Suspended sediment concentration prediction is critical for the design of reservoirs, dams, rivers ecosystems, various operations of aquatic resource structure, environmental safety, and water management. In this study, two different machine models, namely the cascade correlation neural network (CCNN) and feedforward neural network (FFNN) were applied to predict daily-suspended sediment concentration (SSC) at Simga and Jondhara stations in Sheonath basin, India. Daily-suspended sediment concentration and discharge data from 2010 to 2015 were collected and used to develop the model to predict suspended sediment concentration. The developed models were evaluated using statistical indices like Nash and Sutcliffe efficiency coefficient (N_ES), root mean square error (RMSE), Willmott’s index of agreement (WI), and Legates–McCabe’s index (LM), supplemented by a scatter plot, density plots, histograms and Taylor diagram for graphical representation. The developed model was evaluated and compared with CCNN and FFNN. Nine input combinations were explored using different lag-times for discharge (Q_t-n) and suspended sediment concentration (S_t-n) as input variables, with the current suspended sediment concentration as the desired output, to develop CCNN and FFNN models. The CCNN4 model with 4 lagged inputs (S_t-1, S_t-2, S_t-3, S_t-4) outperformed the other developed models with the lowest RMSE = 95.02 mg/l and the highest N_ES = 0.0.662, WI = 0.890 and LM = 0.668 for the Jondhara Station while the same CCNN4 model secure as the best with the lowest RMSE = 53.71 mg/l and the highest N_ES = 0.785, WI = 0.936 and LM = 0.788 for the Simga Station. The result shows the CCNN model was better than the FFNN model for predicting daily-suspended sediment at both stations in the Sheonath basin, India. Overall, CCNN showed better forecasting potential for suspended sediment concentration compared to FFNN at both stations, demonstrating their applicability for hydrological forecasting with complex relationships.

悬浮泥沙浓度预测对于水库、大坝、河流生态系统的设计、水生资源结构的各种运行、环境安全和水管理至关重要。在本研究中，应用两种不同的机器模型，即级联相关神经网络（CCNN）和前馈神经网络（FFNN）来预测印度Sheonath盆地Simga和Jondhara站的日悬浮泥沙浓度（SSC）。收集2010年至2015年的每日悬浮泥沙浓度和排放数据，并用于建立预测悬浮泥沙浓度的模型。使用纳什和萨特克利夫效率系数 (N _ES )、均方根误差 (RMSE)、威尔莫特一致性指数 (WI) 和 Legates-McCabe 指数 (LM)等统计指标对开发的模型进行评估，并辅以散点图，用于图形表示的密度图、直方图和泰勒图。对所开发的模型进行了评估，并与 CCNN 和 FFNN 进行了比较。使用不同的排放滞后时间 (Q _t-n ) 和悬浮泥沙浓度 (S _t-n ) 作为输入变量，以当前悬浮泥沙浓度作为所需输出，探索九种输入组合，以开发 CCNN 和 FFNN 模型。具有 4 个滞后输入（ _St-1、St _-2、St _-3、St _-4 ）的 CCNN4 模型优于其他开发的模型，其最低 RMSE = 95.02 mg/l 和最高 N _ES  = 0.0。 662，Jondhara 站的 WI = 0.890 和 LM = 0.668，而相同的 CCNN4 模型确保为最佳模型 ，Simga 站的RMSE = 53.71 mg/l 最低，N _ES = 0.785，WI = 0.936 和 LM = 0.788 最高。结果表明，CCNN 模型在预测印度 Sheonath 盆地两个站点的日悬浮泥沙量方面优于 FFNN 模型。总体而言，与 FFNN 相比，CCNN 在两个站点都显示出更好的悬浮泥沙浓度预测潜力，证明了它们对具有复杂关系的水文预测的适用性。