Application of Artificial Neural Network for Groundwater Level Simulation in Amritsar and Gurdaspur Districts of Punjab, India
Received: 21-Apr-2015 / Accepted Date: 28-Apr-2015 / Published Date: 08-May-2015 DOI: 10.4172/2157-7617.1000274
In this paper, the most stable and efficient neural network configuration for predicting groundwater level in Amritsar and Gurdaspur districts of Punjab, India is identified. For predicting the model efficiency and accuracy, different types of network architectures and training algorithms are investigated and compared. It has been found that accurate predictions can be achieved with a standard feed forward neural network trained with the Levenberg–Marquardt algorithm providing the best results. Good estimation of groundwater level can be achieved by dividing the boreholes/observation wells into different groups of data and designing distinct networks which is validated by the ANN technique and the degree of accuracy of the ANN model in groundwater level forecasting is within acceptable limits. The ANN method has been found to forecast groundwater level in Amritsar and Gurdaspur districts of Punjab, India.
Keywords: Artificial neural networks; Groundwater level forecasting; Amritsar; Gurdaspur; Punjab; Aquifer exploitation
Groundwater always has been as one important and reliable resource to supply drinking and agriculture water and considered to be a reliable resource for supplying consumption needs of different users . Groundwater Reservoir also called ‘aquifer’ is a complicated system and is exposed to either natural or artificial stresses on the aquifer in different chronological levels resulting in the fluctuations of groundwater level. Thus, to exploit and manage groundwater, mathematical models are needed to predict groundwater level fluctuations. Conceptual and physically-based models are considered to be the main tools for depicting hydrological variables and understanding the physical processes taking place in a system  but they do have practical limitations. When data are not sufficient, getting accurate predictions is more important than conceiving the actual physics. Empirical models remain a good alternative method and generally provide useful results without a costly calibration time . Artificial Neural Network (ANN) models are such ‘black box’ models with particular properties which are greatly suited to dynamic nonlinear system modeling . ANN has proven to be an extremely useful method for modeling and forecasting of hydrological variables/processes [5-8].
Coppola et al.  showed that ANN has potential in accurately predicting of groundwater level fluctuations in an unsteady state of an aquifer influenced by pump and different weather conditions. They noted that predicted results of ANN are more accurate than quantitative models and also showed that ANN models are good at simulating karstic and leaky aquifers where other numerical models are weak in such cases.
In another study by Taiyuan et al.  the effects of hydrological, weather and humidity conditions on groundwater level were simulated by neural networks in lower part of Shenyang river basin, North West of china. The used ANN model was able to predict groundwater level with the average error of 0.37 m or lower with the high accuracy. Nadiri  had dealt with evaluating of artificial neural network (FFN-LM) ability in modeling of complex aquifer of Tabriz.
In this paper, an attempt has been made to identify the most stable and efficient neural network configuration for predicting groundwater level in the Amritsar and Gurdaspur districts of Punjab. The main purpose of this article is to use artificial neural networks especially feed forward back propagation neural networks to simulate and predict groundwater level. Amritsar and Gurdaspur districts of Punjab were chosen as the study area as the groundwater resources have been overexploited in Punjab including Amritsar and Gurdaspur districts during the last two decades. The groundwater level and quality in Punjab have been decreasing steadily as discussed in numerous studies carried out in different parts of Punjab and Indo-Gangetic basin by various researchers [12-34]. For the planning and management of groundwater resources in the region timely and accurate enough forecasts of ground water levels are required. Therefore, ANN technique was used for simulating the groundwater levels in Amritsar and Gurdaspur districts based on groundwater level data of 4 observation wells in 4 blocks namely Ajnala, Majitha, Rayya and Tarsika of Amritsar and 8 observation wells in 8 blocks namely Batala, Dera Baba Nanak, Dina Nagar, Gurdaspur, Fatehgarh Chrian, Kahmuwan, Kalanaur and Sri Hargovindpur taken from the Punjab Water Resources and Environment Directoate, Chandigarh.
The Study Area
Amritsar district is located in northern part of Punjab state and lies between 31° 28’ 30” to 32° 03’15” north latitude & 74° 29’ 30” to 75° 24’ 15” east longitude and having a total area of 5056 sq.km (Figure 1) while Gurdaspur district lies between 31° 36’ to 32° 34’ north latitude & 74° 56’ to 75° 24’ east longitude and having a total area of 3513 sq.km The districts fall in between Ravi river and Beas river. The area has a semiarid climate typical of Northwestern India and experiences four seasons primarily: winter season (December to March) with temperature ranges from 0°C to 15°C, summer season (April to June) where temperatures can reach 42°C, monsoon season (July to September) and post-monsoon season (October to November). Annual rainfall is about 681 mm in Amritsar and 1013 mm in Gurdaspur district.
The study area is a part of Upper Bari Doab. Soils in the study area are fine to coarse loamy, calcareous and are well drained. The main aquifer group is granular zone with alternate layers of thick or thin clay. The aquifer groups are laterally distributed. The total thickness of the alluvium ranges from 300-450 m and there may be 5-6 aquifers.
The available data required to simulate groundwater were monthly rainfall and water level data. These data with one-month time step were introduced to the ANN as input. Water level of plain observation wells of depth of 60 m was available for 2006-2013. While, monthly rainfall data were available for the period 2006-10.
On the basis of the studies carried out by Lallahem et al. , Nadiri  and Mirarabi  time series data of ground water levels and rainfall have been selected for the present studies. Rainfall is considered as one of the important inputs for the ground water level forecasting model. To design network, analogues output and input data of the same period with an equivalent time step were used. Therefore, after processing the available data of water level (main goal in this study) and rainfall, the time step selected for all data is monthly.
Artificial Neural Network (ANN)
Artificial neural networks (ANN), which operates, analogous to that of biological neurons system are getting more and more attention in the area of hydrology and water resources . ANN models are basically data driven models and in hydrological context they are considered as black box models . ANN models can be a good alternative to mathematical models as they have a high processing ability and can execute the future scenarios very fast. Hydrological processes are generally nonlinear in nature. The ability of ANN to model nonlinear processes advocates their use in hydrology and water resources to model various hydrological processes . For the first time McCulloch and Pitts  presented a basic artificial neural network model. With the development of computational techniques, various researchers have suggested a different ANN structures to model various real life problems.
Studies carried out by Aziz and Wong , ASCE [40,41], Abd¨usselam , Agarwal et al. , Gidson , Hagan et al. , Lohani et al. , Taslloti  have demonstrated the application of ANN in rainfall –runoff modeling. In hydrological forecasting the application of ANN is very effective and the works of Jones , Kar et al. , Lohani et al. [3,8], Maier and Dandy  and Uddameri  suggested that the artificial neural networks provides an alternate and effective over the conventional methods. Previous studies have shown that ANN has shown their capability in reproducing the unknown rainfall-runoff relationship, gauge-discharge relationship, dischargesediment relationship, [5-7] and modeling of hydrological time series . Rosmina et al.  mentioned that the modern techniques can be applied to predict and understand the temporal and spatial relations between effective parameters in groundwater level. In order to investigate the effects of hydrological, meteorological and human factors on the ground water levels a three layer back propagation artificial neural network model was applied by the Shaoyuan et al.  for two regions in the Minquin oasis, located in the lower reach of Shiyang river Basin, China, Jothiprakash and Suhasini  demonstrated the capability of ANN model to predict ground water level in Sri ram Sagar reservoir project area, Andhra Pradesh, India, Studies carried out by Zahra and Gholamreza , Kavitha and Naidu  and Bessaih et al.  investigated the use of ANN to forecast ground water level.
Application of neural networks
For developing ANN model generally the data sets are required for the training, validation and testing of the ANN networks. In this study, observed rainfall data were used to train and validate an artificial neural-network. The learning algorithm called the back propagation was applied to the single hidden layer. Scaled Conjugate Gradient (SCG), Levenberg–Marquardt (LM), Gradient Descent with Momentum (GDM), and back propagation were used for the purpose. The Neural Network has been optimized using the MATLAB Neural Network Toolbox. In the training stage, to define the output accurately, the number of neurons was increased step-by-step in the hidden layer. Inputs and outputs have been normalized in the range of (0–1) as NN works efficiently within this range. Neurons in the input layer have no transfer function. Logistic sigmoid (logsig) transfer function has been used in hidden layer while purelinear (purelin) transfer function has been used in output layer. After the successful training of the network, the network was tested with the test data. Using the results produced by the network, statistical methods have been used to make comparisons.
Measures of prediction performance
The prediction performance of ANN model results have been investigated by the statistical methods e.g. RMSE and coefficient of determination (R2) between network output and network target outputs in training and validation groups.
Results and Discussion
The aim of using ANN is to test the ability to predict groundwater level fluctuations in Amritsar and Gurdaspur districts of Punjab. The network has input parameters such as rainfall of current and previous two months, groundwater level of current and two previous months and one output parameter i.e. forecasted groundwater level with 6 month lead period. These monthly data were introduced to the ANN as input. Groundwater level of observation wells was available for 2006-2013.
To design networks, analogues output and input data of the same period with an equivalent step time were used. Training and validation data included for the period 2006 to 2013 for all networks. To consider the efficiency of every algorithm and reach to the best desired conditions, several parameters, and variables such as number of neurons in hidden layers, percent of dividing data into training and validation sets, learning rate, number of repeating epochs and momentum coefficient were varied. Among these conditions, number of neurons and percent of dividing data to the training and validation sets are more effective in changing conditions and reaching to a desired state of network than others are. Optimal network architecture was selected based on the minimum Root Mean Square Error (RMSE). In order to avoid overfitting of ANNs "early stopping" method has been applied.
For artificial neural network modelling input parameter-rainfall of the study area and previous month and current month water level were selected as input to the model and six month ahead water levels in observation wells were selected as output and were normalized. These parameters were scaled between zero and one. Then, to increase the predicting capability of the network, the input and output data were divided into two groups for each data set (i.e. calibration data from 2006 to 2010 and validation data from 2011 to 2013).
To validate the neural networks models, new observation data were introduced to the networks and simulated groundwater level were compared with actual groundwater of all observation wells in the study area (Figures 2 and 3). As the figures show, the neural networks can simulate groundwater level with reasonable accuracy in most of the observation wells.
To evaluate the accuracy of the designed networks, RMSE and coefficient of determination have been computed. It is observed that (Table 1) the values of RMSE varies from 0.20 to 1.73 m during calibration and 0.35 to 2.26 m during validation. Furthermore, the coefficient of determination for both the calibration and validation data shows that the forecasted groundwater tables show reasonably good correlations.
|Location||RMSE (m)||R2||RMSE (m)||R2|
|Dera Baba Nanak||0.31||0.934||0.42||0.906|
Table 1: RMSE and coefficient of determination.
The goal of this study was to evaluate the feed forward neural network as a possible tool for predicting groundwater level in Amritsar and Gurdaspur districts of Punjab. Rainfall of the study area and previous months groundwater levels were taken as input, and the future groundwater levels with six month lead period were the output. A back propagation (BP) neural network model algorithms have been studied in one hidden layers. Number of neurons on hidden layer also varied to optimize network. Based on statistical indices (R2 and RMSE), the best networks were determined for each station (Table 1). These networks were trained with developed ANN network algorithm. To these neural networks, new observation data were introduced to the networks. Then, forecasted groundwater levels were compared with actual groundwater of all observation wells in the study area. There was a good fit between real and calculated data by considering all observation wells.
Authors wish to thank Director, National Institute of Hydrology for all his support and encouragement for this study. Dr. Gopal Krishan thanks Dr. Alan MacDonald, Dr. Dan Lapworth and Dr. Helen Bonsor (BGS-DFID) for their support during the study. Authors thank Er. K.S. Takshi & Er. J.P. Singh, Irrigation department, Punjab and Er. P.S. Bhogal, Director, Punjab Water Resources Environment Directorate, Chandigarh.
- Firouzkouhi R (2011) Simulating groundwater resources of Aghili-Gotvand plain by using mathematical model of finite differences. Msd. Thesis, ShahidChamran University of Ahwaz, Iran.
- Evrendilek F, Karakaya N (2015) Spatiotemporal modeling of saturated dissolved oxygen through regressions after wavelet denoising of remotely and proximally sensed data. Earth Sci Inform 8: 247-254.
- Lohani AK, Goel NK, Bhatia KKS (2014) Improving real time flood forecasting using fuzzy inference system. J Hydrol 509: 25-41.
- Agarwal A, Lohani AA, Singh RD, Kasiviswanathan KS (2013) Radial Basis Artificial Neural Network Models and Comparative Performance. J Indian Water Resour Soc 33: 1-8.
- Lohani AK, Goel NK, Bhatia KKS (2006) Takagi-Sugeno fuzzy inference system for modeling stage-discharge relationship. J Hydrol 331: 146-160.
- Lohani AK, Goel NK, Bhatia KKS (2007) Deriving stage–discharge–sediment concentration relationships using fuzzy logic. HydrolSci J 52: 793-807.
- Lohani AK, Goyal NK, Bhatia KKS (2011) Comparative study of neural network, fuzzy logic and linear transfer function techniques in daily rainfall-runoff modelling under different input domains. Hydrol Process 25: 175-193.
- Lohani AK, Kumar R, Singh RD (2012) Hydrological time series modeling: A comparison between adaptive neuro-fuzzy, neural network and autoregressive techniques. J Hydrol 442: 23-35.
- Coppola E, Szidarovszky F, Poulton M, Charls E (2003) Artificial neural network approach for predicting transient water levels in multilayered groundwater system under variable state, pumping, and climate conditions. J Hydro Eng 8: 348-380.
- Taiyuan F, Shaozhong K, Zailin H, Shaqiun C, Xiaomin M (2007) Neural Networks to Simulate Regional Ground Water Levels Affected by Human Activities. Groundwater 46: 80-90.
- Nadiri A (2007) Predicting groundwater level surrounding Tabriz city. Msd. Thesis, Tabriz University, Iran.
- Chopra RPS, Krishan G (2014a) Analysis of aquifer characteristics and groundwater quality in southwest Punjab, India. Earth Sci Eng 4: 597-604.
- Chopra RPS, Krishan G (2014b) Assessment of groundwater quality in Punjab. J Earth SciClim Change 5: 243.
- Krishan G, Chopra RPS (2015) Assessment of water logging in south western (SW) parts of Punjab, India-a case study from Muktsar district. NDC-WWC J 4: 7-10.
- Krishan G, Takshi KS, Rao MS, Kumar S, Lohani AK (2015a) Spatial analysis of groundwater level in Punjab, India. In: Proceedings of an International conference “India Water Week 2015-Water Management for Sustainable Development" (IWW-2015), 13-17 January, 2015 at New Delhi, India 125.
- Krishan G, Lohani AK, Rao MS, Kumar S (2015b) Spatiotemporal variability analysis of groundwater level for water resources development and management in Northern Punjab, India. J Environ Analytical Toxicology (in press).
- Krishan G, Lapworth DJ, Rao MS, Kumar CP, Smilovic M, et al. (2014a) Natural (Baseline) Groundwater Quality In The Bist-Doab Catchment, Punjab, India: A Pilot Study Comparing Shallow and Deep Aquifers. Int J Earth Sci Eng 7: 16-26.
- Krishan G, Lohani AK, Rao MS, Kumar CP, Takshi KS (2014b) Groundwater fluctuation and trend in Amritsar, Punjab, India. In: Geo-statistical and Geospatial approaches for the characterization of natural resources in the environment: challenges, processes and strategies (Editor: N. JanardhanaRaju). Capital Publishing House, New Delhi 108-111.
- Krishan G, Rao MS, Purushothaman P, Rawat YS, Kumar CP, et al. (2014c) Groundwater Resources in Bist-Doab Region, Punjab, India-an overview. NDC-WWC J 3: 5-13.
- Krishan G, Rao MS, Loyal RS, Lohani AK, Tuli NK, et al. (2014d) Groundwater level analyses of Punjab, India: A quantitative approach. Octa J Environ Res 2: 221-226.
- Krishan G, Lohani AK, Rao MS, Kumar CP (2014e) Prioritization of groundwater monitoring sites using cross-correlation analysis. NDC-WWC J 3: 28-31.
- Krishan G, Rao MS, Kumar CP, Pankaj G, Prabhat S (2014f) Assessment of salinity and groundwater quality with special emphasis to fluoride in a semi-arid region of India. J Earth Sci Clim Change 5: 149.
- Krishan G, Garg P, Takshi KS, Lohani AK, Rao MS, et al. (2014g) Monitoring of Groundwater Fluctuations and Trend in Parts of Northern Punjab (vern. Majha), India. In: Proceedings of an International conference on “Annual Water Resources Association 2014 AWRA” during 3-6 November, 2014 at Virginia, USA.
- Krishan G, Rao MS, Lohani AK, Kumar CP, Takshi KS, et al. (2014h) Assessment of groundwater level in southwest Punjab, India. Hydraulics, Water resources, Coastal & Environmental Engineering-Hydro 2014 (Editors: H.L. Tiwari, S. Suresh, R.K. Jaiswal) Excellent Publishing House, New Delhi. 23: 248-254.
- Krishan G, Lohani AK, Rao MS, Kumar CP, Semwal P (2013a) Optimization of groundwater monitoring network in Bist-Doab, Punjab. In: International Conference “India Water Week 2013-Efficient Water Management: Challenges and Opportunities" (IWW-2013)” 274.
- Krishan G, Rao MS, Lapworth DJ, MacDonald AM (2013b) Indo-gangetic groundwater resilience project- Punjab case study. In: Report of IBG-Groundwater Resilience Project (eds. H.C. Bonsor and A.M. MacDonald) during 4-7 November 2013 at India Habitat Centre, New Delhi. BGS Internal Report, IR/13/060.
- Krishan G, Rao MS, Kumar CP, Prabhat S (2013c)Identifying Salinization Using Isotopes and ionchemistry in Semi-Arid Region of Punjab, India. J GeolGeosci 2: 4.
- Dan L, Krishan G, Rao MS, MacDonald Alan (2014a) Intensive Groundwater Exploitation in the Punjab – an Evaluation of Resource and Quality Trends. Technical Report. NERC Open Research Archive, BGS-UK.
- Lapworth DJ, Krishan G, Macdonald AM, Rao MS, Gooddy DC, et al. (2014b) Using Environmental Tracers to Understand the Response of Groundwater Resources in Nw India to Sustained Abstraction. In Proc. of 41st International Conf. of International Association of Hydro-geologist (IAH-2014) on Groundwater: Challenges and Strategies during Sep. 18-19, 2014. at Marrakech Morocco.
- Lohani AK, Krishan G, Rao MS, Kumar S (2015) Groundwater Level Simulation Using Artificial Neural Network: aA Case Study from Punjab, India. In: Proceedings of an International conference “IndiWater Week 2015-Water Management for Sustainable Development" (IWW-2015), 13-17 January, 2015 at New Delhi, India. pp. 114.
- Macdonald A, Bonsor H, Rao MS, Krishan G, Steenburgen FV, et al. (2013) Groundwater Topologies In the Indo Gangetic Basin. In Proc. of International Conf. on Advances in Water Resources Development &Mangement held at PU, Chandigarh during Oct. 23-27, 2013 P: 2.
- Macdonald AM, Bonsor HC, Krishan G, Rao MS, Ahmed KM, et al. (2014) Groundwater in the Indo-Gangetic Basin: Evolution of Groundwater Typologies. In Proc. of 41st International Conf. of International Association of Hydro-geologist (IAH-2014) on Groundwater: Challenges and Strategies during Sep. 18-19, 2014 at Marrakech Morocco.
- Rao MS, Purushothaman P, Krishan G, Rawat YS, Kumar CP (2014) Hydrochemical and Isotopic Investigation of Groundwater Regime in Jalandhar and Kapurthala Districts, Punjab, India. Int J Earth Sci Eng 7: 06-15.
- Sharma M, Rao MS, Rathore DS, Krishan G (2014) An integrated approach to augment the depleting ground water resource in bist- doab, region of Punjab, India. Int J Earth Sci Eng 7: 27-38.
- Lallahem S, Manina J, Hani A, Najjar Y (2005) On the use of neural networks to evaluate groundwater levels in fractured porous media. J Math Compul Model 37: 1047-1061.
- MirarabiA (2009) Predicting groundwater level in Birjand plain by artificial neural network. articles complex of twelfth conference of geology society of Iran 1-8.
- Menhaj MB (2008) Fundamental of neural network. vol1, Industrial Amir Kabir University, Tehran, Iran.
- McCulloch W (1984) A logical calculus of the ideas immanent in nervous activity. Bull math Biophys 5.
- Aziz ARA, Wong KFV (1992) Neural network approach the determination of aquifer parameter. Groundwater 30: 164-166.
- ASCE Task Committee on Application of Artificial Neural Networks in Hydrology (2000a) Artificial neural networks in hydrology, 1: preliminary concepts. J Hydro Eng ASCE 5: 115-123.
- ASCE Task Committee on Application of Artificial Neural Networks in Hydrology (2000b) Artificial neural networks in hydrology, II: hydrology applications. J Hydro Eng ASCE 5: 124-137.
- Abd¨usselam A (2007) Forecasting surface water level fluctuations of Lake Van by artificial neural networks. Water Resour Manage 21: 399-408.
- Gidson S (2009) Application of Artificial Neural Networks in the Field of Geohydrology. Msd. Thesis, University of the Free State.
- Hagan H, Demuth M, Beale, Martin Hagan (2002) Neural Network Design. (2ndedn)Oklahoma State University,Oklahoma.
- Taslloti B (2004) Estimating groundwater level by using MODFLOW and artificial neural network. Msd. Thesis, TarbiatModares University of Tehran, Iran.
- Jones MT (2008) Artificial intelligence a systems approach, neural network. (1stedn) Sudbury, Mass, Jones and Bartlett Publishers, England 498.
- Kar AK, Lohani AK, Goel NK, Roy GP (2011) Development of Flood Forecasting System Using Statistical and ANN Techniques in the Downstream Catchment of Mahanadi Basin, India. J Water Resour Protection 2: 880-887.
- Maier HR, Dandy GC (2000) Neural networks for the prediction and forecasting of water resources variables: a review of modeling issues and applications. Environ Modell Softw 15: 101-124.
- Uddameri V (2006) Using statistical and artificial neural network models to forecast potentiometric levels at a deep well in South Texas. Environ Geol 51: 885-895.
- Rosmina B, Nabil B, Charles B, Suhaila S (2007) Artificial Neural Network for Precipitation and Water Level Predictions of Bedup River. IAENG Int J Comput Sci 34: 2.
- Shaoyuan Feng, Shaozhong Kang, ZailinHuo, Shaojun Chen, Xiaomin Mao (2008) Artificial Neural Network for Precipitation and wound water 46: 80-90.
- Jothiprakash V, Sakhare S (2008) Ground Water Level Fluctuations using Artificial Neural Network. The 12th International Conference of International Association for Computer Methods and Advances in Geomechanics (IACMAG).
- Ghadampour Z, Rakhshandehroo G (2010) Using Arificial Neural Networks to Forsecast Groundwater Depth in Union County Well. World Acad Sci Eng Technol 38.
- Mayilvaganan MK, Naidu KB (2010) Comparative Study of ANN and ANFIS for the Prediction of Groundwater Level of a Watershed. Global J Math Sci: Theory and Practical 3: 299-306.
- Bessaih N, Qureshi M, Al-Jabri FS, Al-Harmali IR, Al Naamani ZA (2014) Groundwater Water Level Prediction in Wadi El Jezzy Catchment Using ANN. Proceedings of the World Congress on Engineering 2014 Vol I, WCE 2014, July 2-4, 2014, London, U.K.
Citation: Lohani AK, Krishan G (2015) Application of Artificial Neural Network for Groundwater Level Simulation in Amritsar and Gurdaspur Districts of Punjab, India. J Earth Sci Clim Change 6: 274. Doi: 10.4172/2157-7617.1000274
Copyright: ©2015 Lohani AK, et al. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.