نقشه برداری رقومی بافت خاک با استفاده از رگرسیون درختی و شبکه عصبی مصنوعی در منطقه بیجار کردستان

نوع مقاله : مقالات پژوهشی

نویسندگان

• کمال نبی اللهی ¹
• احمد حیدری ²
• روح الله تقی زاده مهرجردی ³

¹ دانشگاه کردستان

² دانشگاه تهران

³ دانشگاه اردکان

https://doi.org/10.22067/jsw.v0i0.28735

چکیده

در مطالعه حاضر جهت پهنه بندی رقومی کلاس های بافتی خاک در منطقه بیجار کردستان، 103 پروفیل حفر، تشریح و از افق های سطحی A نمونه برداری شد. متغیرهای محیطی یا فاکتورهای خاک سازی که در این پژوهش استفاده شد شامل اجزاء سرزمین، داده های تصویر +ETM ماهواره لندست و نقشه سطوح ژئومورفولوژی می باشد. همچنین، جهت ارتباط دادن بین داده های خاک (رس، شن و سیلت) و متغیرهای کمکی از مدل های شبکه عصبی مصنوعی و رگرسیون درختی بهره گرفته شد. نتایج این تحقیق نشان داد که مدل رگرسیون درختی دارای دقت بیشتری نسبت به شبکه عصبی مصنوعی به منظور پیش بینی هر سه پارامتر رس، شن و سیلت می باشد. برای جزء رس، مدل رگرسیون درختی و شبکه عصبی مصنوعی دارای ضریب تبیین و میانگین ریشه مربعات خطا 46/0، 81/0 و 10/17، 50/12 براساس داده های آزمون (20درصد) می باشد. نتایج نشان داد که برای پیش بینی رس، شن و سیلت پارامترهای سطوح ژئومورفولوژی، شاخص خیسی، شاخص همواری دره با درجه تفکیک بالا، ارتفاع، طول شیب و باند 3 مهم‌ترین بوده اند. در کل نتایج نشان داد که مدل های درختی دارای دقت بالاتری نسبت به روش شبکه عصبی مصنوعی بوده و همچنین تفسیر نتایج مدل درختی بسیار راحت تر می باشد. لذا پیشنهاد می شود که جهت تهیه نقشه رقومی خاک از مدل های درختی در مطالعات آینده استفاده شود.

کلیدواژه‌ها

• متغیرهای محیطی
• تغییرات مکانی
• نقشه برداری رقومی

20.1001.1.20084757.1394.28.5.15.3

عنوان مقاله [English]

Digital Mapping of Soil Texture Using Regression Tree and Artificial Neural Network in Bijar, Kurdistan

نویسندگان [English]

• kamal nabiollahi ¹
• ahmad haidari ²
• rohollah taghizade mehrjardi ³

¹

² tehran university

³ University of Ardakan

چکیده [English]

Soil texture is an important soil physical property that governs most physical, chemical, biological, and hydrological processes in soils. Detailed information on soil texture variability is crucial for proper crop and land management and environmental studies. Therefore, at present research, 103 soil profiles were dogged and then sampled in order to prepare digital map of soil texture in Bijar, Kurdistan. Auxiliary data used in this study to represent predictive soil forming factors were terrain attributes, Landsat 7 ETM+ data and a geomorphologic surfaces map. To make a relationship between the soil data set (i.e. Clay, sand and silt) and auxiliary data, regression tree (RT) and artificial neural network (ANN) were applied. Results showed that the RT had the higher accuracy than ANN for spatial prediction of three parameters. For the clay fraction, determination of coefficient (R2) and root mean square root (RMSE) calculated for two models were 0.46, 0.81 and 17.10, 12.50, based on validation data set (20%). Our results showed some auxiliary variables had more influence on predictive soil class model which included: geomorphology map, wetness index, multi-resolution index of valley bottom flatness, elevation, slope length, and B3. In general, results showed that decision tree models had higher accuracy than ANN models and also their results are more convenient for interpretation. Therefore, it is suggested using of decision tree models for spatial prediction of soil properties in future studies.

کلیدواژه‌ها [English]

• Auxiliary data
• Spatial variation
• Digital soil mapping

مراجع

1- Bell J.C., Cunningham R.L., and Havens M.W. 1992. Calibration and validation of a soil- landscape model for predicting soil drainage class. SSSJA, 56: 1860–1866.

2- Bie S.W., and Beckett P.H.T. 1971. Quality control in soil survey. II: The cost of soil survey. J. Soil Sci, 22: 453–465.

3- Breiman L., Friedman J.H., Olshen R.A., and Stone C.J. 1984. Classification and regression. Tress. Wadsworth, Belmont, CA.

4- Bui E.N., Loughhead A., and Corner R. 1999. Extracting soil-landscape rules from soil previous surveys. Aus. J. Soil Res, 37: 495-508.

5- Bui E.N., and Moran C.J. 2001. Disaggregation of polygons of surficial geology and soil maps using spatial modelling and legacy data. Geoderma. 103, 79– 94.

6- Cassel D.K., Wendroth O., and Nielsen D.R., 2000. Assessing spatial variability in an agricultural experiment station field, opportunities arising from spatial dependence. Agron. J, 92: 706–714.

7- Cerri C.E.P., Coleman K., Jenkinson D.S., Bernoux M., Victoria R., and Cerri C.C. 2003. Modeling soil carbon from forest and pasture ecosystems of Amazon, Brazil. SSSJA, 67: 1879–1887.

8- Fernndez-Glvez J., Simmonds L.P., and Barahona E. 2005. Estimating detailed soil water profile records from point measurements. E. J. Soil Sci, 57: 23-45.

9- Florinsky I.V., Eilers R.G., Manning G.R., and Fuller L.G. 2002. Prediction of soil properties by digital terrain modeling. Env. Model. Soft, 17: 295– 311.

10- Gee G.W., and Bauder J.W. 1986. Particle size analysis. p. 383-411. In: A. Klute. (ed). Methods of Soil Analysis. Part 1. A. Soc. Ag. Madison, WI.

11- Hassink J. 1992. Effects of soil texture and structure on carbonand nitrogen mineralization in grass-land soils. Biol. Fertil. Soils, 14: 126–134.

12- Henderson B.L., Bui E.N., Moran C.J., and Simon D.A.P. 2005. Australia-wide predictions of soil properties using decision trees. Geoderma. 124, 383-398.

13- Hengl T., Rossiter D.G., and Stein A. 2003. Soil sampling strategies for spatial prediction by correlation with auxiliary maps. Geoderma, 120: 75–93.

14- Jafari A., Finke P.A., de Wauw J.V., Ayoubi S., and Khademi H. 2012. Spatial prediction of USDA- great soil groups in the arid Zarand region, Iran: comparing logistic regression approaches to predict diagnostic horizons and soil types. E. J. Soil Sci, 63: 284–298.

15- Jain M.K., Kothyari U.C., and Raju K.G.R. 2005. GIS based distributed model for soil erosion and rate of sediment outflow from Catchments. J. Hydraulic Eng, 13:755–769.

16- Kheir B., Greve M.H., Bocher P.K., Greve M.B., Larsen R., and McCloy K. 2010. Predictive mapping of soil organic carbon in wet cultivated lands using classification-tree based models: The case study of Denmark. J. Env. Man, 91: 1150-1160.

17- Kheir R.B., Greve M.H., Abdallah C., and Dalgaard T. 2010. Spatial soil zinc content distribution from terrain parameters: A GIS-based decision-tree model in Lebanon. Environ. Poll, 158: 520–528.

18- Luoto M., and Hjort J. 2005. Evaluation of current statistical approaches for predictive geomorphological mapping. Geomorph, 67, 299-315.

19- Malone B.P., McBratney A.B., Minasny B., and Laslett G.M. 2009. Mapping continuous depth functions of soil carbon storage and available water capacity. Geoderma, 154: 138– 152.

20- McBratney A.B., Odeh I.O.A., Bishop T.F.A., Dunbar M.S., and Shatar T.M. 2000. An overview of pedometric techniques for use in soil survey. Geoderma, 97: 293–327.

21- McBratney A.B., Santos M.L.M., and Minasny B. 2003. On digital soil mapping. Geoderma, 117: 3–52.

22- Mendonça-Santos M.L., McBratney A.B., and Minasny B. 2006. Soil prediction with spatially decomposed environmental factors. Digital Soil Mapping — An Introductory Perspective, 31: 269–278.

23- Minasny B., and McBratney A.B. 2007. Incorporating taxonomic distance into spatial prediction and digital mapping of soil classes. Geoderma, 142: 285–293.

24- Moonjun R., Farshad A., Shrestha D.P., and Vaiphasa C. 2010. Artificial Neural Network and Decision Tree in Predictive Soil Mapping of Hoi NumRin Sub-Watershed, Thailand. Digital Soil Mapping. Pro. Soil Sci, 2, pp 151-164.

25- Moore I.D., Grayson R.B., and Ladson A.R. 1991. Digital terrain modeling: review of hydrological, geomorphological and biological applications. Hyd. Proc, 5: 3-30.

26- Moran C.J., and Bui E.N. 2002. Spatial data mining for enhanced soil map modelling. I. J. Geog. Info. Sci, 16: 533-549.

27- Oberthur T., Dobermann A., and Neue H.U. 1996. How good is a reconnaissance soil map for agronomic purposes? Soil Use Manage, 12: 33–43.

28- Quinlan J.R. 2001. Cubist: An Informal Tutorial. Available at http://www.rulequest.com.

29- Rossiter D.G., and Hengl T. 2001. Technical note: Creating geometrically-correct photo- interpretation, photo-mosaics, and base maps for a projects GIS. Available at http://www.itc.nl/rossiter.

30- Ryan P.J., McKenzie N.J., O'Connell D., Loughhead A.N., Leppert P.M., Jacquier D., and Ashton L. 2000. Integrating forest soils information across scales: spatial prediction of soil properties under Australian forests. For. Eco. Manag, 138:139–157.

31- Scull P., Franklin J., and Chadwick O.A. 2005. The application of classification of tree analysis to soil type prediction in a desert landscape. Eco. Model, 181: 1-15.

32- Taghizadeh-Mehrjardi R., Minasny B., Sarmadian F., and Malone, P.B. 2013. Digital mapping of soil salinity in Ardakan region, central Iran. Geoderma, 213: 15-28.

33- Thattai D., and Islam S. 2000. Spatial analysis of remotely sensed soil moisture data. J. Hydrol. Eng, 5: 386–392.

34- Ungaro F., Ragazzi F., Cappellin R., and Giandon P. 2008. Arsenic concentration in the soils of the Brenta Plain (Northern Italy): Mapping the probability of exceeding contamination thresholds. J. Geo. Explo, 96: 117-131.

35- Voltz M., and Webster R. 1990. A comparison of kriging, cubic-splines and classification for predicting soil properties from sample information. J. Soil Sci, 41: 473–490.

36- Voltz M., Lagacherie P., and Louchart X. 1997. Predicting soil properties over a region using sample information from a mapped reference area. Eur. J. Soil Sci, 48: 19–30.

37- Webster R. 1968. Fundamental objection to the 7thapproximation. J. Soil Sci, 19: 354–365.

38- Wischmeier W.H., and Smith D.D. 1978. Predicting Rainfall Erosion Losses, a Guide to Conservation Planning, Agriculture Handbook No. 537. U.S. Department of Agriculture, Washington, DC.

39- Zhao Z., Chow T.L., Rees H.W., Yang Q., Xing Z., and Meng F. 2009. Predict soil texture distributions using an artificial neural network model. Com. Elec. Agr, 65: 36-48.

40- Zinck J.A. 1989. Physiography and soils. Lecture notes for K6 course. Soils Division, pp. 156, ITC, Enschede, The Netherlands.