مهندسی زراعی

شماره جاری

بر اساس شماره‌های نشریه

بر اساس نویسندگان

بر اساس موضوعات

نمایه نویسندگان

نمایه کلیدواژه ها

درباره نشریه

اهداف و چشم انداز

بانک ها و نمایه نامه ها

پیوندهای مفید

پرسش‌های متداول

فرایند پذیرش مقالات

تأثیر پیش‌پردازش متغیرهای ورودی مدل عصبی - فازی همراستا با استفاده از روش تجزیه به مؤلفه اصلی جهت برآورد درصد سدیم تبادلی خاک

نوع مقاله : مقاله پژوهشی

نویسندگان

1 گروه علوم خاک دانشگاه زنجان

2 عضو هیئت علمی مرکز آموزش عالی شهید باکری میاندوآب-دانشگاه ارومیه

3 گروه خاک دانشکاه زنحان

چکیده

خاک‌های سدیمی به‌دلیل درصد بالای سدیم تبادلی ویژگی‌های فیزیکی و شیمیایی نامطلوبی دارند. این مشکل منجر به کاهش ظرفیت آب قابل استفاده و کاهش رشد گیاهان می‌شود. برای اندازه‌گیری درصد سدیم تبادلی نیاز به اطلاع از مقدار ظرفیت تبادل‌کاتیونی است. اما اندازه‌گیری آن پرهزینه بوده و زمان بر نیز می‌باشد. بنابراین، اندازه‌گیری آن با استفاده از ویژگی‌های زودیافت خاک ضروری است. هدف از انجام این پژوهش توسعه یک مدل هوشمند بر اساس هوش مصنوعی و با استفاده از مدل تلفیقی عصبی- فازی همراستا (CANFIS) برای تخمین درصد سدیم تبادلی در جنوب شرقی استان آذربایجان شرقی است. در این رابطه 209 نمونه خاک به‌صورت شبکه‌بندی منظم (250×250 متر) از عمق صفر تا 25 سانتی‌متری برداشت و برای اندازه‌گیری درصد سدیم تبادلی و برخی دیگر از عوامل تأثیرگذار بر روی آن به آزمایشگاه منتقل شد. نتایج نشان داد که به‌ترتیب نسبت جذب سدیم (961/0)، هدایت الکتریکی (808/0)، pH (638/0)، مقدار رس (524/0)، شن (482/0) و سیلت (389/0) بیشترین تأثیر را در تخمین درصد سدیم تبادلی خاک دارند. در این پژوهش رابطه بین درصد سدیم تبادلی و نسبت جذب سدیم با ضریب تبیین 91/0 محاسبه‌ شد. مدل CANFIS با ورودی‌های انتخاب ‌شده از آنالیز به مؤلفه‌های اصلی مشتمل بر نسبت جذب سدیم، هدایت الکتریکی، واکنش خاک دارای کارائی بیشتری نسبت به مدل CANFIS با پنج ورودی نشان داد. ‌طوری‌که آماره‌های جذرمیانگین مربعات خطا و ضریب تبیین برای مدل مناسب‌تر و به‌ترتیب 0/1 و 96/0 محاسبه شد. نتایج موید کارایی بالای شبکه‌های عصبی - فازی در تخمین درصد سدیم تبادلی است.

کلیدواژه‌ها

عنوان مقاله [English]

Investigation of the most Important Factors in Prediction the Soil Exchangeable Sodium Percentage by Neural-Fuzzy Constant Neural Model

نویسندگان [English]

  • ALi Barikloo 1
  • Moslem Servati Khajeh 2
  • parisa alamdari 3

1 Department of soil science, university of Zanjan

2 Assistant professor Shahid bakeri high education of miandoab, Urmia University

3 university of zanjan

چکیده [English]

Introduction: A variety of precise farming practices in arid and semi-arid regions such as Iran require periodic information on soil salinity and sodium content. Sodic soils have unfavorable physical and chemical properties due to the high percentage of exchangeable sodium (ESP). This problem reduces the capacity of available water and growth of plants. To measure the percentage of exchangeable sodium, it is necessary to measure the amount of cation exchange capacity (CEC). Because determining CEC are time consuming, it is appropriate and economical to develop a method that determines ESP indirectly from easy-measured properties. One of the methods to study the relationships and correlations between different soil properties and their quantitative expression is the use of some statistical models. These models, called transfer functions, include data mining, regression models, artificial neural networks, and the coherent neural-fuzzy integrated system (CANFIS).
Materials and Methods: The aim of this study was to develop an intelligent model (CANFIS) for predicting soil ESP from soil easy-measured properties in approximately 1450 ha of salt affected soils, South East of Urmia Lake, Bonab region, East Azarbaijan Province. For this purpose, 209 soil samples were taken by grid survey method from surface (0-25 cm) and then carried out laboratory for measure necessary soil properties. Soil acidity and electrical conductivity of samples were measured in a ratio of 1: 5 soils to water, soil tissue by hydrometric method, sodium cation by flame photometer and calcium and magnesium by returned titration method.
Results and Discussion: Pearson correlation method showed that the accuracy of estimating intelligent models depends on the correct choice of first layer input information. Therefore, using the correlation matrix, the relationship between soil parameters (independent variable) and the percentage of exchangeable sodium (dependent variable) was determined. Sodium absorption ratio (0.961), electrical conductivity (0.808), pH (0.638), clay content (0.524), sand (0.482) and silt (0.389) have the greatest effect on estimation Percentage of exchangeable sodium in soil. Also, the positive relationship between soil reaction and the percentage of exchangeable sodium on the one hand and the high correlation between the percentage of exchangeable sodium and electrical conductivity indicate the importance of the fine soil. In this study, the relationship of linear regression between the percentage of exchangeable sodium and the ratio of sodium uptake with an explanation coefficient of 0.91 was calculated, which is significant at the level of 5% probability. Two important targets were designed in this paper. First target is determining performance of Fuzzy Neural Networks (CANFIS) in predicting ESP by sand, clay, pH, SAR, EC as input variable. The second target is evaluation of performance of CANFIS model by selected variable of PCA model. Results showed that the performance of second model was acceptable Model 1 justifies 88% of the changes in the percentage of exchangeable sodium by entering all inputs. But CANFIS model with higher inputs selected by PCA model (principal component analysis) including sodium adsorption ratio, electrical conductivity, soil reaction has higher accuracy. So that the values of root mean square error and correlation coefficient in the test stage for the first model were 0.88 and 3.25 and the second model was 0.96 and 1.0, respectively.
Conclusion: These results demonstrated the superiority of intelligent models in explanation of the relationship between ESP and other soil easily-measured properties. In order to model the soil retrieval properties such as cation exchange capacity and to achieve the most suitable model, it is necessary to pay attention to the number and most effective input variables. Because the main goal is to provide a model with a minimum number of inputs as well as inputs that are easy to measure and in a short time. The results of quantification of the importance of variables in the CANFIS model confirm the use of three characteristics of sodium adsorption ratio, electrical conductivity of soil saturated extract and soil acidity in modeling the percentage of exchangeable sodium. The results of this study can be generalized to soils of similar arid and semi-arid regions. Also, due to the ambiguity of soil-related phenomena or the approximate values of the measured values of different soil properties and the uncertainty in the data, the use of hybrid models such as CANFIS that use fuzzy sets, It can be useful in fitting soil transfer functions.
Keywords: Easly-measured Properties, Hard-measured Properties, PCA All right reserved.

کلیدواژه‌ها [English]

  • "Easly measured Properties"
  • " Hard measured Properties"
  • "PCA "
مراجع
  1. Abdulshahed M., Longstaff  A.P., Fletcher S., and Myers A. 2015. Thermal error modelling of machine tools based on anfis with fuzzy c-means clustering using a thermal imaging camera. Applied Mathematical Modelling, 39(7):1837-1852.‏
  2. Adhikari P., Shukla M.K., and Mexal J.G. Spatial variability of electrical conductivity of desert soil irrigated with treated wastewater: implications for irrigation management. Applied and Environmental Soil Science, 2011:1–11.
  3. Amini M., Abbas Pour 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, 53:748-757.
  4. Amutha R., and Porchelvan P. 2011. Seasonal prediction of groudwater levels using anfis and radial basis neural network. International Journal of Geology, Earth and Environmental Sciences, 1:98-108.
  5. Auerswald K., Simon S., Stanjek H. Influence of soil properties on electrical conductivity under humid water regimes. Soil Sci, 166(6):382–390.
  6. Aytek A. 2008. Co-active neuro-fuzzy inference system for evapotranspiration modeling: soft computing, a fusion of foundations method. Journal of Applied Science, 13(7):691-700.
  7. Bayat Varkeshi M., Zare Abyaneh H., Marofi S., Sabziparvar A.A. and Soltani F. 2009. Simulation of reference evapotranspiration using artificial neural method and empirical methods and comparison with experimental lysimeter data in cold semi-arid climate of hamedan. Journal of Water and Soil Conservation­, 16(­4):79-100. (In Parsian with English abstract)
  8. Bhargava G.P., and Abrol I.P. 1978. Characteristics of some typical salt affected soils of uttar pradesh. division of soils and agronomy, Central Soil Salinity Research Institute: Yazd.
  9. Bouyoucos G.J. 1962. Hydrometer method improved for making particle size analysis of soils. Agronomy Journal, 56: 464-466.
  10. Bower C.A., Reitemeier R.F., and Fireman M. 1952. Exchangeable cation analysis of saline and alkali soils. Soil Science 73:251-261.
  11. Cabena P.H., Stadler R., Verhees J., and Zanasi A. 1998. Discovering data mining: from concept to implementation, IBM, New Jersey, 195 Pp.
  12. Chiu S.L. 1994. Fuzzy model identification based on cluster estimation. Journal of Intelligent and Fuzzy Systems, 2(3):267-278.
  13. Dahiya I. S., Richter J., and Malik R. S. 1984. Soil spatial variability: a review. International Journal of Tropical Agriculture, 11:91-102.
  14. Ebrahimi F., Afsar A., Rezaeinour J., and Ghanbari Sorkhi A. 2017. An efficient intellighent approach for short-term load forecasting. Industrial engineering & management sharif. 33(1):43-54. (in Parsian with English abstract)
  15. Emerson W.W., and Bakker A.C. 1973. The comparative effects of exchangeable calcium, magnesium and sodium on some physical properties of red-brown earth sub-soils. II. The spontaneous dispersion of aggregates in water. Australian Journal of Soil Research, 11(2):151 – 157.
  16. Farahmand A., Oustan S.H., Jafarzadeh A.J., and Asgarzad A.N. 2011. The parameters of sodium and salinity in some salt affected soils of the tabriz plain. Journal of Soil and Water, 22:1-15. (in Persian)
  17. Fireman M., and Wadleigh C.H. 1951. A statistical study of the relation between pH and the exchangeable-sodium-percentage of western soils. Journal of Soil Science, 71(4):273-286.
  18. Hemmatpour, and  Hashemi H. 2012. Using pca and rda feature reduction techniques for ranking seismic attributes. Journal of the Earth and Space Physics, 37(4):217-227. (In Parsian with English abstract)
  19. Jang J.S., Sun C.T., and Mizutani E. 1997. Neuro-fuzzy and soft computing: a computational approach to learning and machine intelligence [Book Review]. IEEE Transactions on automatic control, 42(10):1482-1484.
  20. Jang J.S. 1993. ANFIS: adaptive-network-based fuzzy inference system. IEEE Transactions on Systems, Man, and Cybernetics, 23(3):665-685
  21. Johnson R.A., and Wichern D.W. 2014. Applied multivariate statistical analysis. London, UK Pearson Prentice-hall, 6:590p.
  22. Jurinak J., and Suarez D.L. 1990. The Chemistry of Salt-Affected Soils. In K. K. Tanji (Ed.). Agricultural Salinity Assessment and Management, 71:42-63. American Society of Civil Engineers, New York: N.Y.
  23. Karami A., and Afiuni-Zadeh S. 2012. Sizing of rock fragmentation modeling due to bench blasting using adaptive neuro-fuzzy inference system and radial basis function. International Journal of Mining Science and Technology, 22:459–463.
  24. Keshavarzi, and Sarmadian F. 2012. Mapping of spatial distribution of soil salinity and alkalinity in a semi-arid region. Ann Warsaw Agricult Univ SGGW Land Reclam, 44(1):3–14.
  25. Keshavarzi A., Bagherzadeh A., Omran E.S.E., and Iqbal M. 2016. Modeling of soil exchangeable sodium percentage using easily obtained indices and artificial intelligence-based models. Modeling Earth Systems and Environment, 2(3):1-10.‏
  26. Kline P. 2014. An easy guide to factor analysis. New York: Routledge.
  27. Liu C.W., Lin K.H., and Kuo Y.M. 2003. Application of factor analysis in the assessment of groundwater quality in a black foot disease area in taiwan. Science of the Total Environment­, 313:77-89.
  28. Zhou S., Lin M., and Ma L. 2008. Support vector machine optimized with genetic algorithm for short-term load forecasting. International Symposium on Knowledge Acquisition and Modeling. IEEE, 654-657.
  29. Mahdavi Tabatabaei N., Mortezaeei S.R., Taghizadegan N., and Nayir A. 2008. Short term load forecasting by neural network in mashhad (iran) power system. University of Pitesti Electronics and Computers Science, 2(8):12-18.
  30. Mcbratney A.B., and Odeh I.O.A. 1997. Application of fuzzy sets in soil science: fuzzy logic, fuzzy measurements and fuzzy decisions. Geoderma, 77(2-4):85-113.
  31. Merdun H., Meral O.C., and Apan R.M. 2006. Comparison of artificial neural network and regression pedotransfer functions for predict of water retention and saturated hydraulic conductivity. Soil and Tillage Research, 90:108-116.
  32. Metternicht G., and Gonzalez S. 2004. Foundations of a fuzzy exploratory model for soil erosion hazard prediction. Environmental Modelling & Software, 20(6):715-728.
  33. Minasny B., Hopman J., Harter W.T., Eching S.O., Toli A., and Denton M.A. 2004. Neural networks prediction of soil hydraulic functions for alluvial soils using multistep outflow data. Soil Science Society of America Journal, 68:417-429.
  34. Mohaddes F. 2010. Principal component and factor analysis case study: assets price evaluation and inflation impacts. Economic Research and Policy Department Central Bank of the Islamic Republic of Iran.
  35. Mohammadi J., and Taheri M. 2005. Estimation of pretransfer function using fuzzy regression. Journal of Agriculture Science and Technology, 2:51-60.
  36. Monem M.J., and Kiapasha M.S. 2009. Development and evaluation of an upstream fuzzy control system model for irrigation canals. Journal of Iranian Water Research, 3(4):41-50.
  37. MousaviR., Sarmadian F., Omid M., and Bogaret p. 2021. Application of Machine Learning Models in Spatial Estimation of Soil Phosphorus and Potassium in Some Parts of Abyek Plain. Journal of Iranian Spoi Research, 35(4):397-411.
  38. Omran E.S. 2008. Is soil science dead and buried Future image in the world of 10 billion people. Catrina: The International Journal of Environmental Sciences, 3(2):59–68.
  39. Rashidi M., and Seilsepour 2008. Modeling of soil exchangeable sodium percentage based on soil sodium adsorption ratio. Journal of Agricultural and Biological Science, 3(4):22-26.
  40. Rhoades J. D. 1982. Cation exchange capacity. In A. L. Page Et Al (Ed.). (Part. 2). (Pp. 149-157). Methods Of Soil Analysis, Agron. Monogr. 9, American Society Of Agronomy, Madison, WI, USA.
  41. Richards L.A. 1954. Diagnosis and improvement of saline alkali soils, Agriculture, 160, Handbook 60. US Department of Agriculture, Washington DC.
  42. Robbins C.W., and Meyer W.S. 1990. Calculating ph from ec and sar values in salinity models and sar from soil and bore water pH and EC data. Soil Research, 28(6):1001–1011.
  43. Rowell D.L. 1994. Soil science: methods and application. England: longman group, harlow, UK.
  44. Sarani F., Gholamalizadeh A., and Shabani A. 2016. Comparing regression and artificial intelligence models for estimating soil exchangeable sodium percentage from sodium absorption ratio (case study: miankangi region soils, sistan. Journal Water and Soil Science. 26(2):125-137. (in Parsian with English abstract)
  45. Sarmadian F., and Keshavarzi A. 2016. Application of canfis model in prediction of soil cation exchange capacity in some arid and semi-arid regions of iran. Journal of range and watershed management. Iranian Journal of Natural Resources, 69(2):397-410. (In Persian)
  46. Schaap M.G., and Bouten W. 1996. Modelling water retention curves of sandy soils using neural networks. Water Resources Research, 32:3033-3040.
  47. Seilsepour M., and Rashidi M. 2008a. Modelling of soil sodium adsorption ratio based on soil electrical conductivity. ARPN J Agric Biol Sci 3:27–31.
  48. Singh P., and Deo M.C. 2007. Suitability of different neural networks in daily flow Applied Soft Computing, 7:968-978.
  49. Spearman C. 1994. General intelligence: objectively determined and measured. American Journal of Psychology, 15:92-201.
  50. Tamari S., Wosten J.H.M., and Ruz-Suarez J.C. 1996. Testing an artificial neural network for predicting soil hydraulic conductivity. Soil Science Society of America Journal, 60:1732-1741.
  51. 1996. Soil survey laboratory methods manual. Soil survey investigations republic, washington: united states government print.
  52. Wiegand C. L., Lyles L., and Carter D.L. 1986. Interspersed salt-affected and unaffected dryland soils of the lower rio grande valley: ii. Occurrence of salinity in relation to infiltration rates and profile characteristics. Soil Science Society of America Journal, 30(1):106-110.
  53. Wosten J.H.M., Pachepsky Y.A., and Rawls W.J. 2001. Pedotransfer functions: bridging the gap between available basic soil data and missing soil hydraulic characteristics. Journal of Hydrology, 251:123-150.
  54. Zare Abyaneh H., and Bayat Varkeshi M. 2013. Development and application of statistical and neural, fuzzy, genetic algorithm models in estimation of spatial distribution of water table level. Journal of water and soil conservation. Journal of Agricultural Sciences and Natural Resources, 20(4):1-25. (in Parsian with English abstract)
  55. Zare Abyaneh H., Bayat Varkeshi M., and Marofi S. 2011. Forecasting of garlic (allium sativum l.) Evapotranspiration by using multiple modeling. Journal of Agricultural Science and Natural Resource, 18(2):89-107. (In Parsian with English abstract)

 

مهندسی زراعی
دوره 45، شماره 3
آذر 1401
صفحه 299-315
فایل ها
هم رسانی
ارجاع به این مقاله
آمار