Evaluation of hydrological and data-based models in estimation of daily runoff in Galikesh watershed

Abstract

Estimating the runoff in a watershed is important not only in the management and proper land-use utilisation, but also plays an important role in minimising the flood damages. In this paper, four methods were used to simulate daily runoff in the Galikesh watershed. In the first method, IHACRES hydrological model was used and in other methods three data-based models, namely, artificial neural network (ANN), K-nearest neighbourhood (KNN) and adaptive neural-fuzzy inference system (ANFIS) were applied. First calibration and training of hydrological and ANN, KNN and ANFIS models, then the performance of all models were compared for both calibration and test periods. Results showed that the data-based models had better performance in simulating the rainfall-runoff process than the hydrological model. Based on observed and simulated runoffs, the correlation coefficient for KNN, ANN and ANFIS were calculated as 0.85, 0.83 and 0.85 and the root mean square error equalled to 1.106, 1.1667 and 1.1168 m³/s, respectively. This is while for IHACRES hydrological model, the correlation coefficient and root mean square error were derived as 0.67 and 1.54 m³/s, respectively.