نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانش آموخته دکتری گروه علوم خاک، دانشگاه علوم کشاورزی و منابع طبیعی گرگان

2 استاد گروه علوم خاک، دانشگاه علوم کشاورزی و منابع طبیعی گرگان

3 استادیار موسسه تحقیقات خاک و آب کرج

4 استادیار گروه علوم جنگل، دانشگاه علوم کشاورزی و منابع طبیعی گرگان

چکیده

روش‌های نقشه‌برداری رقومی خاک نیازمند داده‌های کمی برای تخمین هستند که به‌کارگیری آن‌ها در مناطق با تعداد داده خاک کم، و عدم دسترسی مناسب بسیار سخت می‌باشد. انجام عملیات میدانی به‌ویژه در سطح وسیع کاری زمان‌بر و همراه با هزینه زیاد است که عملیات نقشه‌برداری را مشکل‌ساز می‌نماید. از دیگر سو، باور در نقشه‌برداری رقومی بر این است که وجود یک خاک منحصر به فرد در منطقه وابستگی زیادی به متغیرهای محیطی آن منطقه و شناسایی دقیق آن‌ها دارد. در این مطالعه از الگوریتم جنگل تصادفی (RF) به همراه اطلاعات طبقه‌بندی 64 خاکرخ و 19 متغیر محیطی، شامل خصوصیات توپوگرافی، واحدهای ژئومورفولوژی، کاربری اراضی و شاخص پوشش گیاهی، برای تهیه نقشه کلاس خاک در بخشی از فلات لسی استان گلستان استفاده گردید. ژئومورفولوژی، ارتفاع، جهت شیب و کاربری اراضی تقریبا در همه سطوح رده‌بندی دارای بیش‌ترین اهمیت در تخمین کلاس‌های خاک بودند. نتایج ارزیابی دقت الگوریتم RF با متغیرهای ورودی مختلف نشان داد شاخص‌های صحت مدل از جمله صحت کلی و کاپا به ترتیب از 91/0 و 83/0 برای گروه بزرگ، به 78/0 و 56/0 برای زیرگروه، و 50/0 و 32/0 برای فامیل کاهش می‌یابد. کم‌ترین و بیش‌ترین مقدار خطای تخمین نمونه‌های اعتبارسنجی در مدل‌سازی 69/32 و 38/65 درصد به ترتیب برای سطح گروه بزرگ و فامیل خاک دست آمد و کلاس‌های دارای تعداد نمونه بیش‌تر، خطای کم‌تری داشتند. مطالعه حاضر نشان داد که در مناطق با محدودیت داده از ایران، نقشه‌برداری رقومی خاک، استفاده از متغیرهای محیطی با دقت بالا همراه با تعداد نمونه خاک کم می‌تواند نتایج مطلوبی را در سطوح بالای رده‌بندی ارائه دهد.

کلیدواژه‌ها

عنوان مقاله [English]

Evaluation of Accuracy of Digital Soil Mapping with Limited Data in a Part of Loess Plateau, Golestan Province

نویسندگان [English]

  • Sedigheh Maleki 1
  • Farhad Khormali 2
  • Mohsen Bagheri Bodaghabadi 3
  • Jahangir Mohammadi 4

1 PhD student, Department of Soil Science, Faculty of Water and Soil Engineering, Gorgan University of Agricultural Sciences and Natural Resources, Gorgan, Iran

2 Professor, Department of Soil Science, Faculty of Water and Soil Engineering, Gorgan University of Agricultural Sciences and Natural Resources, Gorgan, Iran

3 Assistant Professor, Soil and Water Research Institute, Karaj, Iran

4 Assistant Professor, Department of Forestry Science, Gorgan University of Agricultural Sciences and Natural Resources, Gorgan, Iran

چکیده [English]

Abstract
Digital soil mapping approaches that require quantitative data for prediction are difficult to implement in countries with limited data on soil and auxiliary variables. Extensive field sampling is very labor intensive and costly that is problematic for mapping missions. On the other side, it is believed in digital soil mapping approaches that unique soil conditions (soil types or soil properties) can be associated with unique combination and configuration of environmental variables. In this study we used a Random Forest (RF) algorithm combined with classification information of 64 soil profiles and 19 environmental variables (including terrain attribute, geomorphology units, land use and vegetation cover index) to map soil classes in the part of loess plateau, Golestan Province Iran. Geomorphology, elevation, slope aspect and land use were the most important parameters in prediction of soil map in different taxonomic level. The results of accuracy assessment of RF with different entrance variables revealed that accuracy of model including overall accuracy and kappa index respectively decreased of 0.91 and 0.83 for great group, 0.78 and 0.56 for subgroup, 0.50 and 0.32 for family. The minimum and maximum Out of bag (OOB) estimate error rate in modeling were 32.69% and 65.38% for great group and soil family, respectively and the soil classes with higher frequency had the lower OOB error. The present study showed that in regions of Iran with limited data, digital soil mapping and high resolution ancillary data with smaller sample size can be led to an effective result in higher taxonomic levels. 

کلیدواژه‌ها [English]

  • Environmental variables
  • Limited data
  • Map accuracy
  • Random forest
References
Abbaszadeh Afshar F., Ayoubi Sh., and Jafari A. 2018. The extrapolation of soil great groups using multinomial logistic regression at regional scale in arid regions of Iran. Geoderma, 315: 36–48.
Bagheri Bodaghabadi M., Esfandiarpoor Borujeni I., Salehi M.H., Mohammadi J., and Toomanian N. 2015. Assessment of the expert knowledge’s effect in digital soil mapping and soil sampling. 14th Congress of Soil Science, Rafsanjani University, Iran. (In Persian)
Banaei M.H. 2000. The map of resources and land capability of Iran soils. Soil and Water Research Institute, Karaj, Iran. (In Persian)
Behrens T., Förster H., Scholten T., Steinrücken U., Spies E.D., and Goldschmitt M. 2005. Digital soil mapping using artificial neural networks. Journal of Plant Nutrition and Soil Science, 168(1): 21-33.
Breiman L. 2001. Random forests. Machine Learning, 45(1): 5-32.
Breiman L., and Cutler A. 2004. Random Forests homepage. Retrieved April 23rd.
Brungard C.W. 2009. Alternative sampling and analysis methods for digital soil mapping in southwestern Utah. Thesis for Master of Science, Utah State University, USA, 284p.
Brungard C.W., Boettinger J.L., Duniway M.C., Wills S.A., and Edwards Jr T.C. 2015. Machine learning for predicting soil classes in three semi-arid landscapes. Geoderma, 239-240: 68-83.
Brus D.J., Kempen B., and Heuvelink G.B.M. 2011. Sampling for validation of digital soil maps. European Journal of Soil Science, 62: 394–407.
Frechen M., Kehl M., Rolf C., Sarvati R., and Skowronek, A. 2009: Loess chronology of the Caspian Lowland in Northern Iran. Quaternary International, 128(1-2): 220-233.
Gallant J.C., and Dowling T.I. 2003. A multi resolution index of valley bottom flatness for mapping depositional areas. Water Resources Research, 39: 1347-1360.
Häring T., Dietz E., Osenstetter S., Koschitzki T., and Schröder B. 2012. Spatial disaggregation of complex soil map units: a decision-tree based approach in Bavarian forest soils. Geoderma, 185–186: 37–47.
Hengl T., Heuvelink G.B.M., and Stein A. 2004. A generic framework for spatial prediction of soil variables based on regression-kriging. Geoderma, 120(1-2): 75-93.
Hengl T., Toomanian N., Reuter H., and Malakouti, M.J. 2007. Methods to interpolate soil categorical variables from profile observations: Lessons from Iran. Geoderma, 140: 417-427.
Huete A.R. 1988. A soil adjusted vegetation index (SAVI). Remote Sensing of Environment, 25: 295–309.
Jafari A., Ayoubi S., Khademi H., Finke P.A., and Toomanian N. 2013. Selection of a taxonomic level for soil mapping using diversity and map purity indices: A case study from an Iranian arid region. Geomorphology, No of Pages 12.
Kehl M., Sarvati R., Ahmadi H., Frechen M., and Skowronek A. 2005. Loess paleosol-sequences along a climatic gradient in Northern Iran. Eiszeitalter u. Gegenwart, 55: 149-173.
Kempen B., Brus D.J., Heuvlink G.B.M., and Stoorvogel J.J. 2009. Updating the 1:50000 Dutch soil map using legacy soil data: A multinomial logistic regression approach. Geoderma, 151: 311-326.
Khormali F., and Kehl M. 2011. Micromorphology and development of loess-derived surface and buried soils along a precipitation gradient in Northern Iran. Quaternary International, 234: 109–123.
MathWorks. 2009. Matlab. The Math Works., Inc., Natick, MA.
Maleki S., Khormali F., Bagheri Bodaghabadi M., Mohammadi J., Kehl M., Hoffmeister D., Ghaffary M. 2017. Using Unmanned Aerial Vehicle in future studies of digital soil mapping? Accuracy, coverage and the effects on preparing of geomorphology map. 15th Soil Congress, University of Isfahan, Iran. (In Persian)
Marchetti A., Piccini C., Santucci S., Chiuchiarelli I., and Francaviglia R. 2011. Simulation of soil types in Teramo province (central Italy) with terrain parameters and remote sensing data. Catena, 85: 267-273.
McBratney A.B., Mendonc Santos M.L., and Minasny B. 2003.On digital soil mapping. Geoderma, 117: 3-52.
Mirakzehi K.h., Pahlavan-Rad M.R., Shahriari, A., and Bameri, A. 2018. Digital soil mapping of deltaic soils: A case of study from Hirmand (Helmand) river delta. Geoderma, 313: 233–240.
Minasny B. and McBratney A.B. 2006. A conditioned Latin hypercube method for sampling in the presence of ancillary information. Computers & Geosciences, 32: 1378–1388.
Myles A.J., Feudale R.N., Liu Y., Woody N.A., and Brown S.D. 2004. An introduction to decision tree modeling. Journal of Chemometrics, 18(6): 275–285.
Pahlavan Rad M.R., Toomanian N., Khormali F., Brungard C.W., Komaki C.B., and Bogaert P. 2014. Updating soil survey maps using random forest and conditioned Latin hypercube sampling in the loess derived soils of northern Iran. Geoderma, 232–234: 97–106.
Pahlavan-Rad M.R., Khormali F., Toomanian N., Brungard C.W., Kiani F., and Komaki C.B., Bogaert P. 2016. Legacy soil maps as a covariate in digital soil mapping: A case study from Northern Iran. Geoderma, 279: 141–148.
R Development Core Team. 2013. R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria. Retrieved from http://www.R-project.org.
Sreenivas K., Dadhwal V.K., Kumar S., Harsha G.S., Mitran T., Sujatha G., Janaki Rama Suresh G., Fyzee M.A., and Ravisankar T. 2016. Digital mapping of soil organic and inorganic carbon status in India. Geoderma, 269: 160-173.
Stoorvogel J.J., Kempen B., Heuvelink G.B.M., and  Bruin S. 2009. Implementation and evaluation of existing knowledge for digital soil mapping in Senegal. Geoderma, 149: 161–170.
Stum A.K., Boettinger J.L., White M.A., and Ramsey R.D. 2010. Random Forests applied as a soil spatialpredictive model in arid Utah, P 179-189. In: Boettinger J.L., Howell D., Moore W, A.C., Hartemink A., Kienast-Brown E.S. (Ed.), Digital Soil Mapping: Bridging Research, Environmental Application, and Operation. Progress in Soil Science. Springer, Logan, USA.
Soil Survey Staff. 1996. Soil survey laboratory methods manual. Report No. 42, USDA, NRCS, NCSS.
Soil Survey Staff. 2014. Keys to Soil Taxonomy (12th Ed.), U.S. Department of Agriculture, Natural Resources Conservation Service. 372p.
Taghizadeh-Mehrjardi R., Minasny B., Sarmadianc F., and Malone B.P. 2014. Digital mapping of soil salinity in Ardakan region, central Iran. Geoderma, 213: 15–28.
Tajik S., Ayoubi S., and Nourbakhsh F. 2012. Prediction of soil enzymes activity by digital terrain analysis: comparing artificial neural network and multiple linear regression models. Environmental Engineering Science, 29(8): 798-806.
Teng H., Viscarra Rossel R.A., Shi Zh., and Behrens Th. 2018. Updating a national soil classification with spectroscopic predictions and digital soil mapping. Catena, 164: 125-134.
Toomanian N., Jalalian A., Khademi H., Karimian Eghbal M., and Papritz A. 2006. Pedodiversity and pedogenesis in Zayandeh-rud Valley, Central Iran. Geomorphology, 81: 376–393.
Wang X., Wei H., Khormali F., Taheri M., Kehl M., Frechen M., Lauer M., and Chen M. 2016. Grain-size distribution of Pleistocene loess deposits in northern Iran and its palaeoclimatic implications. Quaternary International, 1-11.
Wang Sh., Jin X., Adhikari K., Li W., Yu M., Bian Zh., and Wang Q. 2018. Mapping total soil nitrogen from a site in northeastern China. Catena, 166: 134-146.
Weiss A.D. 2001. Topographic position and landforms analysis. Proceedings of the ESRI User Conference, 9–13 July, San Diego, CA, USA.
Wilson J.P., and Gallant J.C. 2000. Terrain analysis. Wiley & Sons, New York.
Zeraatpisheh M., Ayoubi Sh., Jafari A., and Finke P. 2017. Comparing the efficiency of digital and conventional soil mapping to predict soil types in a semi-arid region in Iran. Geomorphology, 285: 186–204.
Zhu A.X., Yang L., Li B., Qin Ch., English E., Burt J.E., and Zhou Ch. 2008. Purposive Sampling for Digital Soil Mapping for Areas with Limited Data. In: Digital Soil Mapping with Limited Data, Part 12. Springer Science, pp. 223- 245.