Main content area

Simulation of suspended sediment based on gamma test, heuristic, and regression-based techniques

Singh, Vijay Kumar, Kumar, Devendra, Kashyap, P. S., Kisi, Ozgur
Environmental earth sciences 2018 v.77 no.19 pp. 708
fuzzy logic, regression analysis, sediments, suspended sediment
In the present study, four different heuristic techniques viz. multi-layer perceptron (MLP), radial basis function (RBF), self-organizing maps (SOM), and co-active neuro-fuzzy inference system (CANFIS) with hyperbolic tangent and sigmoid transfer functions and two regression-based techniques, i.e., multiple linear regression (MLR) and sediment-rating curve (SRC), were used for suspended sediment modeling. Gamma test (GT), correlation function (CF), M test, and trail–error procedure were applied for estimation of appropriate input variables as well as training data length. The results of the GT and CF suggested the five input variables (Qₜ, Qₜ₋₁, Qₜ₋₂, Sₜ₋₁, and Sₜ₋₂, where Qₜ₋₁ and Sₜ₋₁ indicate the discharge and sediment values of one previous day) as the best combination. The optimal training data length (75% of total data) was estimated by M test and trail–error procedure for development of the applied models. The MLP with sigmoid transfer function (M-2) performed better than the all other models. The results of sensitivity analysis indicated that the present-day discharge (Qₜ), 1-day lag discharge (Qₜ₋₁) and 1-day lag suspended sediment (Sₜ₋₁) are the most influenced parameters in modeling current day suspended sediment (Sₜ).