A novel multi-objective electromagnetism-like mechanism algorithm with applications in reservoir flood control operation.

Reservoir flood control operation (RFCO) is a complex problem that involves various constraints and purposes, which include the safety of the dam, watershed flood control and navigation. These objectives often conflict with each other. Thus, traditional methods have difficulty in solving the multi-objective problem efficiently. In this paper, a multi-objective self-adaptive electromagnetism-like mechanism (MOSEM) algorithm is introduced in the local searching operation of the proposed method. To enhance the optimization ability of EM, a self-adaptive parameter is applied in the local search operation of MOSEM for adjusting the values of parameters dynamically. Moreover, MOSEM is tested by several benchmark test problems and compared with some well-known multi-objective evolutionary algorithms. A case study is also used for solving RFCO problems of the Three Georges Reservoir by using the multi-objective cultured differential evolution (MOCDE), non-dominated sorting genetic algorithm-II (NSGA-II) and proposed MOSEM methods. The study results reveal that MOSEM can provide alternative Pareto-optimal solutions (POS) with better convergence properties and diversification.

Assessing spatial connectivity effects on daily streamflow forecasting using Bayesian-based graph neural network.

Data-driven models have been widely developed and achieved impressive results in streamflow prediction. However, the existing data-driven models mostly focus on the selection of input features and the adjustment of model structure, and less on the impact of spatial connectivity on daily streamflow prediction. In this paper, a basin network based on graph-structured data is constructed by considering the spatial connectivity of different stations in the real basin. Furthermore, a novel graph neural network model, variational Bayesian edge-conditioned graph convolution model, which consists of edge-conditioned convolution networks and variational Bayesian inference, is proposed to assess the spatial connectivity effects on daily streamflow forecasting. The proposed graph neural network model is applied to forecast the next-day streamflow of a hydrological station in the Yangtze River Basin, China. Six comparative models and three comparative experimental groups are used to validate model performance. The results show that the proposed model has excellent performance in terms of deterministic prediction accuracy (NSE ≈ 0.980, RMSE≈1362.7 and MAE ≈ 745.8) and probabilistic prediction reliability (ICPC≈0.984 and CRPS≈574.1), which demonstrates that establishing appropriate connectivity and reasonably identifying connection relationships in the basin network can effectively improve the deterministic and probabilistic forecasting performance of the graph convolutional model.