The reservoir is an important hydraulic engineering measure for human utilization and management of water resources. Additionally, a reasonable and effective reservoir operating plan is essential for realizing reservoir function. To explore the application of a deep learning algorithm on the field of reservoir operations, a recurrent neural network (RNN), long short-term memory (LSTM), and gated recurrent unit (GRU) are employed to predict outflows for the Xiluodu (XLD) reservoir. Meanwhile, this paper summarized the law of the effect of parameter setting on model performance compared to the simulation performance of three models, and analyzed the main factors that affect reservoir operation to provide the reference for future model of application research. Results show (1) the number of iterations and hidden nodes mainly influence the model precision, and the former has more effect than the latter, and the batch size mainly affects the calculated speed; (2) all three models can predict the reservoir outflow accurately and efficiently; (3) the operating decision generated by three models can implement the flood control and power generation goal of the reservoir and meet the operating regulation; and (4) under different hydrological periods, the influence factors of reservoir operation and their importance are different.

Water quality plays a pivotal role in human health and environmental sustainability. However, traditional water quality prediction models are limited by high model complexity and long computation time, whereas AI models often struggle with high-dimensional time series and lack physical interpretability. This paper proposes a two-dimensional water quality surrogate model that couples physical numerical models and AI. The model employs physical simulation results as input, applies spectral proper orthogonal decomposition to reduce the dimensionality of the simulation results, utilizes a long short-term memory neural network for matrix forecasting, and reconstructs the two-dimensional concentration field. The simulation and predictive performance of the surrogate model were systematically evaluated through four design scenarios and three sampling dataset lengths, with a particular focus on the convection–diffusion zone and high-concentration zone. The results indicated that the model achieves high prediction accuracy for up to 7 h into the future, with sampling dataset lengths ranging from 20 to 80 h. Specifically, the model achieved an average R² of 0.92, a MAE of 0.38, and a MAPE of 1.77%, demonstrating its suitability for short-term water quality predictions. The methodology and findings of this study demonstrate the significant potential of integrating spectral proper orthogonal decomposition and deep learning for water quality prediction. By overcoming the limitations of traditional models, the proposed surrogate model provides high-accuracy predictions with enhanced physical interpretability, even in complex, dynamic environments. This work offers a practical tool for rapid responses to water pollution incidents and supports improved watershed water quality management by effectively capturing pollutant diffusion dynamics. Furthermore, the model’s scalability and adaptability make it a valuable resource for addressing intelligent management in environmental science.

The middle reaches of the Yangtze River are a crucial breeding habitat for four major Chinese carps. The ecohydrological characteristics of their spawning grounds are crucial factors influencing spawning for these species: black carp (Mylopharyngodon piceus), grass carp (Ctenopharyngodon idella), silver carp (Hypophthalmichthys molitrix), and bighead carp (Aristichthys nobilis). To investigate the impact of ecohydrological processes within the Three Gorges Reservoir on spawning, this study focused on the spawning grounds of the four major Chinese carps in the Yichang–Yidu section of the Yangtze River. By identifying key ecohydrological indicators and leveraging hydrological and spawning monitoring data from 2013 to 2024, the response characteristics of the four major Chinese carps’ spawning to these hydrological processes were analyzed. The results showed that the key ecohydrological indicators currently stimulating spawning for the four major Chinese carps are the fish-perceived daily flow rate increase, the fish-perceived cumulative flow rate increase, and the daily flow rate increase. These three indicators are significantly positively correlated with the scale of spawning for the four major Chinese carps. The thresholds for spawning at least 20% of the annual spawning total are: a perceived daily flow increase (P_da) of 4.52–36.05%; a perceived cumulative flow increase (P_cu) of 36.15–180.23%; and a daily flow increase (Q_av) of 588–2825 m³/s. The optimal water temperature for the reproduction of the four major Chinese carps is 21–23 °C. Overall, since the Three Gorges Reservoir’s normal operation, the frequency and scale of spawning for the four major Chinese carps have been highest during periods of rising water. It is recommended that, within the corresponding thresholds, ecological operation be conducted twice a year, once in mid-June and once in early July or late June. Daily flow increases can be controlled within the range of 588–2000 m³/s. This study analyzed the correlation between eco-hydrological indicators and the stimulation of spawning of the four major Chinese carps, providing optimized flow ranges and habitat conditions for ecological operation, which is conducive to promoting the reproduction and spawning of the four major Chinese carps in the Yichang–Yidu spawning grounds in the middle reaches of the Yangtze River.

To meet the demand for water temperature prediction in the ecological operation of reservoirs, this study presents a long-term water temperature forecasting model based on machine learning algorithms using the Yidu spawning grounds, located downstream of the Three Gorges Reservoir (TGR), as a case study. The results demonstrated that the transfer learning model outperformed conventional models in terms of prediction accuracy, forecast duration, and computational efficiency. Specifically, the transfer learning model achieved an average error of 0.16–0.35 °C, outperforming the conventional model (with an error range of 0.15–0.6 °C), and exhibited superior capability in capturing complex water temperature variations. Regarding computational efficiency, the transfer learning model required significantly less training time and adapted rapidly to new data, enhancing the practical applicability of the model. During the critical ecological operation period (May–June), the transfer learning model’s average absolute error was 0.2–0.3 °C, effectively supporting optimal selection of the reservoir’s ecological operation timing. The findings provide a scientific basis for decision making in the integrated operation of reservoirs.

To investigate the movement characteristics of fish eggs and to clarify their movement behavior as flow conditions transition from slow to rapid, a hydrodynamics-based fish egg movement model was proposed. Indoor flume experiments under slow-flow conditions conducted previously by the research group were used as a basis. Twenty-three operating conditions with different water depths and discharges were designed, including fifteen rapid-flow conditions and eight slow-flow conditions. Numerical simulations were performed to examine the influence of flow velocity on fish egg movement under different flow conditions. The results show that fish eggs drift with the flow under different flow conditions, and their longitudinal velocity lags behind the flow velocity. At low flow velocities, the vertical velocity distribution of fish eggs is relatively concentrated. With increasing flow velocity, the vertical velocity becomes more dispersed in the high-velocity range. A power–law relationship exists between flow velocity and the trajectory slope of fish egg movement. When the flow velocity is lower than 0.5 m/s, the trajectory slope varies significantly with flow velocity; when it exceeds 1.2 m/s, the slope approaches a constant value. Water depth has a limited influence on fish egg velocity and trajectory slope under both slow-flow and rapid-flow conditions. By combining the relationships among flow velocity, trajectory slope, and suspension rate, a flow velocity of 0.3 m/s is identified as the critical flow velocity for maintaining the safe drifting of fish eggs. The findings provide technical support for ecological operation strategies aimed at fishery resource conservation.