the rest were used as test set. The results show that the two networks are all suitable for rainfall-runoff models and better than conceptual and physical based models. LSTM models outperform the ANN models with the values of $R^2$ and $NSE$ beyond 0.9, respectively. Considering different lead time modelling the LSTM model is also more stable than ANN model holding better simulation performance. The special units of forget gate makes LSTM model better simulation and more intelligent than ANN model. In this study, we want to propose new data-driven methods for flood forecasting.

HIGHLIGHTS. Propose a TCN model for flood simulation and forecast.Explore the optimal hyperparameter combination of TCN at different forecast periods in flood f

Flood forecasting using traditional physical hydrology models requires consideration of multiple complex physical processes including the spatio-temporal distribution of rainfall, the spatial heterogeneity of watershed sub-surface characteristics, and runoff generation and routing behaviours. Data-driven models offer novel solutions to these challenges, though they are hindered by difficulties in hyperparameter selection and a decline in prediction stability as the lead time extends. This study introduces a hybrid model, the RS-LSTM-Transformer, which combines Random Search (RS), Long Short-Term Memory networks (LSTM), and the Transformer architecture. Applied to the typical Jingle watershed in the middle reaches of the Yellow River, this model utilises rainfall and runoff data from basin sites to simulate flood processes, and its outcomes are compared against those from RS-LSTM, RS-Transformer, RS-BP, and RS-MLP models. It was evaluated against RS-LSTM, RS-Transformer, RS-BP, and RS-MLP models using the Nash–Sutcliffe Efficiency Coefficient (NSE), Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and Bias percentage as metrics. At a 1-h lead time during calibration and validation, the RS-LSTM-Transformer model achieved NSE, RMSE, MAE, and Bias values of 0.970, 14.001m³/s, 5.304m³/s, 0.501% and 0.953, 14.124m³/s, 6.365m³/s, 0.523%, respectively. These results demonstrate the model's superior simulation capabilities and robustness, providing more accurate peak flow forecasts as the lead time increases. The study highlights the RS-LSTM-Transformer model's potential in flood forecasting and the advantages of integrating various data-driven approaches for innovative modelling.

Changes in the hydrological process caused by urbanization lead to frequent flooding in cities. For fast-growing urban areas, the impact of urbanization on the hydrological process needs to be systematically analyzed. This study takes Zhengzhou as an example to analyze the impact of urbanization on the hydrological process based on 1971–2012 hourly rainfall-runoff data, combining Geographic Information Systems with traditional hydrological methods. Our study indicates that the rain island effect in different districts of city became stronger with the increase of its built-up. The uneven land use resulted in the difference of runoff process. The flood peak lag was 25–30% earlier with the change of land use. The change of flood peak increased by 10–30% with the change of built-up. The runoff coefficient increases by 20–35% with the increase of built-up, and its change increased with the change of land use. Affected by the rain island effect, precipitation tends to occur in areas where built-up is dominant, which overall magnifies the impact of urbanization on the hydrological process. This provides new ideas for urban flood control. Refine flood control standards according to regional land use changes to cope with the hydrological process after urbanization.

Globally there is already a lot of pressure on water resources because of climate change, economic development, as well as an increasing global populace. Many rivers originate in the mountains, where snowfall fluctuations and the global climate’s inherent unpredictability affect the hydrological processes. Climate change sensitivity has been recognized in recent years and would affect hydropower, such as humidity, cloudiness, and precipitation, that are considered; global warming emerges as one of the most important contributors to climate change. The Yangtze River supports rich biodiversity and provides important ecosystem services for human survival and development. In addition, climate changes, particularly short-term and long-term precipitation and temperature fluctuations, influence the snow regime and the hydrological development of river flow response at the basin and sub-basin scales. More precise this review focused to understand the hydropower potential, freshwater fisheries, and hydrological response of snow dynamics in snow-dominated basins.

Global warming is affecting animal populations worldwide, through chronic temperature increases and an increase in the frequency of extreme heatwave events. Reservoirs are essential for water security. All watersheds with reservoirs are impacted by their construction. These artificial ecosystems controlled by humans change considerably the natural terrestrial and aquatic ecosystem and systems and their biodiversity. The rapid increase in population growth, urbanization, and industrialization are accompanied by an increase in river discharges, which increases the total amount of pollutants. HMs contamination in aquatic environments, as well as the subsequent absorption of HMs into the food chain by aquatic creatures and people, endangers public health. Multiple uses of reservoirs promote benefits in terms of economic development, income, and employment. HMs in water can be ingested directly by aquatic species like fish and can also be ingested indirectly through the food chain; thus, it is much more important and required to conduct frequent monitoring of the aquatic environment. As a result, this review summarizes knowledge about the effects of cascade dams on river water temperature and increases on the stress physiology of fishes, and adaptation to climate change is also needed to produce more fish without global warming.