برآورد مقاومت فروروی در خاک های زراعی دشت اردبیل با استفاده از توابع انتقالی رگرسیونی و شبکه عصبی مصنوعی

نوع مقاله : مقالات پژوهشی

نویسندگان

• غلام رضا شیخ زاده
• شکراله اصغری
• ترحم مصری گندشمین

دانشگاه محقق اردبیلی

https://doi.org/10.22067/jsw.v30i3.42235

چکیده

مقاومت فروروی (PR) یکی از پویاترین ویژگی های مکانیکی خاک است که عملیات خاک ورزی، رشد گیاه و فعالیت های بیولوژیکی خاک را تحت تاثیر قرار می دهد. اندازه گیری مستقیم این متغیر دشوار، زمان بر و پرهزینه است. هدف از تحقیق حاضر ارائه توابع انتقالی رگرسیونی و شبکه عصبی مصنوعی برای برآورد PR خاک بر پایه متغیرهای زود یافت شامل توزیع اندازه ذرات، کربن آلی، جرم مخصوص ظاهری و حقیقی، کربنات کلسیم معادل، تخلخل کل و رطوبت اولیه خاک مزرعه بود. به این منظور 105 نمونه از عمق 0 تا cm 10 خاک های زراعی دشت اردبیل برداشته شد سپس برخی ویژگی های فیزیکی و شیمیایی آن‌ها تعیین گردید. داده ها به دو سری آموزشی (78 نمونه) و آزمونی (27 نمونه) تقسیم شدند. برای اشتقاق توابع انتقالی رگرسیونی و شبکه عصبی به ترتیب از نرم افزارهای 18 SPSS و MATLAB استفاده گردید. نتایج توابع رگرسیونی و شبکه عصبی نشان داد که مناسب ترین متغیرها در برآورد PR خاک، رطوبت اولیه مزرعه، جرم مخصوص ظاهری و توزیع اندازه ذرات خاک بودند. مقادیر ضریب تبیین (R2)، مجذور میانگین مربعات خطا (RMSE) و معیار اطلاعات آکائیک (AIC) برابر 55/0، MPa 89/0 و 67/14- و 91/0، MPa 37/0 و 64/146- به ترتیب برای مناسب ترین تابع رگرسیونی و شبکه عصبی به دست آمد. بنابراین دقت توابع شبکه عصبی در برآورد PR خاک منطقه مورد مطالعه بیشتر از توابع رگرسیونی بود.

کلیدواژه‌ها

• تخمین
• رطوبت اولیه
• فشردگی خاک
• متغیر زودیافت

20.1001.1.20084757.1395.30.3.23.7

عنوان مقاله [English]

Estimating Penetration Resistance in Agricultural Soils of Ardabil Plain Using Artificial Neural Network and Regression Methods

نویسندگان [English]

• Gholam Reza Sheykhzadeh
• shokrollah asghari
• Tarahom Mesri Gundoshmian

University of Mohaghegh Ardabili

چکیده [English]

Introduction: Penetration resistance is one of the criteria for evaluating soil compaction. It correlates with several soil properties such as vehicle trafficability, resistance to root penetration, seedling emergence, and soil compaction by farm machinery. Direct measurement of penetration resistance is time consuming and difficult because of high temporal and spatial variability. Therefore, many different regressions and artificial neural network pedotransfer functions have been proposed to estimate penetration resistance from readily available soil variables such as particle size distribution, bulk density (Db) and gravimetric water content (θm). The lands of Ardabil Province are one of the main production regions of potato in Iran, thus, obtaining the soil penetration resistance in these regions help with the management of potato production. The objective of this research was to derive pedotransfer functions by using regression and artificial neural network to predict penetration resistance from some soil variations in the agricultural soils of Ardabil plain and to compare the performance of artificial neural network with regression models.
Materials and methods: Disturbed and undisturbed soil samples (n= 105) were systematically taken from 0-10 cm soil depth with nearly 3000 m distance in the agricultural lands of the Ardabil plain ((lat 38°15' to 38°40' N, long 48°16' to 48°61' E). The contents of sand, silt and clay (hydrometer method), CaCO3 (titration method), bulk density (cylinder method), particle density (Dp) (pychnometer method), organic carbon (wet oxidation method), total porosity(calculating from Db and Dp), saturated (θs) and field soil water (θf) using the gravimetric method were measured in the laboratory. Mean geometric diameter (dg) and standard deviation (σg) of soil particles were computed using the percentages of sand, silt and clay. Penetration resistance was measured in situ using cone penetrometer (analog model) at 10 replicates. The data were divided into two series as 78 data for training and 27 data for testing. The SPSS 18 with stepwise method and MATLAB software were used to derive the regression and artificial neural network, respectively. A feed forward three-layer (8, 11 and 15 neurons in the hidden layer) perceptron network and the tangent sigmoid transfer function were used for the artificial neural network modeling. In estimating penetration resistance, The accuracy of artificial neural network and regression pedotransfer functions were evaluated by coefficient of determination (R2), root mean square error (RMSE), mean error (ME) and Akaike information criterion (AIC) statistics.
Results and discussion: The textural classes of study soils were loamy sand (n= 8), sandy loam (n= 70), loam (n= 6) and silt loam (n= 21). The values of sand (26.26 to 87.43 %), clay (3.99 to 17.34 %), organic carbon (0.3 to 2.41 %), field moisture (4.56 to 33.18 mass percent), Db (1.02 to 1.63 g cm-3) and penetration resistance (1.1 to 6.6 MPa) showed a large variations of study soils. There were found significant correlations between penetration resistance and sand (r= - 0.505**), silt (r= 0.447**), clay (r= 0.330**), organic carbon (r= - 0.465**), Db (r= 0.655**), θf (r= -0.63**), CaCO3 (r= 0.290**), total porosity (r= - 0.589**) and Dp (r= 0.266*). Generally, 15 regression and artificial neural network pedotransfer functions were constructed to predict penetration resistance from measured readily available soil variables. The results of regression and artificial neural network pedotransfer functions showed that the most suitable variables to estimate penetration resistance were θf, Db and particles size distribution. The input variables were n and θf for the best regression pedotransfer function and also Db, silt, θf and σg for the best artificial neural network pedotransfer function. The values of R2, RMSE, ME and AIC were obtained equal to 0.55, 0.89 MPa, 0.05 MPa and -14.67 and 0.91, 0.37 MPa, - 0.0026 MPa and -146.64 for the best regression and artificial neural network pedotransfer functions, respectively. The former researchers also reported that there is a positive correlation between penetration resistance with Db and a negative correlation between penetration resistance with θf and organic carbon.
Conclusion: The results showed that silt, standard deviation of soil particles (σg), bulk density (Db), total porosity and field water content (θf) are the most suitable readily available soil variables to predict penetration resistance in the studied area. According to the RMSE and AIC criteria, the accuracy of artificial neural network in estimating soil penetration resistance was more than regression pedotransfer functions in this research.

کلیدواژه‌ها [English]

• Estimation
• Initial moisture
• Readily available variable
• Soil compaction

مراجع

1- Abbaspour Gilandeh Y., and Shaygani Soltanpour A.R. 2014. Soil cone index prediction using artificial neural networks model and its comparison with regression models. Journal of Soil Management and Sustainable Production. 187-204. (in Persian)

2- Alijanpour Shalmani A., Shabanpour M., Asadi., H., and Bagheri F.2011. Estimation of soil aggregate stability in forest soils of Guilan Province by artificial neural networks and regression pedotransfer functions. Water and soil Science. 21:152-163. (in Persian)

3- Bachmann J., Contreras K., Hartage K. H. and MacDonald R. 2005. Comparison of soil strength data obtained in situ with penetrometer and with vane shear test. Soil &Tillage Research. 89:86-102.

4- Bayat H., Neyshabouri M.R. and Hajabbasi M. 2008. Comparing neural networks, linear and nonlinear regression techniques to model penetration resistance. Turkish Journal of Agriculture and Forestry. 32: 425-433.

5- Besalatpour A.A., Hajabbasi M.A., and Ayoubi S. 2010. Estimation of some physical and mechanical properties of soils using artificial neural network. Sixth National Congress on Civil Engineering. Semnan, Iran.

6- Blake G.R. and Hartge K.H. 1986. Bulk density, p. 363-375. In: Klute, A. (ed). Methods of Soil Analysis. Part 1. 2nd ed. Agronomy. Monograph. 9. ASA, Madison, WI.

7- Blake G.R., and Hartge K.H. 1986. Particle Density. p. 377-382. In: Klute, A. (ed). Methods of Soil Analysis. Part 1. 2nd ed. Agronomy. Monograph. 9. ASA, Madison, WI

8- Busscher W.J. and Bauer P.J. 2003. Soil strength cotton growth and lint yield in a southeastern USA coastal loamy sand. Soil & Tillage Research. 56: 197-204.

9- Campanharo W.A., Sperandio H.V., Cecilio R.A., Hollanda M.P. and Guariz H.R. 2009. Variabilidade espacial da resistência a penetração do solo a penetração em areas sob cultivos puros e consorciados de cafe e eucalipto. Revista Brasileira de Agroecologia. 2: 2721-2724.

10- Campbell G.S. 1985. Soil Physics with Basic: Transport Models for Soil–Plant System. Elsevier. New York. 150 p.

11- Cunha J.P.A.R., Vieira L.B. and Magalhaes A.C. 2002. Resistência mecânica do solo à penetração sob diferentes densidades e teores de agua.. Engenharia na Agricultura. 1:1-7.

12- Emami H., Lakzian A., and Mohagerpour M. 2010. Study of the relationship between slope of retention curve and some physical properties of soil quality. Journal of Water and Soil. 24: 1027-1035. (In Persian)

13- Farahani E., Mosaddeghi M.R., and Mahboubi. A.A. 2012. Measuring the mechanical strength and hardsetting phenomenon in selected soils of Hamadan province. Journal of Science and Technology of Agriculture and Natural Resources, Water and Soil Science. 16: 181-194. (in Persian)

14- Gardner W.H. 1986. Water Content. p. 493-544. In: Klute, A. (ed). Methods of Soil Analysis. Part 1. 2nd ed. Agronomy. Monograph. 9. ASA, Madison, WI

15- Gee G.W. and Bauder J.W. 1986. Particle-size analysis. p. 383–411. In: Klute, A. (ed). Methods of Soil Analysis. Part 1. 2nd ed. Agronomy. Monograph. 9. ASA, Madison, WI

16- Ghaboussi J., Garrett J .H. and Wu X. 1991. Knowledge-based modeling of material behavior with neural networks. Journal of Engineering Mechanics. 117: 132-153.

17- Gomez J.A., Giraldez J.V., Pastor M. and Fereres E. 1999. Effects of tillage method on soil physical properties, infiltration, and yield in an olive orchard. Soil & Tillage Research. 52:167-175.

18- Grunwald S., Rooney D.J., McSweeney K., and Lowery B. 2001. Development of pedotransfer functions for a profile cone penetrometer. Geoderma. 100: 25-47.

19- Gupta S.C., Schneider E.C., Larson W.E. and Hadas A. 1987. Influence of corn residue on compression and compaction behavior of soils. Soil Science Society of America Journal. 51: 207-212.

20- Jorreh M., Bayat h., Safari Sinejani A.A., and Davatgar N. 2012. Estimation of soil penetration resistance using fractal parameters of particle and aggregate size distributions. Journal of Water and Soil. 23: 13-27. (in Persian)

21- Kozak E., Pachepsky Y.A., Sokolowski S., Sokolowska Z. and Stepniewski W. 1996. A modified number-based method for estimating fragmentation fractal dimensions of soils. Soil Science Society of America Journal. 60: 1291- 1297.

22- Kushwaha P.L. and Zhang Z.X. 1998. Evaluation of factors and current approaches related to computerized design of tillage tools: a review. Journal of Terramechanics. 35:69-86.

23- Laboski C.A.M., Dowdy R.H. Allmaras R.P., and Lamb J.A. 1998. Soil strength and water content influence on corn root distribution in a sandy soil. Plant and Soil. 203: 239-247.

24- Marshall T.J., Holmes J.W., and Rose C.W. 1996. Soil Physics. 3rd ed. Cambridge, Cambridge University Press.

25- Mesri Gundoshmian T., Ghasemzadeh H.R., Abdollahpour S.H., Navid H., and Sahraeian H., 2009. Determining appropriate neural network model for predicting quantitative grain loss of combine harvester lexion 510. Agriculture Science. 20: 211-220. (in Persian)

26- Minasny B., Hopman J.W., Harter T.X., Eching T., Toli A. and Denton M.A. 2004. Neural networks prediction of soil hydraulic functions for alluvial soils using multi step outflow data. Soil Science Society of America Journal. 68: 417- 429.

27- Mosaddeghi M.R., Hajabbasi M.A. and Khademi H. 2006. Tensile strength of sand, palygorskite and calcium carbonate mixtures and interpretation with the effective stress theory. Geoderma 134: 160–170.

28- Mosaddeghi M.R., Hemmat M.A. Hajabbasi M.A. Vafaeian M. and Alexandrou A. 2006. Plate Sink age versus confined compression tests for in situ soil compressibility studies. Biosystem Engineering. 93: 325–334.

29- Mullins CE., Young I.M., Bengough A.G., and Ley G.J. 1987. Hard-setting soils. Soil Use Managment. 3:79–83.

30- Ohu J.O., Ekwue E. and Folorunse O.A. 1994. The effect of addition of organic matter on the compaction of a vertisol from Northern Nigeria. Soil Technology. 7: 155-162

31- Page A.L. (ed.).1985. Methods of Soil Analysis. Part 2. Chemical and Microbiological Methods. Agronomy No. 9. American Society of Agronomy, Madison, WI.

32- Puppala A.J., Acar Y.B. and Tumay M.T. 1995. Cone penetration in very weakly cemented sand. Journal of Geotechnical and Geoenvironmental Engineering. 121: 589-600.

33- Rezaei A., and Soltani A. 2008. Introduction to Applied Regression Analysis. Isfahan University Press. (in Persion)

34- Santos F.L., De Jesus V.A.M. and Valente D.S.M. 2012. Modeling of soil penetration resistance using statistical analyses and artificial neural networks. Acta Scientiarum. Agronomy. 34: 219-224.

35- Vaz C.M.P., Manieri J.M., de Maria I.C. and Tuller M. 2011. Modeling and correction of soil penetration resistance for varying soil water content. Geoderma. 166: 92-101.

36- Vaz, C.M.P., Luis H.B. and Hopmans J.W. 2001. Contribution of water content and bulk density to field soil penetration resistance as measured by a combined cone penetrometer-TDR probe. Soil & Tillage Research. 60: 35-42.

37- Walkley A.J. and Black I.A. 1934 Estimation of soil organic carbon by the chromic acid titration method. Soil Science. 37: 29-38.

38- Zareh haghi D., Neyshabouri M.R., Gorji M., Monirifar H., and Shorafa M. 2011. Determination of non-limiting water range for seedling growth of Pistachio at two levels of soil compaction. Water and Soil Sience. 22: 61-71. (in Persian)