To maximize the benefits of power generation and water supply of the reservoir under the premise of ensuring ecological flow as much as possible, it is necessary to formulate a highly operational release scheme in the actual production scheduling process. To mitigate the ecological impacts of reservoir operations, enhanced environmental flow releases are required; however, this results in diminished reservoir economic outputs. Therefore, in order to determine the government subsidy standards for ecological regulation of reservoirs and improve the enthusiasm of water conservancy departments for ecological regulation, it is necessary to conduct comprehensive analysis and research on the benefits of ecological regulation. According to the ecological releases of the reservoir, the reservoir operation scheme is formulated, and the comprehensive benefits of the reservoir operation are analyzed and studied to determine the optimal operation scheme. Based on the monthly inflow runoff of the Baishi Reservoir to the Daling River from 1956 to 2011, constrained by the ecological base flow specified by the government, and combined with the water supply and power generation functions of the reservoir, an optimal operation model of the Baishi Reservoir based on ecological release is constructed. The water supply, power generation, and ecological benefits of the reservoir discharge are comprehensively analyzed and calculated to analyze and study the loss of economic benefits caused by the reservoir discharge and the ecological benefits that can be obtained from the ecological discharge. Based on the comprehensive evaluation of multiple indicators, the Technique for Order Preference by Similarity to an Ideal Solution (TOPSIS) fuzzy comprehensive evaluation method is used to select the optimal scheduling scheme. The optimal scheduling plan for a reservoir is closely related to its characteristic water level. In order to improve the efficiency of reservoir scheduling, monthly control of reservoir discharge can be implemented. The guarantee rate of urban domestic water supply and ecological water use can be increased as much as possible, while the guarantee rate of agricultural water use can be appropriately reduced to obtain the optimal comprehensive benefits. The outflow considering ecological release is 6.5–7 m³/s from June to April and 1 m³/s in May. The outflow without considering ecological release is 4 m³/s from June to April and 1 m³/s in May. This study has certain guiding significance and value for the formulation of an ecological operation scheme for reservoirs and the analysis of benefits.

To address limitations such as short forecast periods, data collection challenges, insufficient understanding of physical mechanisms, and single-scale constraints, forecasting factors and their characteristics were analyzed across astronomical, global, and watershed scales. Forecasting factors were selected based on astronomical observations, ocean current predictions, traditional calendars, and agricultural proverbs, and their characteristics were quantitatively processed. A BP neural network optimized by the Gray Wolf Optimizer (GWO) algorithm (GWO-BP) was constructed, and the dataset derived from sample division of the Fengman Reservoir Basin was used to train the model for secondary fitting. The model successfully fit and predicted the annual inflow of the Fengman Reservoir Basin from 2013 to 2017. Through a comparison with the GWO–Support Vector Machine (GWO-SVM) model, results showed that the GWO-BP model exhibited superior predictive performance. This method integrates multi-scale, easily accessible, and quantifiable forecasting factors, facilitating the extension of long-term runoff forecasting applications within the river basin.

The authors have requested that this preprint be removed from Research Square.