Visitors: 1383

  MAZEDAN DIGITAL LIBRARY    

  JOURNAL MANAGEMENT SYSTEM

MDL
JMS  
MAZEDAN DIGITAL LIBRARY

Using Artificial Neural Network Technique Rainfall-Runoff Modeling in Khanpur Dam Watershedem

JOURNAL:MAZEDAN TRANSACTIONS ON ENGINEERING SYSTEMS DESIGN

Download pdf
# Authors First Online DOI Downloads Citations
1. Muhammad Taqi*, Usman Ali Naeem, Mujahid Iqbal, Afaq Ahmad 27 Sep 2021 na 17 0
Abstract

The rainfall-runoff analysis is extremely imperative in planning and developing water resources. In the present study, Rainfall-Runoff models based on artificial neural networks were developed for the Khanpur dam watershed Pakistan. The meteorological data used for this model was collected by the Water and Power Development Authority (WAPDA). Seven different types of rainfall-runoff models were designed using a daily meteorological parameter (Rainfall, Evaporation, Temperatures, and discharges). For each case, data sets were trained using fifteen neurons and two no of delays, and the data sets were distributed as (80, 10, 10) percent for training, testing, and validation respectively. These parameters were set using trial and error procedures. The above-constructed models were trained using the ANN lavenberg Marquard (trainlm) function. ANN models were validated using cross validation approach for generalization and best model is calibrated using actual data. All models performed well, the NS and R range between (62%-70%) and (0.69-0.82) respectively. the performance of the all models is in satisfactory to good.

Keywords

ANN, Matlab, Meteorological parameter, Rainfall-Runoff

References

  1. [1]    . R. Ghumman, Y. M. Ghazaw, A. R. Sohail, and K. Watanabe, “Runoff forecasting by artificial neural network and conventional model,” Alexandria Eng. J., vol. 50, no. 4, pp. 345–350, 2011, doi: 10.1016/j.aej.2012.01.005.

    [2]    A. R. Ghumman, I. S. Al-Salamah, S. S. AlSaleem, and H. Haider, “Evaluating the impact of lower resolutions of digital elevation model on rainfall-runoff modeling for ungauged catchments,” Environ. Monit. Assess., vol. 189, no. 2, 2017, doi: 10.1007/s10661-017-5766-0.

    [3]    M. Tu Pham, H. Vernieuwe, B. De Baets, and N. E. C. Verhoest, “A coupled stochastic rainfall-evapotranspiration model for hydrological impact analysis,” Hydrol. Earth Syst. Sci., vol. 22, no. 2, pp. 1263–1283, 2018, doi: 10.5194/hess-22-1263-2018.

    [4]    S. Nauman, Z. Zulkafli, A. H. Bin Ghazali, and B. Yusuf, “Impact assessment of future climate change on streamflows upstream of Khanpur Dam, Pakistan using Soil and Water Assessment Tool,” Water (Switzerland), vol. 11, no. 5, 2019, doi: 10.3390/w11051090.

    [5]    Z. M. Yaseen, M. F. Allawi, A. A. Yousif, O. Jaafar, F. M. Hamzah, and A. El-Shafie, “Non-tuned machine learning approach for hydrological time series forecasting,” Neural Comput. Appl., vol. 30, no. 5, pp. 1479–1491, 2018, doi: 10.1007/s00521-016-2763-0.