International Journal of Agricultural Engineering

Open Access Open Access  Restricted Access Subscription Access
Open Access Open Access Open Access  Restricted Access Restricted Access Subscription Access

Prediction of TDS in Groundwater by using BP-NM Modeling


Affiliations
1 Department of Agricultural and Food Engineering, Indian Institute of Technology, Kharagpur (W.B.), India
     

   Subscribe/Renew Journal


Total dissolved solids (TDS) comprise inorganic salts (principally calcium, magnesium, potassium, sodium, bicarbonates, chlorides, and sulfates) and some small amounts of organic matter that are dissolved in water. TDS in drinking-water originate from natural sources, sewage, urban run-off, industrial wastewater, and chemicals used in the water treatment process, and the nature of the piping or hardware used to convey the water. The present study deals with the prediction of TDS in Nadia district, West Bengal using back propagation neural network approach with gradient descent training method and the performance evaluation was done using RMSE, NSE, IOA, MAE and R2. It is found that the best result was obtained by M-6-10-1 (Input- Hidden-Output). The effectiveness of total hardness, chloride, potassium is also explained by the result of this study.

Keywords

Back Propagation Neural Network, TDS, Gradient Descent Method, Hidden Nodes, Correlation Matrix, MATLAB.
Subscription Login to verify subscription
User
Notifications
Font Size


  • Arai, M. (1993). Bounds on the number of hidden units in binary-valued three layered neuralnetworks. Neural Networks, 6 : 855-860.

  • Asghari, M. A., Nadiri, A. and Fijani, E. (2006). Ability to study different models of artificial neural networks to evaluate groundwater level in the hard formation. Tenth Conference of Geological Society, Teheran.

  • Banerjee, P., Singh, V. S., Chattopadhyay, K., Chandra, P. C., Bhoop, Singh (2011). Artificial Neural network model as a potential alternative for groundwater salinity forecasting. J. Hydrology, Elsevier, 398 (3-4): 212-220.

  • Haykin, S. (1994). Neural networks : A comprehensive foundation. Macmillan, New York, U.S.A.

  • Hecht-Nielsen, R. (1987). Kolmogorov’s mapping neural network existence theorem. IEEE first InternationalConference on Neural Networks, 3 : 11-13.

  • Khaki, M., Yousoff, I. and Islami, N. (2014). Application of neural network and neuro-fuzzy system for assessment of groundwater quality. CLEAN Soil Air Water, WileyOnline Library, 43 (4) : 551-560.

  • Kheradpisheha, I. Z., Talebib, A., Rafatia, L., Ghaneeiana, M.T. and Ehrampousha, M.H. (2015). Groundwater quality assessment using artificial neural network: A case study of Bahabadplain, Yazd, Iran Z., 20 (1): 65-71.

  • Kumar, V., Methew, N. S. and Swaminathan, G. (2010).Analysis of groundwater from potability from Tiruchirappalli city using back propagation ANN Model and GIS. J. Environ. Protec., I : 136-142.

  • Kuo, Y. M., Liu C. W. and Lin, K. H. (2004). Evaluation of the ability of anartificial neural network model to access the variation of groundwater quality in an area of blackfoot disease in Taiwan.Water Res. Elsevier., 38 (1): 148-158.

  • Lek, S., Delacoste, M., Baran, P., Dimopoulos, I., Lauga, J. and Aulagnier, S. (1996). Application of neural networks to modeling non-linear relationships in ecology. Ecological Modeling, 90 : 39-52.

  • Mehrdadi, N., Hasanlou, H., Jafarzadeh, M.T., Hasanlou, H. and Abodolabadi, H. (2012). Simulation of low TDS and biological units of Fajr industrial wastewater treatment plant usingartificial neural network and principal component analysis hybrid method. J. Waterresource &Protection, 4: 370-376.

  • Nash, J. E. and Sutcliffe, J.V. (1970). River flow through conceptual models part I – Adiscussion principles. Index of Agreement. J. Hydrology, Elsevier, 10 (3): 282-290.

  • Rajasekaran, S. and Pai, G. A. V. (2004). Neural networks, fuzzy logic and geneticalgorithms- Synthesis and applications, 3rd Ed. Prentice-Hall of India Private Limited.

  • Salmani, M. H. and Jajaei, E. S. (2016). Forecasting models for flow and total dissolved solids in Karoun river-Iran. J. Hydrology, Elsevier, 535: 148-159.

  • Whittemore, D. O., McGergor, K. M. and Marotz, G. A. (1989). Effects of variations in recharge on groundwater quality. J. Hydrology, Elsevier, 106(1-2): 131-145.

  • Willmott C. J. (1981). On the validation of models. Physical Geography, Taylor &Francis Online, 2 : 184-194.

  • Yesilnacar, M. I., Sahinkaya, E., Naz, M. and Ozkaya, B. (2008). Neural network prediction of nitrate in groundwater of Harran Plain, Turkey. Environmental Geology, 56(1): 19-25.

  • Zare, A.H., Bayat, V. M. and Daneshkare, A. P. (2011). Forecasting nitrate concentration in groundwater using artificial neural network and linear regression models. International Agro physics, 25 (2) : 187 – 192.


Abstract Views: 282

PDF Views: 0




  • Prediction of TDS in Groundwater by using BP-NM Modeling

Abstract Views: 282  |  PDF Views: 0

Authors

Debaditya Gupta
Department of Agricultural and Food Engineering, Indian Institute of Technology, Kharagpur (W.B.), India
Alivia Chowdhury
Department of Agricultural and Food Engineering, Indian Institute of Technology, Kharagpur (W.B.), India

Abstract


Total dissolved solids (TDS) comprise inorganic salts (principally calcium, magnesium, potassium, sodium, bicarbonates, chlorides, and sulfates) and some small amounts of organic matter that are dissolved in water. TDS in drinking-water originate from natural sources, sewage, urban run-off, industrial wastewater, and chemicals used in the water treatment process, and the nature of the piping or hardware used to convey the water. The present study deals with the prediction of TDS in Nadia district, West Bengal using back propagation neural network approach with gradient descent training method and the performance evaluation was done using RMSE, NSE, IOA, MAE and R2. It is found that the best result was obtained by M-6-10-1 (Input- Hidden-Output). The effectiveness of total hardness, chloride, potassium is also explained by the result of this study.

Keywords


Back Propagation Neural Network, TDS, Gradient Descent Method, Hidden Nodes, Correlation Matrix, MATLAB.

References