The Use of NARX Neural Networks to Forecast Daily Groundwater Levels

The lack of information to manage groundwater for irrigation is one of the biggest concerns for farmers and stakeholders in agricultural areas of Mississippi. In this study, we present a novel implementation of a nonlinear autoregressive with exogenous inputs (NARX) network to simulate daily groundwater levels at a local scale in the Mississippi River Valley Alluvial (MRVA) aquifer, located in the southeastern United States. The NARX network was trained using the Levenberg-Marquardt (LM) and Bayesian Regularization (BR) algorithms, and the results were compared to identify an optimal architecture for the forecasting of daily groundwater levels over time. The training algorithms were implemented using different hidden node combinations and delays (5, 25, 50, 75, and 100) until the optimal network was found. Eight years of daily historical input time series including precipitation and groundwater levels were used to forecast groundwater levels up to three months ahead. The comparison between LM and BR showed that NARX-BR is superior in forecasting daily levels based on the Mean Squared Error (MSE), coefficient of determination (R2), and Nash-Sutcliffe coefficient of efficiency. The results showed that BR with two hidden nodes and 100 time delays provided the most accurate prediction of groundwater levels with an error of ± 0.00119 m. This innovative study is the first of its kind and will provide significant contributions for the implementation of data-based models (DBMs) in the prediction and management of groundwater for agricultural use.

[1]  J. Tóth.  A Theoretical Analysis of Groundwater Flow in Small Drainage Basins , 1963 .

[2]  J. Nash,et al.  River flow forecasting through conceptual models part I — A discussion of principles☆ , 1970 .

[3]  I. J. Leontaritis,et al.  Input-output parametric models for non-linear systems Part II: stochastic non-linear systems , 1985 .

[4]  R. D. Lorenz,et al.  A structure by which a recurrent neural network can approximate a nonlinear dynamic system , 1991, IJCNN-91-Seattle International Joint Conference on Neural Networks.

[5]  David J. C. MacKay,et al.  Bayesian Interpolation , 1992, Neural Computation.

[6]  Mohammad Bagher Menhaj,et al.  Training feedforward networks with the Marquardt algorithm , 1994, IEEE Trans. Neural Networks.

[7]  Hava T. Siegelmann,et al.  Computational capabilities of recurrent NARX neural networks , 1997, IEEE Trans. Syst. Man Cybern. Part B.

[8]  Sun-Yuan Kung,et al.  A delay damage model selection algorithm for NARX neural networks , 1997, IEEE Trans. Signal Process..

[9]  Martin T. Hagan,et al.  Gauss-Newton approximation to Bayesian learning , 1997, Proceedings of International Conference on Neural Networks (ICNN'97).

[10]  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..

[11]  J. K. Arthur,et al.  Hydrogeology, model description, and flow analysis of the Mississippi River alluvial aquifer in northwestern Mississippi , 2001 .

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

[13]  D. Poston,et al.  Agricultural Practices of the Mississippi Delta , 2004 .

[14]  M. G. Anderson.  Encyclopedia of hydrological sciences. , 2005 .

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

[16]  Nancy L. Barber,et al.  Estimated withdrawals from principal aquifers in the United States, 2000 , 2005 .

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

[18]  Adebayo Adeloye,et al.  Artificial neural network based generalized storage–yield–reliability models using the Levenberg–Marquardt algorithm , 2006 .

[19]  Ozgur Kisi,et al.  Streamflow Forecasting Using Different Artificial Neural Network Algorithms , 2007 .

[20]  Alison Adams,et al.  Field‐Scale Application of Three Types of Neural Networks to Predict Ground‐Water Levels 1 , 2007 .

[21]  C. Wax,et al.  A climatological basis for conserving groundwater and reducing overflow in aquaculture ponds in the Southeast United States , 2007 .

[22]  Eugen Diaconescu,et al.  The use of NARX neural networks to predict chaotic time series , 2008 .

[23]  K. P. Sudheer,et al.  Artificial Neural Network Modeling for Groundwater Level Forecasting in a River Island of Eastern India , 2010 .

[24]  W. Clark,et al.  Water Use Conservation Scenarios for the Mississippi Delta Using an Existing Regional Groundwater Flow Model , 2010 .

[25]  C. T. Green,et al.  The fate and transport of nitrate in shallow groundwater in northwestern Mississippi, USA , 2011 .

[26]  Ioannis K. Nikolos,et al.  Artificial Neural Network (ANN) Based Modeling for Karstic Groundwater Level Simulation , 2011 .

[27]  Fi-John Chang,et al.  Regional estimation of groundwater arsenic concentrations through systematical dynamic-neural modeling , 2013 .

[28]  Madan K. Jha,et al.  Groundwater-level prediction using multiple linear regression and artificial neural network techniques: a comparative assessment , 2013, Hydrogeology Journal.

[29]  Ramli Adnan,et al.  Flood prediction using NARX neural network and EKF prediction technique: A comparative study , 2013, 2013 IEEE 3rd International Conference on System Engineering and Technology.

[30]  A W Jayawardena.  Environmental and Hydrological Systems Modelling , 2014 .

[31]  Samad Emamgholizadeh,et al.  Prediction the Groundwater Level of Bastam Plain (Iran) by Artificial Neural Network (ANN) and Adaptive Neuro-Fuzzy Inference System (ANFIS) , 2014, Water Resources Management.

[32]  Ruixiu Sui,et al.  Irrigation Methods and Scheduling in the Delta Region of Mississippi: Current Status and Strategies to Improve Irrigation Efficiency , 2014 .

[33]  Ismail Yusoff,et al.  Application of the Artificial Neural Network and Neuro‐fuzzy System for Assessment of Groundwater Quality , 2015 .

[34]  A. Mercer,et al.  Identification of recharge zones in the Lower Mississippi River alluvial aquifer using high-resolution precipitation estimates , 2015 .

[35]  Dominique Salameh,et al.  Short-term relationships between emergency hospital admissions for respiratory and cardiovascular diseases and fine particulate air pollution in Beirut, Lebanon , 2015, Environmental Monitoring and Assessment.

[36]  Archana Sarkar,et al.  River Water Quality Modelling Using Artificial Neural Network Technique , 2015 .

[37]  Fi-John Chang,et al.  Modeling water quality in an urban river using hydrological factors--data driven approaches. , 2015, Journal of environmental management.

[38]  Gopal Krishan,et al.  Application of Artificial Neural Network for Groundwater Level Simulation in Amritsar and Gurdaspur Districts of Punjab, India , 2015 .

[39]  E. A. Affum,et al.  Total coliforms, arsenic and cadmium exposure through drinking water in the Western Region of Ghana: application of multivariate statistical technique to groundwater quality , 2015, Environmental Monitoring and Assessment.

[40]  Vassilis Z. Antonopoulos,et al.  Dispersion Coefficient Prediction Using Empirical Models and ANNs , 2015, Environmental Processes.

[41]  Huan Wang,et al.  A Comparative Study of Artificial Neural Networks, Support Vector Machines and Adaptive Neuro Fuzzy Inference System for Forecasting Groundwater Levels near Lake Okeechobee, Florida , 2015, Water Resources Management.

[42]  Nandita Singh,et al.  ANN modelling of sediment concentration in the dynamic glacial environment of Gangotri in Himalaya , 2015, Environmental Monitoring and Assessment.

[43]  Suet-Peng Yong,et al.  Scaled UKF–NARX hybrid model for multi-step-ahead forecasting of chaotic time series data , 2015, Soft Computing.

[44]  Yongbo Liu,et al.  Current Agricultural Practices Threaten Future Global Food Production , 2015 .

[45]  Li-Chiu Chang,et al.  Prediction of monthly regional groundwater levels through hybrid soft-computing techniques , 2016 .

[46]  Chuanmin Hu,et al.  The development of a non-linear autoregressive model with exogenous input (NARX) to model climate-water clarity relationships: reconstructing a historical water clarity index for the coastal waters of the southeastern USA , 2017, Theoretical and Applied Climatology.

[47]  W. Lee,et al.  Simultaneous hydrological prediction at multiple gauging stations using the NARX network for Kemaman catchment, Terengganu, Malaysia , 2016 .