XML Persian Abstract Print

Department of Nature Engineering, Faculty of Natural Resources, University of Guilan, Rasht, Iran
Abstract:   (379 Views)
Introduction and Objective: Predicting the rainfall-runoff process is an important issue in the management of natural resources as well as water resources. However, this process has its own complexities and many effective factors, including rainfall factors (rainfall intensity and value), vegetation (type and canopy), soil factors (soil texture, initial soil moisture, and soil permeability) and It is the way of land management. The current research aimed to provide a model for predicting the rainfall-runoff process using artificial neural network (ANN) modeling and field runoff data.
Material and Methods: The research was conducted on a hillslope located in the University of Guilan with clay-loam soil, in the form of replicated pairs of plots in different vegetation treatments and land management. Moreover, using a rain gauge set, the amount of rainfall was measured after each rainfall event. The amount of runoff was also estimated by the plots, and from the difference between the amounts of rainfall and runoff, the amounts of initial loss on the surface of each plot were calculated for each rainfall event in different previous soil moisture conditions. Then, in order to model the obtained data, they were divided into two categories of training and test data. The parameters of runoff values were considered as output of the model and rainfall values, the percentage of rangeland and tree cover, the previous soil moisture, and the percentage of litter were considered as the inputs of the model.
Results: The values of R2=0.97, MSE=0.004 and R2=0.91, MSE=4.2 were obtained in the training stage and the testing stage of the model, respectively, and finally a high-performance model for simulating the rainfall-runoff process was obtained. The result of modeling process showed that the rangeland cover has the highest efficiency on runoff control.
Conclusion: The mentioned model can be used to predict the effect of different vegetation scenarios on runoff generation or to estimate runoff based on the rainfall of meteorological stations.
Full-Text [PDF 1372 kb]   (102 Downloads)    
Type of Study: Research | Subject: حفاظت آب و خاک
Received: 2023/09/17 | Revised: 2023/10/20 | Accepted: 2023/10/21

Add your comments about this article : Your username or Email:

Send email to the article author

Rights and permissions
Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

© 2024 CC BY-NC 4.0 | Journal of Watershed Management Research

Designed & Developed by : Yektaweb