Input Parameters Preprocessing in Artificial Neural Networks and Adaptive Neuro- Fuzzy Inference System Using Stepwise Regression and Gamma Test Techniques for Estimation of Daily Evaporation

Document Type : Original Article

Authors

1 Ph. D. Student of Irrigation and Drainage of Shahrekord University

2 Assistant Professor of Water Engineering Department of Shahrekord University

Abstract

Being a function of different meteorological parameters and their interactions, evaporation is a complex, nonlinear phenomenon. Preprocessing of input parameters to select appropriate combinations is complex when modeling nonlinear systems. Data preprocessing reduces trial and error steps and recognizes most important parameters on noted phenomenon for modeling using intelligent methods. In this study, two methods of stepwise regression (FS) and gamma test (GT) were used for preprocessing input parameters in multi-layer perceptron neural network and adaptive neuro- fuzzy inference system to estimate daily evaporation (Ep) at Shahrekord meteorological station. To evaluate the effect of input parameters preprocessing in intelligent models using different statistical error criteria, ANN-FS, ANN-GT, ANFIS-FS and ANFIS-GT with preprocessed parameters were compared against each other and also with ANN and ANFIS models without preprocessed parameters. The results showed that all six models have a high degree of precision to estimate daily Ep. ANFIS-FS model represented a determination coefficient (R2) of0.91 and root mean square error (RMSE) of 0.11 both of training and test steps. Although the accuracy of models was slightly each other, but the ability of determination of important of input parameters, education and recognition of the best combination of input parameters with 3720 data in this study by gamma test, makes this model a useful tool for fast preprocessing input parameters to model evaporation

Keywords

References

[1]   بازرگان لاری، ع. 1384. رگرسیون خطی کاربردی. چاپ اول، انتشارات مرکز نشر دانشگاه شیراز.
[2]   دزفولی، ک. ا. 1384. اصول تئوری فازی و کاربردهای آن در مدل­سازی مسایل مهندسی آب. انتشارات جهاد دانشگاهی، واحد امیرکبیر، چاپ اول.
[3]   رضایی، ع. و ا. سلطانی. 1382. مقدمه­ای بر تحلیل رگرسیون کاربردی. دانشگاه صنعتی اصفهان، مرکز نشر.
[4]   سبزی­پرور، ع. ا.، ح. زارع ­ابیانه و م. بیات ­ورکشی. 1389. مقایسه­ی یافته­های مدل شبکه‎ی استنتاج تطبیقی عصبی- فازی با مدل­های رگرسیونی به­منظور برآورد دمای خاک در سه اقلیم متفاوت. نشریه آب و خاک (علوم و صنایع کشاورزی)، جلد 24، شماره 2، صفحه 285-274.
[5]   شایان­نژاد، م.، ج. ساداتی­نژاد و ه. فهمی. 1386. تعیین تبخیر و تعرق بالقوه با استفاده از رگرسیون فازی. مجله تحقیقات منابع آب ایران، شماره 3، صفحه 19-9.
[6]      Abudu, S., C. Cui, P. King, J. Moreno and S. Bawazir. 2011. Modeling of daily pan evaporation using partial least squares regression. Technological Sci. 54 (1): 163-174.
[7]      Ahmadi, A., D. Han, M. Karamouz and R. Remesan. 2009. Input data selection for solar radiation estimation. Hydrol. Processes 23: 2754–2764.
[8]      Deswal, S. and M. Pal. 2008. Artificial neural network based modeling of evaporation losses in reservoirs. Proc. World Acad. Sci. Eng. Technol. 29: 279–283.
[9]      Doorenbos, J. and W. O. Pruitt. 1977. Guidelines for prediction of crop water requirements. FAO Irrig. and Drain. Paper no. 24, Rome.
[10]  Eslamian, S. S., S. A. Gohari, M. Biabanaki and R. Malekian. 2008. Estimation of monthly pan evaporation using artificial neural networks and support vector machines. J. Appl. Sci. 8(19): 3497–3502.
[11]  French, M. N., W. F. Krayewski and R. R. Cuykendall. 1992. Rainfall forecasting in space and time using a neural networks. J. Hydrol. 137: 1-37.
[12]  Jain, S. K., A. Das and D. K. Srivastava. 1999. Application of ANN for reservoir inflow prediction and operation. J. Water Res. Plan. Manage. 125 (5): 263-271.
[13]  Jensen, M. E., R. D. Burman and R. G. Allen. 1990. Evapotranspiration and irrigation water requirements. ASCE Manual and Report on Engineering Practice No.70. New York.
[14]  Jones, A., D. Evans, S. Margetts and P. Durrant. 2002. The Gamma Test. Chapter IX in Heuristic and Optimization for Knowledge Discovery. Edited by Ruhul Sarker, Hussein Abbass and Charles Newton. Idea Group Publishing, Hershey, PA. 27 pp.
[15]  Keskin, M. E. and O. Terzi. 2006. Artificial neural network models of daily pan evaporation. J. Hydrol. Eng. 11(1): 65–70.
[16]  Kisi, O. 2006. Daily pan evaporation modeling using a neuro-fuzzy computing technique. J. Hydrol. 329: 636–646.
[17]  Kisi, O. and O. Ozturk. 2007. Adaptive Neuro fuzzy Computing Technique for Evapotranspiration Estimation. ASCE 133: 4-368.
[18]  Kumar, M., N. S. Raghuwanshi, R. Singh, W. W. Wallender and W. O. Pruitt. 2002. Estimating evapotranspiration using artificial neural networks. J. Irrig. and Drain. ASCE. 128 (4): 224-233.
[19]  Mcculloch, W. and W. Pitts. 1943. Logical calculus of the ideas immanent in nervous activity. Bull. Math Biophys. 5: 33-115.
[20]  Moghaddamnia, A., M. Ghafari-Gousheh, J. Piri, S. Amin and H. Han. 2009. Evaporation estimation using artificial neural networks and adaptive neuro-fuzzy inference system techniques. J. Advance Water Res. 32: 88-97.
[21]  Noori, R., A. Karbassi and M. S. Sabahi. 2009. Evaluation of PCA and gamma test techniques on AAN opration for weekly solid waste prediction, J. Environmental Manage.91: 767-771.
[22]  Noori, R., G. Hoshyaripour, K. H. Ashrafi and B. Nadjar-Araabi. 2010. Uncertainty analysis of developed ANN and ANFIS models in prediction of carbon monoxide daily concentration. J. Atmospheric Environment 44: 476-482.
[23]  Rahimi-Khoob, A. 2009. Estimating daily pan evaporation using artificial neural network in a semi-arid environment. Theor. Appl. Climatol. 98: 101–105.
[24]  Rogers, L. L. and F. U. Dowla. 1994. Optimization of groundwater remediation using artificial neural networks with parallel solute transport modeling. Water Resour. Res. 30 (2): 457-481.
[25]  Remesan, R., M. Shamim and D. Han. 2008. Model data selection using gamma test for daily solar radiation estimation. J. Hydrol. Processes 22: 4301–4309.
[26]  Shukla, M. B., R. Kok, S. O. Prasher, G. Clark and R. Lacroix. 1996. Use of artificial neural network in transient drainage design. Trans. ASAE. 39 (1): 119-124.
[27]  Sudheer, K. P., A. K. Gosain, D. Rangan and S. M. Saheb. 2002. Modeling evaporation using an artificial neural network algorithm. Hydrol. Process. 16: 3189–3202.
[28]  Sudheer, K. P., A. K. Gosain and K. S. Ramasastri. 2003. Estimating actual evapotranspiration from limited climate data using neural computing technique. J. Irrg. Drain. Eng. 129(3): 214–218.
[29]  Tabari, H., S. Marofi and A. Sabziparvar. 2010. Estimation of daily pan evaporation using artificial neural network and multivariate non-linear regression. J. Irri. Sci. 28: 399-406.
[30]  Terzi, O. and M. E. Keskin. 2005. Modelling of daily pan evaporation. J. Appl. Sci. 5(2): 368–372.
[31]  Thirumalaian, K. and M. C. Deo. 1998.River stage forecasting using artificial neural network. J. Hydrol. Eng. 3 (1): 26-32.
[32]  Trajkovic, S., B. Todorovic and M. Stankovic. 2003. Forecasting of reference evapotranspiration by Artificial Neural Network. J. Irrg. Drain. Eng. 129 (6): 454–457.
[33]  Traore, S., Y. M. Wang and T. Kerh. 2010. Artificial neural network for modeling reference evapotranspiration complex process in Sudano-Sahelian zone. Agri. Water Manage. 97: 707-714.
[34]  Yang, C. C.,S. O. Prasher and R. Lacroix.1996. Application of artificial neural network to land drainage engineering. Trans. ASAE. 39 (2): 525-533.6
Irrigation and Water Engineering
Volume 3, Issue 1 - Serial Number 9
December 2012
Pages 63-76

Files

Share

How to cite

Statistics