GROUNDWATER LEVEL FORECASTING USING FEED FORWARD NEURAL NETWORK TRAINED WITH DIFFERENT ALGORITHMS

ABSTRACT Feed forward neural networks have been applied successfully in the field of hydrology. They are easy to handle and can approximate any input/output map. The performance of fourteen types of algorithms trained with feed forward neural network is examined to determine the combination that can predict the groundwater levels accurately and efficiently using a relatively short length of groundwater level records. Tirupati, located in Chittoor district of the drought-prone Rayalaseema region of Andhra Pradesh, South India was chosen as the study area as its groundwater levels declined in the last decade due to overexploitation. Results reveal that feed forward neural network trained with Levenberg-Marquardt algorithm predicts well the groundwater levels.

[1]  M. Bierkens.  Modeling water table fluctuations by means of a stochastic differential equation , 1998 .

[2]  J.J.B. Bronswijk,et al.  Modelling soil water dynamics in the unsaturated zone — State of the art , 1988 .

[3]  F. C. van Geera,et al.  An extension of Box-Jenkins transfer/noise models for spatial interpolation of groundwater head series , 1997 .

[4]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[5]  R Govindaraju,et al.  ARTIFICIAL NEURAL NETWORKS IN HYDROLOGY: II, HYDROLOGIC APPLICATIONS , 2000 .

[6]  Paulin Coulibaly,et al.  Groundwater level forecasting using artificial neural networks , 2005 .

[7]  M. S. Kamel.  Neural networks: the state of the art , 2000, ICM'99. Proceedings. Eleventh International Conference on Microelectronics (IEEE Cat. No.99EX388).

[8]  Martin Knotters,et al.  Estimating fluctuation quantities from time series of water-table depths using models with a stochastic component , 1997 .

[9]  J. Kaluarachchi,et al.  Parameter estimation using artificial neural network and genetic algorithm for free‐product migration and recovery , 1998 .

[10]  Wendy D. Graham,et al.  Comparison of univariate and transfer function models of groundwater fluctuations , 1993 .

[11]  R. S. Govindaraju,et al.  Artificial Neural Networks in Hydrology , 2010 .

[12]  Holger R. Maier,et al.  Neural networks for the prediction and forecasting of water resource variables: a review of modelling issues and applications , 2000, Environ. Model. Softw..

[13]  B. Bobée,et al.  Artificial neural network modeling of water table depth fluctuations , 2001 .

[14]  Reinder A. Feddes,et al.  Simulation model of the water balance of a cropped soil: SWATRE , 1983 .

[15]  Jan G. De Gooijer,et al.  TARSO modeling of water table depths , 1999 .

[16]  P. C. Nayak,et al.  Groundwater Level Forecasting in a Shallow Aquifer Using Artificial Neural Network Approach , 2006 .