Daily river flow forecasting in a semi-arid region using twodatadriven

نویسندگان

  • Ahad Tavasoli Range and Watershed Management Dept., Hormozgan University, Bandarabas, Iran
  • Ahmad Nohegar Programming and Environment Management Dept., Environment Faculty, University of Tehran, Tehran, Iran
  • Arash Malekian Faculty of Natural Resources, University of Tehran, Karaj, Iran
  • Hanieh Asadi Watershed Management Dept., Trabiat Modares University, Noor, Iran
  • Mahdi Safari Faculty of Agriculture, Engineering, Bahonar Kerman University, Kerman, Iran
چکیده مقاله:

Rainfall-runoff relationship is very important in many fields of hydrology such as water supply and water resourcemanagement and there are many models in this field. Among these models, the Artificial Neural Network (ANN) wasfound suitable for processing rainfall-runoff and opened various approaches in hydrological modeling. In addition,ANNs are quick and flexible approaches which provide very promising results, and are cheaper and simpler toimplement than their physically based models. Therefore, this study evaluated the use of ANN models to forecastdaily flows in Bar watershed, a semi-arid region in the northwest Razavi Khorasan Province of Iran. Two differentneural network models, the multilayer perceptron (MLP) and the radial basis neural network (RBF), were developedand their abilities to predict run off were compared for a period of fifty-five years from 1951 to 2006. The bestperformance was achieved based on statistical criteria such as RMSE, RE and SSE. It was found that MLP showed agood generalization of the rainfall-runoff relationship and is better than RBF. In addition, 1-day antecedent runoffaffected river flow, such that the statistical criteria decreased but the 5-day antecedent rainfall remained unaffected.Furthermore, considering MLP, RE and RMSE, the best model produced the values 46.21 and 0.75 while the RBFmodel recorded 177.60 and 0.82, respectively.

برای دانلود باید عضویت طلایی داشته باشید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

daily river flow forecasting in a semi-arid region using twodatadriven

rainfall-runoff relationship is very important in many fields of hydrology such as water supply and water resourcemanagement and there are many models in this field. among these models, the artificial neural network (ann) wasfound suitable for processing rainfall-runoff and opened various approaches in hydrological modeling. in addition,anns are quick and flexible approaches which provide very ...

متن کامل

Statistical model of daily flow in arid and semi arid regions

Abstract Stochastic model for synthetic data generation is not available for daily flows of intermittent streams. Such a model is required in the planning and operation of structures on an intermittent stream for purposes where short time flow fluctuations are important. In this study a model is developed for such a case. The model consists of four steps: determination of the days on which fl...

متن کامل

Trends in precipitation and stream flow in the semi-arid region of Atrak River Basin, North Khorasan, Iran

In this paper trends of precipitation and stream flow are analyzed in the Atrak River basin in the North Khorasan province. Normal score linear regression, Mann-Kendall, and Seasonal Kendall trend tests were adopted. Three precipitation variables and two stream flow variables including total precipitation, maximum daily precipitation, and number of rainy days, mean discharge and peak discharge ...

متن کامل

Estimating Daily Reference Evapotranspiration in a Semi-Arid Region Using Remote Sensing Data

Estimating daily evapotranspiration is challenging when ground observation data are not available or scarce. Remote sensing can be used to estimate the meteorological data necessary for calculating reference evapotranspiration ETo. Here, we assessed the accuracy of daily ETo estimates derived from remote sensing (ETo-RS) compared with those derived from four ground-based stations (ETo-G) in Kur...

متن کامل

Groundwater level fluctuation forecasting Using Artificial Neural Network in Arid and Semi-Arid Environment

In arid and semi-arid environments, groundwater plays a significant role in the ecosystem. In the last decades, groundwater levels have decreased due to the increasing demand for water, weak irrigation management and soil damage. For the effective management of groundwater, it is important to model and predict fluctuations in groundwater levels. In this study, groundwater table in Kashan plain ...

متن کامل

Forecasting Crop Water Requirement By Et-Hs model For Arid and Semi Arid Region of Iran

Estimating actual crop water requirement and irrigation schedule are essential for designing of the irrigation systems, storage construction and water conveyance structures. Many models have developed for estimating crop water requirement. Although most of these methods need different climatic parameters, providing and forecasting all of these parameters always are not available. Most of the ti...

متن کامل

منابع من

با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ذخیره در منابع من قبلا به منابع من ذحیره شده

{@ msg_add @}


عنوان ژورنال

دوره 20  شماره 1

صفحات  11- 21

تاریخ انتشار 2015-01-01

با دنبال کردن یک ژورنال هنگامی که شماره جدید این ژورنال منتشر می شود به شما از طریق ایمیل اطلاع داده می شود.

میزبانی شده توسط پلتفرم ابری doprax.com

copyright © 2015-2023