asrin hosseini; mohammad reza golabi; safar marofi; nasim khalediyan; mohammad solatani
Abstract
Simulation of the rainfall-runoff process is the most important step in water engineering and water resource management studies. Exploitation of surface water and underground water resources, river management and flood warning requires prediction of river and runoff discharges of the watershed. In this ...
Read More
Simulation of the rainfall-runoff process is the most important step in water engineering and water resource management studies. Exploitation of surface water and underground water resources, river management and flood warning requires prediction of river and runoff discharges of the watershed. In this study, Extended Kalman Filter-based Neural Network (EKFNN) method was used for rainfall-runoff modelling. Then, the results were compared with the Gene Expression Planning method, which showed good performance in rainfall-runoff modelling in most recent studies. The data used in this study is related to daily runoff and rainfall of the rain gauge and hydrometric stations of Malayer plain which includes Peyhan, Marvil and Namyleh stations, during the period of 2001 to 2013. The results indicated that the EKFNN model was superior to GEP model in daily river flow modelling in Malayer plain. In addition, the speed of implementation of the Gene Expression Planning model was greater and was able to present results in a short time. Finally, EKFNN model was selected as the superior model for Malayer plain.
massoumeh zeinalie; mohammad reza golabi; mohammad reza sharifi; maryam hafezparast
Abstract
Having predicted river flow, we can predict and control natural disasters such as flood and drought in addition to managing utilization of water resources. New models in this domain can help correct management and planning. In this study, three models are evaluated: Gene Expression Planning (GEP), Bayesian ...
Read More
Having predicted river flow, we can predict and control natural disasters such as flood and drought in addition to managing utilization of water resources. New models in this domain can help correct management and planning. In this study, three models are evaluated: Gene Expression Planning (GEP), Bayesian Network (BN), and Support Vector Machine (SVM). The data used for this research is precipitation data and daily flow of Gamasiab River in Nahavand during 10 years period (1381-1391). Results indicated that the relative superiority of the gene expression planning model to other models and better performance of SVM model in comparison with BN in daily river flow modeling. In addition, implementing gene expression planning model was faster than other models and could provide results in a short time. The SVM model is also more fitted to estimate the final minimum values. Finally, GEP model with coefficient of determination of 0.9230 and root mean square of 0.5867 in the training phase and coefficient of determination of 0.9025 and root mean square of 0.4936 in the test phase was selected as the superior model.
