تعیین ترکیب بهینه متغیرهای ورودی با استفاده از آزمون گاما برای مدل‌سازی پتاسیم قابل جذب در سیستم عصبی-فازی (مطالعه موردی: منطقه میانکنگی؛ زابل)

نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانشجوی کارشناسی ارشد، گروه علوم مهندسی خاک، دانشکده آب و خاک، دانشگاه زابل، زابل، ایران

2 گروه علوم مهندسی خاک، دانشکده آب و خاک، دانشگاه زابل، زابل، ایران

چکیده

یکی از مراحل مهم و پیچیده برای مدل­سازی غیرخطی، پیش پردازش داده­های ورودی به منظور انتخاب ترکیبی مناسب از آن­ها در مدل می­باشد. در این مطالعه آزمون گاما برای انتخاب ترکیب بهینه متغیرهای ورودی در مدل­سازی پتاسیم قابل جذب استفاده شد. برای تعیین بهینه تعداد داده­های مورد نیاز برای مدل­سازی از آزمون M استفاده شد. به منظور مدل­سازی تعداد هشت متغیر ورودی استفاده گردید. مدل­سازی پتاسیم قابل جذب با استفاده از تعداد نقاط بهینه، متغیرهای منتخب با خوشه­بندی کاهشی در سیستم عصبی فازی انجام شد. نتایج نشان داد که شش متغیر شامل (درصد رس، سیلت، ماده آلی، هدایت الکتریکی، رطوبت اشباع و pH) ترکیب بهینه متغیرها در مدل­سازی پتاسیم قابل جذب در منطقه میانکنگی می­باشند. همچنین با استفاده از خروجی آزمون M تعداد 112 داده (60 درصد داده­ها) برای بخش آموزش مدل­سازی مناسب تشخیص داده شد. نتایج حاکی از این واقعیت است که روش M در قسمت آموزش از دقت و سرعت مناسبی نسبت به روش آزمون و خطا در یافتن تعداد مناسب داده­های ورودی، برخوردار می­باشد. نتایج حاصل از مدل­سازی نیز بیانگر آن بود که روش عصبی فازی توانایی و عملکرد بالایی در برآورد مقدار پتاسیم قابل جذب در خاک­های منطقه میانکنگی را داشته است (R2=0.90 و RMSE=4.27). همچنین، در این تحقیق، در راستای مدل­سازی و پیش­بینی پتاسیم قابل جذب، درصد کربن آلی مهمترین ورودی شناخته شد.

کلیدواژه‌ها


عنوان مقاله [English]

Determining Optimal Combination of Input Variables Using Gamma Test for Absorbable Potassium Modeling in the Fuzzy-Neural System (Case Study: Mian-Kangi Region Zabol)

نویسندگان [English]

  • Amin Delarami 1
  • Ahmad Gholamalizadeh 2
  • Asma shabani 2
1 MSc Student, Department of soil sciences, Faculty of soil and water, University of Zabol, Zabol, Iran
2 Department of soil sciences, Faculty of soil and water, University of Zabol, Zabol, Iran
چکیده [English]

One of the important and complex steps for nonlinear modeling is pre-processing of input data in order to select the appropriate combination of them in the model. The gamma test was used to select the optimal combination of input variables for available potassium modeling in this study. The M test was used for determining the optimal number of data needed for modeling. Eight input variables were used for modeling. Modeling the available potassium was done by the number of optimum points and selected variables with subtractive clustering in the fuzzy neural system. The results showed that six variables (clay percentage, silt, organic matter, electrical conductivity, saturation moisture and pH) are the optimal combination of variables in modeling the available potassium in Mian-Kangi region. Also, 112 of measured data (60%) were considered as suitable data for the modeling training section using the M test results. The results indicated that the M method has better accuracy and speed than the trial and error method for finding the appropriate number of input data in training section. The results of modeling also indicated that the fuzzy neural method has high capability and performance in estimating the amount of available potassium in the soil of Mian-Kangi region (R2 = 0.90 and RMSE = 4.27). Also, organic carbon percentage was the most important input for modeling and predicting the amount of available potassium.

کلیدواژه‌ها [English]

  • M test
  • Gamma test
  • Available potassium
  • Fuzzy neural
  • Fast measured properties
Ayoubi, Sh., Mohammad Zamani, S. and Khormali, F. 2007. Prediction total N by organic matter content using some geostatistic approaches in part of farm land of Sorkhankalateh, Golestan Province. Journal of Agricultural Science and Natural Resources, 14(4): 215-225. (In Persian)
Ayoubi, S., Mehnatkesh, A., Jalalian, A., Sahrawat, K.L. and Gheysari, M. 2014. Relationships between grain protein, Zn, Cu, Fe and Mn contents in wheat and soil and topographic attributes. Archives of Agronomy and Soil Science, 60(5): 625-638.
Bohra, J.S. and Doerffling, K. 1993. Potassium nutrition of rice (Oryza Sativa L.)Varieties under NaCl salinity. Plant and Soil, 152: 299-303.
Bouyoucos, G.J. 1962. Hydrometer method improved for making particle size analyses of soils. Agronomy Journal, 54(5): 464-465.
Corcoran, J., Wilson, I. and Ware, J. 2003. Predicting the geo-temporal variations of crime and disorder. International Journal of Forecasting, 19: 623-634.
Chen, S.M. and Chung, N.Y. 2006. Forecasting enrollments using high-order fuzzy time series and genetic algorithms. International Journal of Intelligent Systems, 21: 485-501.
Chung, C.H., Chiang, Y.M. and Chang, F.J. 2012. A spatial neural fuzzy network for estimating pan evaporation at ungauged sites. Hydrology and Earth Systems Sciences, 16: 255-266.
Dinpashoh, Y., Fakheri-Fard, A., Moghaddam, M., Jahanbakhsh, S. and Mirnia, M. 2004. Selection of variables for the purpose of regionalization of Iran’s precipitation climate using multivariate methods. Journal of Hydrology, 297:109-123.
Evans, D. 2001. Data derived estimations of noise using near neighbor distance distributions. Ph.D. Thesis, Cardiff University, Wales, U.K.
Evans, D. and Jones, A.J. 2002. A proof of the gamma test. Proceedings of Royal Society, Series A, 458(20-27): 2759-2799.
Gholamalizadeh Ahangar, A., Sarani, F., Hashemi, M. and Shabani, A. 2015. Comparison of linear regression methods, geostatistical and artificial neural network modeling of organic carbon in dry land of Sistan plain. Journal of Water and Soil, 28(6):1250-1260. (In Persian)
Hashemi, M., Gholamalizadeh Ahangar, A. and Shabani, A. 2016. Evaluating pedotransfer functions for estimating ESP in the soils of Sistan plain. Journal of Agricultural Engineering, 38(2): 77-93. (In Persian)
Jafari Haghighi, M. 2003. Methods of Soil Analysis. First Edition. Publication of nedaye zoha. 129 p. (In Persian)
Jang, J.S.R. 1993. ANFIS Adaptive-Network-Based Fuzzy inference system. IEEE Transactions on Systems Man and Cybernetics, 23: 665-658.
Jones, A.J. 2004. New tools in non-linear modeling and prediction. Computational Management Science, 1: 109-149.
Kim, M. and Gilley, J.E. 2008. Artificial neural network estimation of soil erosion and nutrient concentrations in runoff from land application areas. Computers and Electronics in Agriculture, 64(2): 268-275.
Koncar, N. 1997. Optimization methodologies for direct inverse neuro control. Ph.D. Thesis, Department of Computing, Imperial College of Science, Technology and Medicine, University of London, London.
Kumar, M., Raghuwanshi, N.S., Singh, R., Wallender, W.W. and Pruitt, W.O. 2002. Estimating evapotranspiration using artificial neural network. Journal of Irrigation and Drainage Engineering-ASCE, 128: 224-233.
Landeras, G., Ortiz-Barredo, A. and López, J.J. 2009. Forecasting weekly evapotranspiration with ARIMA and artificial neural network models. Journal of Irrigation and Drainage Engineering, 135(3): 323-334.
Merdun, H., Çınar, Ö., Meral, R. and Apan, M. 2006. Comparison of artificial neural network and regression pedotransfer functions for prediction of soil water retention and saturated hydraulic conductivity. Soil and Tillage Research, 90(1): 108-116.
Mir, H., Gholamalizadeh Ahangar, A. and Shabani, A. 2016. Determination of the most important soil parameters affecting the availability of phosphorus in Sistan plain, using connection weight method in neural networks. Journal of Water and Soil, 29(6):1674-1687. (In Persian)
Moghaddamnia, A., Ghafari Gousheh, M., Piri, J. and Han, D. 2008. Evaporation estimation using support vector machines technique. World Academy of Science, Engineering and Technology, 43: 14-22.
Moghaddamnia, A., Remesan, R., Hassanpour Kashani, M., Mohammadi, M., Han, D. and Piri, J. 2009. Comparison of LLR, MLP, Elman, NNARX and ANFIS Models- with a case study in solar radiation estimation. Journal of Atmosphere and Solar-Terrestrial Physics, 71: 975-982.
Mukerji, A., Chatterjee, C. and Raghuwanshi, N.S. 2009. Flood forecasting using ANN, neuro-fuzzy, and neuro-GA models. Journal of Hydrologic Engineering, 14(6): 647-652.
Nelson, R.E. 1982. Carbonate and gypsum. In: Page, A. L. (eds). Methods of Soil Analysis-Part II. Soil Science Society of America and American Society of Agronomy, Madison, Wisconsin, USA. PP: 181-197.
Noori, R., Karbassi, A. and Sabahi, M.S. 2009. Evaluation of PCA and gamma test techniques on ANN operation for weekly solid waste prediction. Journal of Environmental Management, 91: 767-771.
Page, A.L. 1982. Methods of Soil Analysis- Part 2: Chemical and Microbiological Properties. Soil Science Society of America and American Society of Agronomy, Madison, Wisconsin, USA. 1572 p.
Piri, J., Amin, S., Moghaddamnia, A., Keshavarz, A., Han, D. and Remesan, R. 2009. Daily pan evaporation modeling in a hot and dry climate. Journal of Hydrologic Engineering, 14(8): 803-811.
Piri, H. and Ansari, H. 2013. Study of drought in Sistan Plain and its impact on Hamoun international. Journal of Wetland Ecobiology- Islamic Azad University, Ahvaz Branch, 5(1): 63-74. (In Persian)
Remesan, R., Shamim, M.A., Han, D. and Mathew, J. 2009. Runoff prediction using an integrated hybrid modeling scheme. Journal of Hydrology, 372: 48-60.
Rezaee Pazhand, H. 2001. Application of Probability and Statistics in Water Resources.1st Edition. Sokhan Gostar, Mashhad. 468 p. (in Persian)
Rhoades, J.D. and Oster, J.D. 1986. Solute Content. Methods of Soil Analysis-Part 1. Physical and Mineralogical Methods. PP: 985-1006.
Sharifi, AR., Dinpashoh, Y., Fakheri-Fard, A. and Moghaddamnia, AR. 2013. Optimum combination of variables for runoff simulation in Amameh watershed using Gamma test. Journal of Soil and Water, 23(4):59-72. (In Persian)
Shu, C. and Ouarda, T.B.M.J. 2008. Regional flood frequency analysis at ungauged sites using the adaptive neuro-fuzzy inference system. Journal of Hydrology, 349: 31-43
Stefansson, A., Koncar, N. and Jones, A.J. 1997. A note on the gamma test. Neural Computing and Applications, 5(3): 131-133.
Zhang, Y.X. 2007. Artificial neural networks based principal component analysis input selection for clinical pattern recognition analysis. Talanta, 73: 68-75.
Zhang, Y.X., Li, H., Hou, A. and Haval, J. 2006. Artificial neural networks based on principal component analysis input selection for quantification in overlapped capillary electrophoresis peaks. Chemo Metrics and Intelligent Laboratory Systems, 82: 165-175.