Iran-Water Resources Research

Iran-Water Resources Research

Forecasting Groundwater Level In Saadat-Shahr Plain, Iran, Using Artificial Neural Networks

Document Type : Original Article

Authors
M.R Nikmanesh 1
G.R Rakhshandehroo 2
1 Faculty of Civil Engineering Department, Islamic Azad University, Arsanjan Branch, Iran
2 Associated Professor of Civil Engineering Department, Shiraz University, Shiraz, Iran
Abstract
A proper architectural design of the Artificial Neural Network (ANN) models can provide a robust tool in water resources modeling and forecasting. The performance of different neural networks in a groundwater level forecasting was examined by researchers in order to identify an optimal ANN architecture that can provide accurate predictions up to 24 months ahead. In this study the Saadat-shahrPlain in Fars Province in central Iran was chosen as the study area. All networks were trained for an 8-year period of data and calibrated for a 24-month period. Experimental results showed that the most accurate forecast (for up to 24 months ahead) is achieved with an FNN trained with the LM algorithm
Keywords
Artificial Neural Network
Groundwater level forecasting
Saadat-shahr Plain
نورانی، و. اصغری مقدم، ا. و ندیری، ع.،(1385)،" ارزیابی سطح آبهای زیرزمینی در آبخوان محدوده شهر تبریز با شبکه‌های عصبی مصنوعی"، سومین کنگره مهندسی عمران، تبریز.
گزارش مطالعات آبهای زیرزمینی دشت سعادت شهر، (1387) شرکت مهندسین مشاور فارساب صنعت، شیراز.
Affandi, A.K. and Watanabe, K., (2007), "Daily groundwater level fluctuation forecasting using soft computer technique," Nature and Science, 5(2), pp.1-10.
Coulibaly, P., Anctil, F., Aravena, R., and Bobee, B., (2001)," Artificial neural network modeling of water table depth fluctuation," Water Resour. Res., 37,  pp.885-896.
Daliakopoulos, N. I., Coulibaly, P.,  and Tsanis, I. K., (2005), "Ground water level forecasting using artificial neural networks," J. Hydrol., 309,pp. 229-240.
 
 
Iran-Water Resources Research
Volume 7, Issue 1
Summer 2011
Pages 82-86

  • Receive Date 16 May 2009
  • Accept Date 08 December 2010