تخمین شاخص کیفیت فیزیکی خاک و عدم قطعیت با به کارگیری شبکه عصبی مصنوعی بوت استرپ

نوع مقاله: مقاله پژوهشی

نویسندگان

1 دانشجوی دکتری، گروه علوم خاک، دانشکده کشاورزی دانشگاه تبریز

2 استاد گروه خاکشناسی، دانشکده کشاورزی، دانشگاه تبریز

3 دانشیار گروه مهندسی آب، دانشکده کشاورزی، دانشگاه تبریز

4 دانشیار گروه خاکشناسی، دانشکده کشاورزی، دانشگاه تبریز

5 استادیار گروه جغرافیای طبیعی،دانشکده جغرافیا و برنامه ریزی، دانشگاه تبریز

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Estimation of soil quality indices and its uncertainty using Bootstrap-based Artificial Neural Networks (BANNs)

نویسندگان [English]

  • M Sabri 1
  • MR Neyishabouri 2
  • MA Ghorbani 3
  • F Shahbazi 4
  • K Valizadeh 5
چکیده [English]

In this study the slope of soil water retention curve at its inflection point(Si) as a soil physical
quality index and its correlation with soil convenient properties and with information on vegetation
cover from satellite images(SAVI) and digital elevation model (DEM) were studied. For this
purpose, 176 disturbed and undisturbed soil samples were collected from East Azarbaijan and Gilan
provinces. The test sites were chosen as such to provide wide variety in terrain, land use
characteristics, vegetation, soil types and soil distribution patterns. Particle size distribution, total
porosity, bulk density, organic matter, EC, pH, CCE, mean weight diameter(MWD), geometric mean
and standard deviation of particle diameter, water content at -30 kPa, DEM and SAVI were used as
pedotransfer function (PTFs) inputs. Since reliable hydrologic prediction is essential for planning,
developing and rational management of the soils, therefore, in this study the uncertainty involved in
Si prediction using artificial neural network (ANN) models was quantified. The uncertainty
associated with Si was investigated using the bootstrap based artificial neural networks (BANNs).
The performance of PTFs was evaluated using the root mean square error (RMSE) between the
observed and the predicted values and the Morgan-granger-newbold test ( MGN). Although
variability exists within bootstrapped replications, improvements were achieved with certain input
combinations of basic soil properties, topography and vegetation information compared with using
only the basic soil properties as inputs.

کلیدواژه‌ها [English]

  • Artificial Neural Networks
  • Bootstrap based ANN
  • Si Index
  • remote sensing
  • uncertainty
منابع مورد استفاده
امامی ح، شرفاء م، نیشابوری م­ر و  لیاقت ع­ا ، 1387 .برآورد شاخص کیفیت فیزیکی  خاک با استفاده از ویژگی های زود  یافت خاک در تعدادی از خاکهای شور وآهکی. علوم کشاورزی ایران (مجله تحقیقات آب و خاک ایران(، دوره 39، شماره1، صفحه­های 39 تا46.
پرویز ل، خلقی م، ولی زاده خ، عراقی نژاد ش و ایران نژاد پ، 1389. ارزیابی کارآیی شاخص تفاضل نرمال شده پوشش گیاهی از طریق پایش وضعیت پوشش گیاهی. صفحه­های 432 تا441. مجموعه مقالات همایش ملی ژئوماتیک.1-2 اردیبهشت ماه، سازمان نقشه برداری کشور، تهران.
ﻋﻠــﻮی ﭘﻨــﺎه  س­ک ، 1382. ﻛــﺎرﺑﺮد ﺳــﻨﺠﺶ از دور در ﻋﻠــﻮم زﻣﻴﻦ(ﻋﻠﻮم ﺧﺎک) . ﻣﺆﺳﺴﻪ اﻧﺘﺸﺎرات و ﭼﺎپ داﻧﺸﮕﺎه ﺗﻬﺮان،
صفحه­های45 تا46 .
Bates BC and Townley LR, 1988. Nonlinear, discrete flood event models: 3. Analysis of prediction. Uncertainty.J Hydrol. 99: 91–101.
Bayat H, Neyshabouri MR, Mohammadi K and Nariman-Zadeh N, 2011. Estimating water retention with pedotransfer functions using multi-objective group method of data handling and ANNs. Pedosphere 21: 107-114.
Blak GR and Hartge KH, 2002 .Bulk density. Pp. 809-812. In: Dan JH and Topp GC (eds) Methods of Soil
Analysis. Part 4. Physical Methods. ASA and SSSA, Madison WI.
Dane JH and Hopmans JW, 2002. Pressure plate extractor. Pp.688-690. In: Dan J H and Topp GC (eds) Methods of Soil Analysis. Part 4. Physical Method. ASA and SSSA, Madison WI.
Diebold FX and Mariano RS, 1995. Comparing Predictive Accuracy. J. Bus and Econ. Stat 13: 253 –263.
Dexter AR, 2004. Soil physical quality. Part I: Theory, effects of soil texture, density, and organic matter,
and effects on root growth. Geoderma 120: 201-214.
Efron B and Tibshirani RJ, 1993. An Introduction to the Bootstrap. Chapman and Hall, London, UK.
Emerson WW and Greenland DJ, 1990. Soil aggregates-formation and stability. Pp. 485-511. In: De Boodt
MF, Hayes MHB and Herbillon A (eds). Soil Colloids and Their Associations in Aggregates. Plenum Press, New York.
Franklin J, Mccullough P and Gray C, 2000.Terrain variables used for predictive mapping of vegetation communities in Southern California. Pp331-354. In: Wilson JP and Gallant JC (eds) Terrain Analysis: Principles and Applications. John Wiley and Sons. New York.
Gee GW and Bauder JW, 1986. Particle - size analysis. Pp. 383–411. In: Klute A (ed) Methods of Soil Analysis Part 1. 2nd ed. Physical and Mineralogical Methods. ASA and SSSA, Madison, WI.
Guerif J, Richard G, Durr C, Machet JM, Recous S and Rogrerestrade J, 2001. A review of tillage effects on cr­op residue management, seedbed conditions and seedling establishment. Soil Tillage Res 61: 13-32.
Leij FJ, Romano N, Palladino M and Schaap MG, 2004. Topographical attributes to predict soil hydraulic
properties along a hillslope transect. Water Resour Res 40: 1–15.
Nelson RE, 1982. Carbonate and gypsum. Pp. 181-197. In Page AL(ed) Methods of Soil Analysis. Part 2.2nd ed .Agron. Monogr. 9. ASA and SSSA, Madison, WI.
Pachepsky YA, Timlin DJ and Rawls WJ, 2001. Soil water retention as related to topographic variables. Soil Sci Soc Am J 65: 1787– 1795.
Romano N, Hopmans JW and Dane JH, 2002. Suction table.Pp.692-698. In: Dan JH and Topp GC (eds) Methods of Soil Analysis. Part 4. Physical Methods. ASA and SSSA, Madison WI.
Sharma SK, Mohanty BP, Zhu J, 2006. Including topography and vegetation attributes for developing pedotransfer functions in southern great plains of USA. Soil Sci Soc Am J 70: 1430–1440.
Shirazi MAand Boresma L, 1984. A unifying quantitative of soil texture. Soil Sci Soc Am J 48: 142- 147.
Shukla MK, Lal R and Ebinger M, 2006. Determining soil quality indicators by factor analysis. Soil Tillage
Res 87(2): 194-204.
Stuart G, Bienenstock E and Doursat R, 1992. Neural networks and the bias/variance dilemma .NC 4:1-58.
Twomey JM and Smith AE, 1998. Bias and variance of validation methods for function approximation neural networks under conditions of sparse data. IEEE Transactions on Systems, Man and Cybernetics C: Applications and Reviews 28(3): 417–430.
Van Genuchten MTh, Leij FJ and Yates SR, 1991. The RETC code for quantifying the hydraulic functions of unsaturated soils. Kerr S, Environmental Research Laboratory, Office of Research and Development, U.S. Environmental Protection Agency. Ada OK 74820.
Vereecken H, Maes J, Feyen J and Darius P, 1989. Estimating the soil moisture retention characteristics from texture, bulk density and carbon content. Soil Sci Soc Am J 148(6): 389-403.
Walkley A and Black IA, 1934. An examination of the Degtjareff method for determining soil organic matter and a proposed modification of the chromic acid titration method. Soil Sci 37: 29-39.
Yoder RE, 1936. A direct method of aggregate analysis and a study of a physical nature of erosion losses. J Am Agron 28: 337-351.
Zolfaghari Z, Mosaddeghi MR and Ayoubi S, 2015. ANN-based pedotransfer and soil spatial prediction functions for predicting Atterberg consistency limits and indices from easily available properties at watershed scale in western Iran. Soil Use Manag. doi: http://dx.doi.org/10.1111/sum.12167.