Application of coupling machine learning techniques and linear Bias scaling for optimizing 10-daily flow simulations, Swat River Basin

Abstract

Accurate hydrological simulations comply with the water (sixth) Sustainable Development Goals (SDGs). The study investigates the utility of ANN and SVR, as well as the post-simulation bias treatment of these simulations at Swat River basin, Pakistan. For this, climate variables were lag adjusted for the first time, then cross-correlated with the flow to identify the most associative delay time. In sensitivity analysis, seven combinations were selected as input with suitable hyperparameters. For SVR, grid search cross-validation determined the optimal set of hyper-parameters, while for ANN, neurons and hidden layers were optimized by trial and error. We ran model by using optimized hyperparameter configurations and input combinations. In comparison to SVRs (Root mean square error (RMSE) 34.2; mean absolute error (MAE) 3.0; CC 0.91) values, respectively, ANN fits the observations better than SVR with (RMSE 11.9; MAE 1.14; CC 0.99). Linear bias-corrected simulations greatly improved ANN performance (RMSE 3.98; MAE 0.625; CC 0.99), while the improvement was slight in the case of SVR (RMSE 35; MAE 0.58; CC 0.92). On seasonal scale, bias-corrected simulations remedy low- and high-flow seasonal discrepancies. Flow duration analysis results reveal deviation at low- and high-flow conditions by models, which were then reconciled by applying bias corrections. HIGHLIGHTS The study represents a couple of AI prognostic models with bias scaling on the Swat Basin case study.; ANN performs best with higher input parameters, while SVR performs robustly with lower input parameters.; Bias scaling of SVR (SVR-BC) improves in depicting peaks.; Bias correction of ANN yields better flow series having minimum errors than other models.;

Keywords

• artificial neural network
• linear bias scaling
• river swat basin
• sensitivity analysis
• streamflow prediction
• support vector machine