استفاده از سطح ویژه برای بهبود تخمین ظرفیت تبادل کاتیونی خاک از طریق شبکه‌های عصبی مصنوعی

نوع مقاله: مقاله پژوهشی

نویسندگان

1 دانشگاه بوعلی سینا-همدان

2 مؤسسه تحقیقات برنج کشور

3 دانشگاه گیلان

چکیده

  ظرفیت تبادل کاتیونی (CEC) یکی از خصوصیات مهم خاک است که اندازه­گیری مستقیم  آن مشکل، وقت گیر و پر هزینه است. علی رغم تحقیقات زیاد در مورد تخمین CEC، چگونگی بهبود تخمین‌ها با معرفی متغیرهای جدید مورد بررسی کافی قرار نگرفته است. بر پایه بررسی انجام شده از منابع علمی داخلی و خارجی در هیچ تحقیقی از متغیر کمکی سطح ویژه برای تخمین  CEC استفاده نشده است. در این تحقیق 1662 نمونه خاک از نقاط مختلف استان گیلان جمع آوری گردید. رس، سیلت، شن، کربن آلی، pH و CEC برای نمونه­های فوق اندازه­گیری شدند. منحنی دانه بندی (PSD) با استفاده از بافت خاک به روش مدل اسکاگز و همکاران شبیه­سازی گردید. سپس سطح ویژه کل (TSS) و حاصل ضرب سطح ویژه جزء رس در کسر جرمی آن (SS1) از منحنی  PSDمحاسبه و برای تخمین CEC به عنوان ورودی در شبکه­های عصبی مصنوعی استفاده شدند.  همبستگی غیر خطی قوی و معنی­داری بین CEC با TSS و SS1 مشاهده شد. استفاده از TSS و SS1 در PTF ها موجب بهبود تخمین CEC گردید. SS1 بیشترین تاثیر را در تخمین CEC داشت. تقسیم داده­ها به هشت گروه بطور معنی­داری موجب بهبود عملکرد PTF ها شده و تاثیر TSS و SS1 بر تخمین CEC را افزایش داد. استفاده از این توابع انتقالی روشی آسان و مقرون به صرفه بوده و می­تواند گامی مهم در بهبود تخمین CEC خاک محسوب شود. 

کلیدواژه‌ها


عنوان مقاله [English]

Using of Specific Surface to Improve the Prediction of Soil CEC by Artificial Neural Networks

نویسندگان [English]

  • H Bayat 1
  • N Davatgar 2
  • S Moallemi 3
چکیده [English]

Cation exchange capacity (CEC) is one of the most important soil properties. Its direct measurement is difficult, costly and time-consuming. In spite of large number of researches done to predict CEC, its prediction improvement by adding new input variables, however, remains a challenging issue. To our knowledge no one has used the auxiliary variable of specific surface to predict CEC. In the present work, 1662 disturbed soil samples were collected from different parts of Guilan province. Soil properties including pH, sand, silt, clay, organic carbon, and CEC were measured. The entire particle size distribution (PSD) curve was extended from limited soil texture data. Using Skaggs et al moded. Then, total specific surface (TSS) and the product of the specific surface of clay fraction and its mass fraction (SS1) were calculated from the extended PSD curve to predict CEC by artificial neural networks. Strong nonlinear correlation was found between CEC, TSS and SS1. CEC predictions were improved by using TSS and SS1 in the PTFs. SS1 was the most important variable in the prediction of CEC. Partitioning the whole data into eight groups improved significantly the performance of the PTFs and increased the effect of TSS and SS1 in improving the CEC prediction. Using these PTFs is an easy and economical method and it would be a great step forward in improving the estimation of soil CEC.  

کلیدواژه‌ها [English]

  • توابع انتقالی
  • سطح ویژه
  • شبکه‌های عصبی مصنوعی
  • ظرفیت تبادل کاتیونی
معلمی س، دواتگر ن و دریغ گفتار ف، 1388. رابطه بین گنجایش تبادل کاتیونی و برخی خصوصیات فیزیکی و شیمیایی در خاک­های گیلان. مجله پژوهشهای خاک، جلد 23) شماره 2). صفحه­های 179-173.
معلمی س و دواتگر ن، 1390. مقایسه توابع انتقالی رگرسیونی و شبکه عصبی مصنوعی در برآورد گنجایش تبادل کاتیونی خاک­های گیلان. مجله علوم و فنون کشاورزی و منابع طبیعی، علوم آب و خاک. سال 15،  شماره 55. صفحه­های 169-181.
مهاجر ر، صالحی م ه، و بیگی هرچگانی ح، 1388. تخمین ظرفیت تبادل کاتیونی خاک با استفاده از رگرسیون و شبکه عصبی و اثر تفکیک داده­ها بر دقت و صحت توابع. علوم و فنون کشاورزی و منابع طبیعی علوم اب و خاک، شماره 49.  صفحه­های 83-97.
 مقدم م، محمدی شوطی س ا و آقائی سربرزه م 1373. آشنایی با روش­های آماری چند متغیره. انتشارات پریور. 208 صفحه
Akaike H, 1974. New Look at the Statistical Model Identification. IEEE Transactions on Automatic Control, AC-19: 716-723.
Amini M, Abbaspour KC, 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: 551-559.
Arnepalli DN, Shanthakumar S, Hanumantha Rao B and Singh DN, 2008. Comparison of methods for determining specific-surface area of fine-grained soils. Geotechnical and Geological Engineering 26: 121-132.
Asadu CLA and Akamigbo FOR, 1990. Relative contribution of organic matter and clay fractions to cationexchange capacity of soils in southern Nigeria. Samaru. Journal of Agricultural Research 7: 17-23.
BellMA and van Keulen H, 1995. Soil pedotransfer functions for four Mexican soils. Soil Science Society of America Journal 59: 865-871.
Bower CA, Reitmeir RF and Fireman M, 1952. Exchangeable cation analysis of saline and alkali soils. Soil Sci. 73: 251-261.
BradyNC and Weil RR, 1999. The Nature and Properties of Soils. 12 th edition. Prentice Hall.
Breeuwsma A, Wosten JHM, Vleeshouwer JJ, Van Slobbe AM and Bouma J, 1986. Derivation of land qualities to assess environmental problems from soil surveys. Soil Science Society of America Journal 50: 186-190.
Carpena O, Lux A and Vahtras K, 1972. Determination of exchangeable cations in calcareous soils. Soil Science 33: 194-199.
Diebold FX, and Mariano RS, 2002. Comparing predictive accuracy. Journal of Business and Economic Statistics 20: 134-144.
Drake EH and Motto HL, 1982. An analysis of the effect of clay and organic matter content on the cation exchange capacity of New Jersey soils. Soil Science 133: 281-288.
Ersahin S, Gunal H, Kutlu T, Yetgin B and Coban S, 2006. Estimating specific surface area and cation exchange capacity in soils using fractal dimension of particle-size distribution. Geoderma 136: 588-597.
Fooladmand HR and Sepaskhah, AR, 2006. Improved estimation of the soil particle-size distribution from textural data. Biosys Eng 94: 133-138.
Gee GW and Or D,  2002. Particle size analysis. Pp. 255-295. In: Warren, AD (ed), Methods of Soil Analysis. Part 4. Physical Methods. Soil Science Society of AmericaMadison, WI.
GesslerPE, MooreID, McKenzieNJ and Ryan PJ, 1995. Soil landscape modelling and spatial prediction of soil attributes. International Journal of Geographical Information Systems 9: 421–432.
Hepper EN, BuschiazzoDE, Hevia GG, Urioste A and Antón L, 2006. Clay mineralogy, cation exchange capacity and specific surface area of loess soils with different volcanic ash contents. Geoderma 135: 216-223.
Hillel D, 1998. Environmental Soil Physics. Academic Press.
Keller A, Von Steiger B, Van der Zee, SEATM and Schulin R, 2001. A stochastic empirical model for regional heavy-metal balances in agroecosystems. Journal of Environmental Quality 30: 1976-1989.
Lal R and Shukla MK, 2004. Principles of Soil Physics. Marcel Dekker, Inc. New York.
Manrique LA, Jones CA and Dyke PT, 1991. Predicting cation-exchange capacity from soil physical and chemical properties. Soil Science Society of America Journal 55: 787-794.
Mc Bratney AB, Minasny B, Cattle SR and Vervoort RW, 2002. From pedotransfer functions to soil inference systems. Geoderma 109: 41-73.
Miller WF, 1970. Inter-regional predictability of cation-exchange capacity by multiple regression. Plant and Soil 33: 721-725.
Minasny B and Mc Bratney AB, 2002. The Neuro-m method for fitting neural network parametric pedotransfer functions. Soil Science Society of America Journal 66: 352-361.
Nelson DW and Sommers LP, 1986. Total carbon, organic carbon and organic matter, Pp. 539–579. In Page, AL (ed), Methods of Soil Analysis. Part 2. American Society of Agronomy and Soil Science Society of America, Madison. WI.
Nemes A, Schaap MG and Wosten JHM, 2003. Functional evaluation of pedotransfer functions derived from different scales of data collection. Soil Science Society of America Journal
67: 1093-1102.
Neuro-Solutions,  2005. Getting Started Manual Version 4. NeuroDimension, Inc. 1800 N. Main Street, uite D4 Gainesville, FL Nørgaard M, 2000. Neural Network Based System Identification Toolbox. Tech. Rep. 00-E-891, Dep. of Automation, Tech. Univ. of Denmark, Lyngby, Denmark.
Odeh IOA, Mc Bratney AB, Chittleborough DJ, 1995. Further results on prediction of soil properties from terrain attributes: heterotopic cokriging and regression-kriging. Geoderma 67: 215–225.
Sahrawat KL, 1983. An analysis of the contribution of organic matter and clay to cation exchange capacity of some Philippine soils: Communications in Soil Science & Plant Analysis 14: 803-809.
Salehi MH, Mohajer R and Beigie H, 2008. Developing Soil Cation Exchange Capacity Pedotransfer Functions using Regression and Neural Networks and the Effect of Soil Partitioning on the Accuracy and Precision of Estimation, Pp. 345-356. International Meeting on SoilFertilityLand Management and Agroclimatology, Turkey.
Seybold C A, Grossman RB  and Reinsch TG, 2005. Predicting cation exchange capacity for soil survey using linear models. Soil Science Society of America Journal 69:856-863.
Skaggs TH, Arya LM, Shouse PJ and Mohanty BP, 2001. Estimating particle-size distribution from limited soil texture data. Soil Science Society of America Journal 65: 1038-1044.
SPSS Inc, 1994. SPSS Professional Statistics: Chicago, SPSS Inc.
Sumner ME and Miller WP, 1996. Cations exchange capacity and exchange coefficients. Pp 1201-1230. In: Sparks DL (Ed), Methods of soil analysis, Part 3- chemical methods. Agronomy Monograph, vol. 9. ASA and SSSA, Madison, WI.
Syers JK, CampbellAS and Walker TW, 1970. Contribution of organic carbon and clay to cation exchange capacity in a chronosequence of sandy soils. Plant Soil 33:104–112.
Theng BKG, Ristori GG, Santi CA and Percival HJ, 1999. An improved method for determining the specific surface areas of topsoils with varied organic matter content, texture and clay mineral composition. European Journal of Soil Science 50: 309-316.
Thompson ML, Zhang H, Kazemi M and Sandor JA, 1989. Contribution of organic matter to cation exchange capacity and specific surface area of fractionated soil materials. Soil Science 148: 250-257.
Tomasella J, Pachepsky Y, Crestana S and Rawls WJ, 2003. Comparison of two techniques to develop pedotransfer functions for water retention. Soil Science Society of America Journal 67: 1085-1092.
Tschapek M and Torres Sanchez RM, 1978. The specific surface of Na+ humate on the basis of coion exclusion. Geochimica et Cosmochimica  Acta 42: 1317-1320.
Wösten JHM, Pachepsky Y and Rawls WJ, 2001. Pedotransfer functions: Bridging the gap between available basic soil data and missing soil hydraulic characteristics. Journal of Hydrology 251: 123-150.