Prediction of irrigation water quality parameters by neural network technique in the Khed Taluka, India
- 1Deptt. of SWCE, CAET, DBSKKV, Dapoli, MS, India
- 2Deptt. of SWCE, CAET, MPKV, Rahuri, MS, India
- 3Deptt. of SWCE, CAET, DBSKKV, Dapoli, MS, India
- 4Deptt. of SWCE, CTAE, MPUAT, Udaipur, Rajasthan, India
Res. J. Recent Sci., Volume 8, Issue (2), Pages 12-16, April,2 (2019)
The ANN model was developed with MLFBP with sigmoid transferred function. While developing ANN model for different input parameters, three steps were followed as identification of model structures, evaluate the performance and adopting model for forecasting. The ANN models were developed for prediction KR, Percent Na, PI, RSC, SAR and SSP using Neurosolutions. In ANN modeling KR, Percent Na, PI, RSC, SAR and SSP, selection of model parameters are very important i.e. input, output and model structure. In the present study, ANN were used to derive and to develop models for prediction KR, Percent Na, PI, RSC, SAR and SSP as groundwater quality parameters of Khed taluka by using post season values of existing groundwater quality parameters as input variables i.e. Na, Mg, K, CaCO3, HCO3. The post season data of groundwater quality parameters for time period 1999-2014 were selected for analysis. Model performance was assessed by statistical method included r, RMSE, Index of Agreement and MBE. In Khed taluka, 3-2-1 was best for predicting KR values and 4-2-1 model was best suited for prediction of percent Na values. In Khed taluka Taluka, for post monsoon season 4-6-1 model was best suited to predict PI and 4-4-1 was best suited to predict RSC. 3-6-1 was best suited to predict RSC and SSP in Khed taluka for post monsoon season.
- Junsawang P., Asavanant J. and Lursinsap C. (2007)., Artificial Neural Network Model for Rainfall-Runoff Relationship., ASIMMOD, Chiang Mai, Thailand, 267-273.
- Swingler K. (1996)., Applying Neural Networks: A practical guide., Academic Press, London.
- Berry M.J.A. and Linoff G. (1997)., Data mining techniques., Wiley, New York.
- Najah A., El-Shafie A., Karim O.A. and El-Shafie A.H. (2013)., Application of artificial neural networks for water quality prediction., Neural Computing and Applications, 22, S187-S201.
- Zanetti S.S., Sousa E.F., Oliveira V.P.S., Almeida F.T. and Bernardo S. (2007)., Estimating evapotranspiration using artificial neural network and minimum climatological data., Journal of Irrigation and Drainage Engineering. ASCE., 133, 83-89.
- Rao V. and Rao H. (1995)., C++ Neural networks and fuzzy logic., Second Edition., BPB Publications, 171-206.
- Kumar M., Bandyopadhyay A., Rahguwanshi N.S. and Singh R. (2008)., Comparative study of conventional and artificial neural network based ETo estimation models., Irrigation Science, 26, 531-545.
- Jacovides C.P. and Kontoyiannis H. (1995)., Statistical procedures for the evaluation of evapotranspiration computing models., Agricultural Water Management, 27(3-4), 365-371.
- Vázquez R.F. (2003)., Effect of potential evapotranspiration estimates on effective parameters and performance of the MIKE SHE-code applied to a medium-size catchment., Journal of Hydrology, 270(3-4), 309-327.
- Willmott C.J. (1982)., Some comments on the evaluation of model performance., Bulletin of the American Meteorological Society, 63(11), 1309-1313.