Study of Pedotransfer Functions Multivariate regression, MLP and RBF to estimate CEC for Soils of North Ahvaz
الموضوعات :علی صالحی 1 , کامران محسنی فر 2 , علی غلامی 3
1 - دانش‌آموخته کارشناسی ارشد خاکشناسی، پردیس علوم و تحقیقات خوزستان، دانشگاه آزاد اسلامی،اهواز، ایران.
2 - عضو هیات علمی گروه خاکشناسی، واحد اهواز، دانشگاه آزاد اسلامی، اهواز، ایران
3 - عضو هیات علمی گروه خاکشناسی، واحد اهواز، دانشگاه آزاد اسلامی، اهواز، ایران.
الکلمات المفتاحية: رگرسیون چند متغیره, Multivariate regression, Cation Exchange Capacity, Pedoteransfer function, Easily Available Soil Properties, ظرفیت تبادل کاتیونی خاک, توابع انتقالی, خصوصیات زودیافت خاک,
ملخص المقالة :
To estimate the Cation Exchange Capacity (CEC), indirect manner used of Pedotransfer Functions (PTFs). CEC is one of the important soil fertility factors, and not measured directly because it is costly and time consuming. Thus, used from regression equations between easily and non-easily soil properties. The purpose of this research, is develop the PTFs for CEC, with use of easily available soil properties. For this purpose, measured for 100 sample of soil contain of 1000 data include soil particle size distribution, bulk density, organic matter, lime, pore space, geometric mean diameter and geometric standard deviation were done. After data normalization, were done PTFs with Multivariate Regression (MR) in SPSS and Artificial Neural Networks (ANNs) for soil CEC in MATLAB software. The ANNs used in research are Multi-Layer Perceptron (MLP) and Radial Basis Function (RBF). Education of ANNs are based on trial and error, until arrived suitable outputs with changes hidden layer number and neuron number. From all data were Selected 70% (700) data for training and 30% (300) for teste. Then were entered all data to software and test different networks with one hidden layer. The network was design with trial and error to maximum correlation coefficient and minimum mean square error (MSE). The results were shows MR is suitable for predict CEC (R2 =0.87) and for MLP network, were shows ANN can good estimated CEC with used of easily soil properties. MLP network able to estimate CEC with 9 neurons in input layer, 7 neurons in hidden layer and 1 neuron in output layer with tangent sigmoid transfer function, Linear transfer function and Bayesian learning algorithm with coefficient correlation 0.97 and MSE 0.013. For RBF networks to estimation CEC coefficient correlation and MSE were 0.55, 0.017 respectively. Results shows the MLP network with 1 hidden layer for estimation CEC with use of soil distribution, bulk density, organic matter and lime, is better than RBF network compared with of MSE and coefficient correlation.
اسماعیل نژاد، ل.، سیدمحمدی، ج.، شعبانپور، م و رمضان پور، ح. (2014). پیشبینی سطح ویژه و ظرفیت تبادل کاتیونی با استفاده از بعد فرکتالی توزیع اندازه ذرات خاک. تحقیقات آب و خاک ایران 45: 463-474.
تقی زاده مهرجردی، ر. ا.، سرمدیان، ف.، ذوالفقاری، ع. ا. و جعفری، ا. (2015). پیش بینی ظرفیت تبادل کاتیونی خاک های ایران با استفاده از روش های گوناگون. مهندسی زراعی 38: 59-77.
عسگری، ه. و گلچین، ا. (1384). تأثیر مواد آلی برمیزان ظرفیت تبادل کاتیونی، ظرفیت نگهداری آب و میزان آب قابل استفاده گیاه در چند خاک بکر وکشت شده. نهمین کنگره علوم خاک ایران. مرکز تحقیقات حفاظت خاک و آبخیزداری کشور.
مهاجر، ر.، صالحی، م. ح. و بیگی هرچگانی ح. (1388). تخمین ظرفیت تبادل کاتیونی خاک با استفاده از رگرسیون و شبکه عصبی و اثر تفکیک داده ها بر دقت و صحت توابع . علوم آب و خاک (علوم و فنون کشاورزی و منابع طبیعی) سال سیزدهم، شماره 49.
Amini, M., Abbaspour, C.K., Khademi, H. and Schulin, R., (2005). Neural network models to predict cation exchange capacity in arid regions of Iran. European Journal of Soil Science 56: 551 - 559.
Briggs, L.J. and McLane, J.W., (1907). The moisture equivalents of soils. USDA Bureau of soils bulletin, Washington, DC.
Keller, A., von Steiger, B., van der Zee, S. and Schulin, R., (2001). A stochastic empirical model for regional heavy-metal balances in agroecosystems. Environ Qual 30.
Kianpoor Kalkhajeh, Y., Rezaie Arshad, R., Amerikhah, H. and Sami, M., (2012). Comparison of multiple linear regressions and artificial intelligence-based modeling techniques for prediction the soil cation exchange capacity of Aridisols and Entisols in a semiarid region. AJAE 3: 39-46.
Lei, W.-J., Tang, X.-Y., Reid, B.J. and Zhou, X.-Y., (2016). Spatial distribution of soil hydraulic parameters estimated by pedotransfer functions for the Jialing River Catchment, Southwestern China. Journal of Mountain Science 13: 29-45.
Liao, K., Xu, S. and Wu, J., (2014). Using support vector machines to predict cation exchange capacity of different soil horizons in Qingdao City, China. Journal of Plant Nutrition and Soil Science 177: 775–782.
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 55: 787-794.
McBratney, A.B., Minasny, B., Cattle, S.R. and Vervoot, R.W., (2002). From pedotransfer function to soil inference system. Geoderma 109: 41-73.
Nanko, K., Ugawa, S., Hashimoto, S., Imaya, A., Kobayashi, M., Sakai, H., Ishizuka, S., Miura, S., Tanaka, N., Takahashi, M. and Kaneko, S., (2014). A pedotransfer function for estimating bulk density of forest soil in Japan affected by volcanic ash. Geoderma 213: 36-45.
Oberthur, T., Doberman, A. and Neue, H.V., (1996). How good is a reconnaissance soil map for agronomic purpose? Soil Use and Management 12: 33-43.
Pachepsky, Y.A. and Rawls, W.J., (2003). Soil structure and pedotransfer functions. European Journal of Soil Science 54: 443-452.
Patil, N.G. and Singh, S.K., (2016). Pedotransfer Functions for Estimating Soil Hydraulic Properties: A Review. Pedosphere 26: 417-430.
Rogowski, A.S. and Wolf, J.K., (1994). Incorporating variability in soil map units delineation. Soil Sci. Soc. Am. J. 58: 163-174.
Seybold, c.a., Grossman, R.B. and Reinsch, T.G., (2005). Predicting action Exchange capacity for soilsurveyusing linear models. Soil Sci. Soc. Am. J. 69: 856-863.
Seyedmohammadi, J., Esmaeelnejad, L. and Ramezanpour, H., (2016). Determination of a suitable model for prediction of soil cation exchange capacity. Modeling Earth Systems and Environment 2: 156.
Shekofteh, H., Ramazani, F. and Shirani, H., (2017). Optimal feature selection for predicting soil CEC: Comparing the hybrid of ant colony organization algorithm and adaptive network-based fuzzy system with multiple linear regression. Geoderma 298: 27-34.
Sposito, G., (2008). The Chemistry of Soils. Oxford University Press.
Tamari, S., Wösten, J.H.M. and Ruiz-Suárez, J.C., (1996). Testing an Artificial Neural Network for Predicting Soil Hydraulic Conductivity. Soil Science Society of America Journal 60: 1732-1741.
Visconti, F., Miguel De Paz, J. and Luis Rubio, J., (2012). Choice of selectivity coefficients for cation exchange using principal components analysis and bootstrap anova of coefficients of variation. European Journal of Soil Science 63: 501–513.
Yao, R.-J., Yang, J.-S., Wu, D.-H., Li, F.-R., Gao, P. and Wang, X.-P., (2015). Evaluation of pedotransfer functions for estimating saturated hydraulic conductivity in coastal salt-affected mud farmland. Journal of Soils and Sediments 15: 902-916.
Yi, X., Li, G. and Yin, Y., (2016). Pedotransfer Functions for Estimating Soil Bulk Density: A Case Study in the Three-River Headwater Region of Qinghai Province, China. Pedosphere 26: 362-373.
