To search, Click below search items. |
| All Published Papers Search Service |
|
|
|
Title |
Modeling of Groundwater Level Fluctuations in a Coastal Aquifer, using Data Driven Approaches |
|
Author |
Safieh Javadinejad, M. Nasrib |
| Citation |
Vol. 26 No. 8 pp. 81-88 |
|
Abstract |
Estimating the groundwater level (GWL) fluctuations is a vital requirement in hydrology and hydraulic engineering which is commonly settled through Artificial Intelligence (AI) models. This study investigated the performances of two different soft computing methods, Multilayer Perceptron Neural Network (MLPNN) and M5 model tree (M5-MT). The models are used in estimation of monthly GWL, observed in a shallow unconfined coastal aquifer. Data from observation wells located near the Ganjimatta, in India were used to estimate the GWL fluctuations. To do this, two scenarios were provided to achieve optimal input variables for modeling GWL at present time. The input parameters applied for developing the proposed models, were monthly time series of total rainfall, average temperature within their lag times, and historical groundwater level observations during the period of 1996 to 2006. The efficiency of each proposed model in Ganjimatt, was investigates in the training and testing stages. Performance evaluation indicated that the M5-MT outperforms the MLPNN model in estimating GWL in the aquifer case study. Based on the M5-MT approach, the development of this model, gives acceptable results for the Indian coastal aquifers. |
|
Keywords |
Groundwater level estimation; multilayer perceptron neural network; M5 model tree; Indian coastal aquifers; Time series modeling |
|
URL |
