نوع مقاله : مقاله پژوهشی

نویسندگان

1 گروه خاکشناسی، دانشکده کشاورزی، دانشگاه زنجان، ایران

2 عضو هیئت علمی دانشگاه زنجان

3 گروه مهندسی آب، دانشکده کشاورزی دانشگاه زنجان ایران

چکیده

ظرفیت تبادل کاتیونی خاک میزان بار مثبتی است که در واحد جرم خاک قابل تبادل است. مدل‌سازی و تخمین ظرفیت تبادل کاتیونی شاخصی مفید از حاصلخیزی خاک می‌باشد. ارزیابی و طراحی سناریو‌های مختلف مدیریتی احتیاج به داشتن اطلاعات دقیق بانک اطلاعات خاک دارد. بدین منظور برای برآورد ظرفیت تبادل ‌کاتیونی خاک، 32 نیمرخ در دشت تبریز حفر گردید و جهت انجام آزمایش­های فیزیکی و شیمیایی مانند توزیع اندازه ذرات، کربن آلی، pH و ظرفیت تبادل کاتیونی خاک، 131 نمونه خاک از عمق­های مختلف جمع­آوری گردید. سپس 7 مدل رگرسیونی که بر­اساس مطالعات پیشین انتخاب شده بودند برای منطقه مورد مطالعه کالیبره شده و مورد ارزیابی قرار گرفتند. همچنین بر اساس ضرایب موجود در مدل­های رگرسیونی، 7 معماری متفاوت شبکه‌های عصبی مصنوعی جهت پیش‌بینی ظرفیت تبادل کاتیونی خاک طراحی گردید و نتایج حاصل از شبکه‌های عصبی مصنوعی و مدل‌های رگرسیونی چند متغیره با استفاده از پارامترهای ضریب همبستگی (R2)، جذر میانگین مربعات خطا (RMSE) و شیب بهترین معادله خط برازش داده شده بین نقاط پیش‌بینی و اندازه‌گیری شده (a) مورد ارزیابی قرار گرفت. نتایج نشان داد که معماری طراحی شده با شبکه عصبی مصنوعی با ضریب تبیین 86/0، RMSE  برابر با 14/2 و شیب خط برابر با 87/0دارای کارایی بالاتری بود که احتمالاً  به دلیل وجود روابط غیر خطی میان ویژگی های زودیافت خاک (متغیرهای مستقل) و ظرفیت تبادل کاتیونی (متغیر وابسته) بود.

کلیدواژه‌ها

عنوان مقاله [English]

Comparision of artificial neural network and regressionpedotransfer functions for istimation of soil cation exchange capacity in northwest of Iran

نویسندگان [English]

  • Ali Barikloo 1
  • jafar nikbakht 3

1 departement of soil science, faculty of ariculture, university of Zanjan, Iran

3 Department of water engineering , faculty of agriculture, university of zanjan, iran

چکیده [English]

 
Soil cation exchange capacity (CEC) is defined as the amount of positive charge that can be exchanged per mass of soil. Modeling and estimating of CEC is a useful index of soil fertility. Assessing and designing various management scenarios requires having accurate information regarding the soil data bank. In order to estimate the soil CEC, 32 profiles were dug in Tabriz plain, and 131 different samples were collected from different depths and physiochemical experiments such as particle size distribution, organic carbon, pH and CEC of soil samples were performed. Then using seven regression models that were selected based on previous studies, were calibrated and evaluated for the study area. Also seven different architectures of artificial neural networks were designed to predict the CEC of soil and the results of artificial neural networks and multivariate regression models were evaluated using correlation coefficient (R2), root mean square error (RMSE). Results revealed that artificial neural network with R2 = 0.86 and RMSE= 2.14 is better than regression based functions due to the existence of nonlinear relations between the easily available soil properties (independent variables) and the CEC (dependent variable).

کلیدواژه‌ها [English]

  • artificial neural network
  • cation exchange capacity
  • dasht-e- Tabriz
  • regressionpedotransfer functions
References
Amini M., Abbaspour K.C., Khademi H., Fathianpour N., Afyuni M., and Schulin R. 2005. Neural network models to predict cation exchange capacity in arid regions of Iran. European Journal of Soil Science, 56(4): 551-559.
Bayat H., Jorreh M., Safari-senjani A.A., and Davatgar N. 2013. Development of pedotransfer function for investigation the relationship between cation exchange capacity and weighted average diameter of aggregates. Soil Management Journal, 2(3): 39-47 (In Persian).
Bell M. A., and Van keulen H. 1995. Soil pedotransfer functions for four Mexican soils. Soil Science Society of America Journal, 59(2):865–871.
Breeuwsma A., Wösten J. H. M., Vleeshouwer J. J., Van Slobbe A. M., and Bouma J. 1986. Derivation of land qualities to assess environmental problems from soil surveys. Soil Science Society of America Journal, 50(1): 186-190.
Carpena O., lax a., and vahtras k. 1972. Determination of exchangeable cations in calcareous soils. Soil Science, 113(3): 194-199.
Daliakopoulos I. N., Coulibaly P., and Tsanis I. K. 2005. Groundwater level forecasting using artificial neural networks. Journal of Hydrology, 309(1): 229-240.
DuBose P., and Klimasauskas C. 1989. Introduction to Neural Networks with Examples and Applications. NeuralWare Inc., Pittsburgh, 317 p.
Fernando M. J., Burau R. G., and Arulanandan K. 1977. A new approach to determination of cation exchange capacity. Soil Science Society of America Journal, 41(4): 818-820.
Gee G. W., and Bauder J. W. 1986. Particle size analysis. p. 383-411. In: A. Klute (Ed), Methods of soil analysis. Part I. Physical and mineralogical methods, 2nd ed., Agronomy Monograph. No: 9. ASA and SSSA. Madison, WI.
Lippmann R. P. 1987. An Introduction to Computing with Neural Nets. ASSP Magazine, IEEE, 4(2): 4-22.
Manrique L. A., Jones C. A., and Dyke P. T. 1991. Predicting cation exchange capacity from soil physical and chemical properties. Soil Science Society of America Journal, 50:787-794.
McBratney A.B., Minasny B., Cattle S.R., and Vervoort R.W. 2002. From pedotransfer function to soil inference systems. Geoderma, 93:225-253.
McLean E.O. 1982. Soil pH and Lime requirement. Pp. 199-224. In: Page A.L., Miller R.H. and Keeney D.R. (Ed.), Methods of Soil Analysis. Part 2. Chemical and Micromorphological Properties. 2nd ed. Agron, Monogr. 9. ASA and SSSA, Madison, WI.
Meamarian-Fard M., and Beigi H. 2009. Comparison of multiple regression and artificial neural network pedotransfer functions for prediction of cation exchange capacity in soils of Chaharmahal-Bakhtiari. Journal of Soil and Water, 23: 90–99. (In Persian)
Minasny B., and McBratney A. 2002. The method for fitting neural network parametric pedotransfer functions. Soil Science Society of America Journal, 66(2): 352-361.
Mirkhani R., Shabanpour M., and Saadat S. 2005. Using particle-size distribution and organic cabon percentage to predict the cation exchange capacity of soils of Lorestan province. Journal of Soil and Water Science, 19(2): 235-242.
Mohajer R., Salehi M., and Beigi H. 2009. Prediction of cation exchange capacity using multiple regression and artificial neural network and effect of data partitioning on the accuary of models. Journal of Soil and Water, 49: 83–97. (In Persian)
Nelson R.E., and Sommers L. 1982. Total carbon, organic carbon and organic matter. Pp. 532-581. In: Page A.L., Miller R.H. and Keeney D.R. (Ed.), Methods of Soil Analysis. Part 2. Chemical and Microbiological Methodes. 2nd ed. Agron. Monogr. 9. ASA and SSSA, Madison, WI.
Nikbakht J., Zolfaghari M., and najib Mortez. 2017. Estimation of Groundwater Level of the Tasuj- East Azarbayejan Plain using artificial neural networks. Hydrogeology, 1(2): 99-115. (In Persian)
Pachepsky Y. A., Timlin D., and Varallyay G. 1996. Artificial neural networks to estimate soil water retention from easily measurable data. Soil Science Society of America Journal, 60(3): 727-733.
Sayegh A.H., Khan P., and Ryan, J. 1978. Factors affecting gypsum and cation exchange capacity determination in gypsiferous soils. Soil Science Journal, 125: 294-300.
Schaap M. G., and Leij F. J. 1998. Using neural networks to predict soil water retention and soil hydraulic conductivity. Soil and Tillage Research, 47(1): 37-42.
Taghizadeh-Mehrjardi R., Mahmoodi S., Heidari A., and Akbarzadeh A. 2009. Estimation of cation exchange capacity using multiple regression and artificial neural network techniques in Khezrabd region, Yazd. Journal of Agricultural Research, 1: 1–11. (In Persian)
Tamari S., Wösten J. H. M., and Ruiz-Suarez J. C. 1996. Testing an artificial neural network for predicting soil hydraulic conductivity. Soil Science Society of America Journal, 60(6): 1732-1741.
Yekom consulting engineers. 1993. Report of semi-detailed studies of Tabriz plain. Regional water company of East Azarbaijan. Tabriz, Iran (In Persian), 217p.
Zolfaghari A., Soltani M., Afshari T., and Sarmadian F. 2013. Comparison of Knearest neighbor and artificial neural network techniques in prediction of cation exchange capacity. Journal of Soil Management and Sustainable Production, 3: 77–94. (In Persian)