Volume 8, Issue 15 (9-2017)                   jwmr 2017, 8(15): 1-12 | Back to browse issues page


XML Persian Abstract Print


Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:

(2017). Evaluation of the Efficiency of Support Vector Regression, Multi-Layer Perceptron Neural Network and Multivariate Linear Regression on Groundwater Level Prediction (Case Study: Shahrekord Plain). jwmr. 8(15), 1-12. doi:10.29252/jwmr.8.15.1
URL: http://jwmr.sanru.ac.ir/article-1-837-en.html
Abstract:   (5154 Views)
Accurate and reliable simulation and prediction of the groundwater level variation is significant and essential in water resources management of a basin. Models such as ANNs and Support Vector Regression (SVR) have proved to be effective in modeling nonlinear function with a greater degree of accuracy. In this respect, an attempt is made to predict monthly groundwater level fluctuations using Multivariate Linear Regression, Multi-Layer Perceptron neural network models and two SVRs with RBF and linear function. In the present study, monthly data (from 2000 to 2010) of 18 observational wells in Shahrekord Plain were used for simulating and predicting the groundwater level. Regarding to NS efficiency and RMSE criteria, MLP model in 56% and SVR in 44%, have the best performance in comparison with other models. For an instance, in well No. 1, SVR-RBF using input parameters of groundwater level, temperature, evaporation and precipitation is superior to other models. General efficiency of MLP, SVR-RBF, and SVR-Linear for NS criteria is 0.703, 0.656 and 0.655, respectively; and for RMSE criteria is 0.857, 0.905 and 0.914 meter, respectively. Results indicate that MLP and SVR models give better accuracy in predicting groundwater levels in the study area when compared to the linear model.
Full-Text [PDF 1875 kb]   (5377 Downloads)    
Type of Study: Research | Subject: Special
Received: 2017/09/18 | Accepted: 2017/09/18 | Published: 2017/09/18

References
1. Abraham, A. 2005. Artificial neural networks. In: Sydenham, P.H. and R. Thorn (eds.) Handbook of measuring system design, 901-908 pp., John Wiley & Sons, Stillwater, OK, USA. [DOI:10.1002/0471497398.mm421]
2. Akbarzadeh, F., H. Hasanpour and S. Emamgholizadeh. 2016. Groundwater level prediction of Shahrood Plain using RBF neural networks. Journal of Watershed Management Research, 7: 104-118 (In Persian). [DOI:10.18869/acadpub.jwmr.7.13.118]
3. Ardiclioglu, M., O. Kisi and T. Haktanir. 2007. Suspended sediment prediction using two different feed-forward backpropagation algorithms. Canadian Journal of Civil Engineering, 34: 120-125. [DOI:10.1139/l06-111]
4. Chen, S.T. and P.S. Yu. 2007. Pruning of support vector networks on flood forecasting. Journal of Hydrology, 347: 67-78. [DOI:10.1016/j.jhydrol.2007.08.029]
5. Dibike, Y.B., S. Velickov, D.P. Solomatine and M.B. Abbott. 2001. Model induction with support vector machines: introduction and applications. Journal of Computing in Civil Engineering, 15: 208-216. [DOI:10.1061/(ASCE)0887-3801(2001)15:3(208)]
6. Erasto, P. 2001. Support vector machines-backgrounds and practice. BSc Thesis, University of Helsinki, Faculty of Science, Rolf Nevanlinna Institute, Helsinki, Finland. 78 pp.
7. Govindaraju, R.S. 2000. Artificial neural networks in hydrology. I: preliminary concepts. Journal of Hydrologic Engineering, 5: 115-123. [DOI:10.1061/(ASCE)1084-0699(2000)5:2(115)]
8. Javadi, M.R., H. Tehranipour, Sh.A. Gholami and M.A. Fatahi Ardakani. 2012. Comparing methods of Mora and Varson and multivariate regression in zoning landslide hazard of Kan Watershed. Journal of Watershed Management Research, 3: 92-105 (In Persian).
9. Kiarash, S., A. Enderami, A. Malekian and M. Mahdavi. Investigation of the capability of artificial neural networks for estimating suspended sediment load (Case Study: Silakhor Watershed, Lorestan Province). 9th International River Engineering Conference, 8 pp., Ahwaz, Iran (In Persian).
10. Lalehzari, R. and S.H. Tabatabaei. 2010. Chemical characteristics of groundwater in Shahrekord Plain. Journal of Environmental Studies, 36: 55-62 (In Persian).
11. Lallahem, S., J. Mania, A. Hani and Y. Najjar. 2005. On the use of neural networks to evaluate groundwater levels in fractured media. Journal of Hydrology, 307: 92-111. [DOI:10.1016/j.jhydrol.2004.10.005]
12. Lijun, F. and L. Shuquan. 2007. Forecasting the runoff using least square support vector machine. Tianjin Teaching Committee, TJGL06-099: 884-889.
13. Mahdavi, R., J. Abedi Koupaei, M. Rezaei and M. Abdolhosseini. 2004. Identification of appropriate sites for artificial recharge of groundwater resources using RS and GIS. 2nd Students Conference on Soil and Water Resources, 11 pp., Shiraz, Iran (In Persian).
14. Moharampour, M., A. Mehrabi and M. Katouzi. 2010. Evaluation of support vector machine on daily flow prediction. 4th Iran Water Resources Management Conference, 11 pp., Tehran, Iran (In Persian).
15. Mukerji, A., C. Chatterjee and N.S. Raghuwanshi. 2009. Flood forecasting using ANN, neuro-fuzzy, and neuro-GA models. Journal of Hydrologic Engineering, 14: 647-652. [DOI:10.1061/(ASCE)HE.1943-5584.0000040]
16. Naserabadi, F., A. Esmali Ouri, H. Akbari and R. Rostamian. 2016. River flow simulation using SWAT model (Case study: Ghareh Su River in Ardabil Province-Iran). Journal of Watershed Management Research, 7: 50-59 (In Persian). [DOI:10.18869/acadpub.jwmr.7.13.59]
17. Pourkerman, M., A. Charkhabi, H. Mosadegh, H. Peyrowan and A. Talebi. 2011. Identification of effective chemical factors on soil resistivity using discriminant analysis stepwise method (case study: marls of Sorkheh Watershed). Iranian Journal of Watershed Management Science and Engineering, 5: 23-32(In Persian).
18. Ramirez, M.C.V., H.F. Campos Velho and N.J. Ferreira. 2005. Artificial neural network technique for rainfall forecasting applied to the Sao Paulo region. Journal of Hydrology, 301: 146-162. [DOI:10.1016/j.jhydrol.2004.06.028]
19. Razavi Ghahfarokhi, S.B., Sh. Karimi Googhari and M.B. Rahnama. 2013. Shahr-e-kord Plain groundwater level modeling using artificial neural networks and wavelet analysis. The 2nd International Conference on Plant, Water, Soil and Weather Modeling, 12 pp., Kerman, Iran (In Persian).
20. Sahrai, Sh. and M. Zaker Moshfegh. 2013. Using support vector machines for river flow prediction. 7th National Congress on Civil Engineering, 9 pp., Zahedan, Iran (In Persian).
21. Smola, A.J. and B. Scholkopf. 2004. A tutorial on support vector regression. Statistics and Computing, 14: 199-222. [DOI:10.1023/B:STCO.0000035301.49549.88]
22. Sreekanth, P.D., N. Geethanjali, P.D. Sreedevi, S. Ahmed, N. Ravi Kumar and P.D. Kamala Jayanthi. 2009. Forecasting groundwater level using artificial neural networks. Current Science, 96: 933- 939.
23. Vapnik, V. 1998. Statistical Learning Theory. John Wiley, New York, USA, 732 pp.
24. Yoon, H., S.C. Jun, Y. Hyun, G.O. Bae and K.K. Lee. 2011. A comparative study of artificial neural networks and support vector machines for predicting groundwater levels in a coastal aquifer. Journal of Hydrology, 396: 128-138. [DOI:10.1016/j.jhydrol.2010.11.002]
25. Yu, P.S., S.T. Chen and I.F. Chang. 2006. Support vector regression for real-time flood stage forecasting. Journal of Hydrology, 328: 704-716. [DOI:10.1016/j.jhydrol.2006.01.021]
26. Zounemat-Kermani, M. 2013. Hydrometeorological parameters in prediction of soil temperature by means of artificial neural network: case study in Wyoming. Journal of Hydrologic Engineering, 18: 707-718. [DOI:10.1061/(ASCE)HE.1943-5584.0000666]
27. Zounemat-Kermani, M. 2014. Principal component analysis (PCA) for estimating chlorophyll concentration using forward and generalized regression neural networks. Applied Artificial Intelligence, 28: 16-29. [DOI:10.1080/08839514.2014.862771]
28. Zounemat-Kermani, M., O. Kisi and T. Rajaee. 2013. Performance of radial basis and LM-feed forward artificial neural networks for predicting daily watershed runoff. Applied Soft Computing, 13: 4633-4644. [DOI:10.1016/j.asoc.2013.07.007]

Add your comments about this article : Your username or Email:
CAPTCHA

Rights and permissions
Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

© 2024 CC BY-NC 4.0 | Journal of Watershed Management Research

Designed & Developed by : Yektaweb