Accurate forecasting of solar radiation (Rs) is significant to photovoltaic power generation and agricultural management. The National Centers for Environmental Prediction (NECP) has released its latest Global Ensemble Forecast System version 12 (GEFSv12) prediction product; however, the capability of this numerical weather product for Rs forecasting has not been evaluated. This study intends to establish a coupling algorithm based on a bat algorithm (BA) and Kernel-based nonlinear extension of Arps decline (KNEA) for post-processing 1–3 d ahead Rs forecasting based on the GEFSv12 in Xinjiang of China. The new model also compares two empirical statistical methods, which were quantile mapping (QM) and Equiratio cumulative distribution function matching (EDCDFm), and compares six machine-learning methods, e.g., long-short term memory (LSTM), support vector machine (SVM), XGBoost, KNEA, BA-SVM, BA-XGBoost. The results show that the accuracy of forecasting Rs from all of the models decreases with the extension of the forecast period. Compared with the GEFS raw Rs data over the four stations, the RMSE and MAE of QM and EDCDFm models decreased by 20% and 15%, respectively. In addition, the BA-KNEA model was superior to the GEFSv12 raw Rs data and other post-processing methods, with R² = 0.782–0.829, RMSE = 3.240–3.685 MJ m⁻² d⁻¹, MAE = 2.465–2.799 MJ m⁻² d⁻¹, and NRMSE = 0.152–0.173.

This study presents an integrated analysis of cohesive bank-collapsed material transportation in a high-curvature channel with a non-cohesive riverbed. A numerical model was established to simulate the erosion and transportation of collapsed materials in a 180° U-bend channel after verification. The novel aspect of this study is that the quantities of the collapsed materials that transformed into suspended and bed loads were comprehensively analyzed. The results show that finer collapsed sediments were only transformed into suspended loads after being eroded, while the coarser particles transformed into both suspended loads and bed loads. When the flow charge was 30 L/s, the quantity of collapsed materials (S1 and S2) that transported downstream was smaller, and coarser materials transformed into suspended loads with a ratio of 88.12–99.86% and bed loads with a ratio of 11.18–0.14%. When the flow charge was 55 L/s, due to the greater shear stress, the quantity of collapsed materials (S1 and S2) that transported downstream was greater, and the ratio ranged from 46.65% to 49.88% and from 50.12% to 53.35%, respectively. This research provides theoretical and practical benefits that reveal the mechanisms of channel bend evolution.