NARX neural network approach for the monthly prediction of groundwater levels in Sylhet Sadar, Bangladesh
doi: 10.19637/j.cnki.2305-7068.2020.02.003
NARX neural network approach for the monthly prediction of groundwater levels in Sylhet Sadar, Bangladesh
-
Abstract:
Groundwater is important for managing the water supply in agricultural countries like Bangladesh. Therefore, the ability to predict the changes of groundwater level is necessary for jointly planning the uses of groundwater resources. In this study, a new nonlinear autoregressive with exogenous inputs (NARX) network has been applied to simulate monthly groundwater levels in a well of Sylhet Sadar at a local scale. The Levenberg-Marquardt (LM) and Bayesian Regularization (BR) algorithms were used to train the NARX network, and the results were compared to determine the best architecture for predicting monthly groundwater levels over time. The comparison between LM and BR showed that NARX-BR has advantages over predicting monthly levels based on the Mean Squared Error (MSE), coefficient of determination (R2), and Nash-Sutcliffe coefficient of efficiency (NSE). The results show that BR is the most accurate method for predicting groundwater levels with an error of ± 0.35 m. This method is applied to the management of irrigation water source, which provides important information for the prediction of local groundwater fluctuation at local level during a short period.
-
Chan RWK, Yuen JKK, Lee EWM, et al. 2015. Application of nonlinear-autoregressiveexogenous model to predict the hysteretic behavior of passive control systems. Engineering Structures, 85: 1-10. https://doi.org/10.1016/j.engstruct.2014.12.007. quality. CLEAN–Soil Air Water, 43(4): 551-560. districts of Punjab, India. Journal of Earth Science and Climatic Change, 06(04): 1000274.https://doi.org/10.4172/2157-7617.1000274. Ravikumar P, Somashekar RK, Angami M. 2011. Hydrochemistry and evaluation of groundwater suitability for irrigation and Lin T, Horne BG, Tiiio P, et al. 1996. Learning long-term dependencies in NARX recurrent neural Networks. IEEE Transactions on Neural Networks, 7(6):1329-1338. Sahoo S, Jha MK. 2013. Groundwater-level prediction using multiple linear regression and artificial neural network techniques: A comparative assessment. Hydrogeology Journal, 21(8): 1865-1887. Guzman SM, Paz JO, Tagert MLM. 2017b. The use of NARX neural networks to forecast daily groundwater levels. Water Resources Management, 31(5): 1591-1603. Coulibaly P, Anctil F, Aravena R, et al. 2001. Artificial neural network modeling of water table depth fluctuations. Water Resources Research, 37(4): 885-896. https://doi.org/10.1029/2000WR900368. Kisi O. 2007. Streamflow forecasting using different artificial neural network algorithms.Journal of Hydrologic Engineering, 12(5): drinking purposes in the Markandeya River basin, Belgaum District, Karnataka State, India. Environmental Monitoring and Guzman SM, Paz JO, Tagert MLM, et al. 2019. Evaluation of seasonally classified inputs for the prediction of daily groundwater levels: NARX networks vs support vector machines. Environmental Modeling and Assessment, 24(2): 223-234. https://doi.org/10.1007/s10666-018-9639-x. Resources Research, 41(12): W12409. https://doi.org/10.1029/2005WR004152. Lehmann EL, Casella G. 1998. Theory of point estimation (2nd ed). New York: Springer. Ahmadian M, Chavoshian M. 2012. Spatial variability zonation of groundwater-table by use geo-statistical methods in central region Morris BL, Lawrence ARL, Chilton PJC, et al.2003. Groundwater and its susceptibility to degradation: A global assessment of the Daliakopoulos IN, Coulibaly P, Tsanis IK. 2005. Groundwater level forecasting using artificial neural networks. Journal of Hydrology,309(1-4): 229-240. https://doi.org/10.1016/j.jhydrol.2004.12.001. Izady A, Davary K, Alizadeh A, et al. 2013. Application of NN-ARX model to predict groundwater levels in the Neishaboor Plain, Iran. Water Resources Management, 27(14):4773-4794. https://doi.org/10.1007/s11269-013-0432-y. Piotrowski AP, Napiorkowski JJ. 2013. A comparison of methods to avoid overfitting in neural networks training in the case of catchment runoff modelling. Journal of Hydrology, Nash JE, Sutcliffe JV. 1970. River flow forecasting through conceptual models part I: A discussion of principles. Journal of Hydrology,10(3): 282-290. https://doi.org/10.1016/0022-1694(70)90255-6. Chen S, Billings SA, Grant PM. 1990. Non-linear system identification using neural networks. International Journal of Control, 51(6): 1191-1214. Khaki M, Yusoff I, Islami N. 2015. Application of the artificial neural network and neurofuzzy system for assessment of groundwater Mackay JD, Jackson CR, Brookshaw A, et al. 2015. Seasonal forecasting of groundwater levels in principal aquifers of the United Kingdom. Journal of Hydrology, 530:815-828. https://doi.org/10.1016/j.jhydrol. 2015.10.018. 6(1): 97-111. https://doi.org/10.1016/j.jhydrol.2012.10.019. Hagan MT, Menhaj MB. 1994. Training feedforward networks with the Marquardt algorithm.IEEE Transactions on Neural Networks, 5(6):989-993. Guzman SM, Paz JO, Tagert MLM. 2017a. The use of NARX neural networks to forecast daily groundwater levels. Water Resources Management, 31(5): 1591-1603. https://doi.org/10.1007/s11269-017-1598-5. Zahid A, Ahmed SRU. 2006. Groundwater resources development in Bangladesh: Contribution to irrigation for food security and constraints to sustainability. Groundwater Governance in Asia, S1: 25-46. Siegelmann HT, Horne BG, Giles CL. 1998. Computational capabilities of recurrent NARX neural networks. IEEE Transactions on Systems, Man and Cybernetics, Part B(Cybernetics), 27(2): 208-215. https://doi.org/10.1109/3477.558801. Leontaritis IJ, Billings SA. 1985. Input-output parametric models for non-linear systems part I: Deterministic non-linear systems.International Journal of Control, 41(2): 303-328. 2-539. Cadenas E, Rivera W, Campos-Amezcua R, et al. 2016. Wind speed prediction using a univariate ARIMA model and a multivariate NARX model. Energies, 9(2): 109. of Hamadan province. Annals of Biological Research, 3(11): 5304-5312. (10): 1989-2006. https://doi.org/10.1007/s11269-009-9534-y. Assessment, 173(1-4): 459-487. https://doi.org/10.1007/s10661-010-1399-2. Kingston GB, Lambert MF, Maier HR. 2005.Bayesian training of artificial neural networks used for water resources modeling. Water Shahid S, Hazarika MK. 2010. Groundwater drought in the northwestern districts of Bangladesh. Water Resources Management, Adeloye AJ, De Munari A. 2006. Artificial neural network based generalized storage-yieldreliability models using the Levenberg-Marquardt algorithm. Journal of Hydrology,326(1-4): 215-230. Barzegar R, Fijani E, Asghari M, et al. 2017.Forecasting of groundwater level fluctuations using ensemble hybrid multi-wavelet neural network-based models. Science of the Total Environment, 599-600(1): 20-31. https://doi.org/10.1016/j.scitotenv.2017.04.189. problem and options for management. Lohani AK, Krishan G. 2015. Application of artificial neural network for groundwater level simulation in Amritsar and Gurdaspur