Superiority of Hybrid Soft Computing Models in Daily Suspended Sediment Estimation in Highly Dynamic Rivers

Estimating sediment flow rate from a drainage area plays an essential role in better watershed planning and management. In this study, the validity of simple wavelet-coupled Artificial Intelligence (AI) models was analyzed for daily Suspended Sediment (SSC) estimation highly dynamic Koyna River basin India. Simple AI such as Neural Network (ANN) Adaptive Neuro-Fuzzy Inference System (ANFIS) were developed by supplying original time series data input without pre-processing through Wavelet (W) transform. The hybrid W-ANN W-ANFIS decomposed sub-signals using Discrete Transform (DWT). total, three mother wavelets, namely Haar, Daubechies, Coiflets employed to decompose into different multi-frequency at appropriate decomposition level. Quantitative qualitative performance evaluation criteria used select best model SSC estimation. reliability also assessed uncertainty analysis. Finally, it revealed that wavelet transform improves model’s predictive efficiency significantly. observed Coiflet ANFIS is superior other can be applied rivers. As per sensitivity analysis, previous one-day (St-1) most crucial variable basin.