واسنجی دستگاه القاگر الکترومغناطیس به منظور برآورد تغییرات عمودی شوری خاک با استفاده از روش‌های فراکاوشی

نوع مقاله: مقاله پژوهشی

نویسندگان

1 استادیار دانشکده کشاورزی و منابع طبیعی، دانشگاه اردکان (مکاتبه کننده)

2 دانشجوی کارشناسی ارشد بیابان زدایی، دانشکده کشاورزی منابع طبیعی، دانشگاه اردکان

3 استاد مهندسی علوم خاک دانشگاه تهران

4 استادیار دانشکده کشاورزی و منابع طبیعی، دانشگاه اردکان

5 مربی مرکز ملی تحقیقات شوری

چکیده

شوری خاک یکی از مشکلات اساسی در مناطق خشک و نیمه­خشک می­باشد. بنابراین، تهیه و به روز رسانی نقشه­های شوری خاک جهت شناسایی مراحل اولیه شوری‌زائی خاک حائز اهمیت می­باشد. دستگاه القاگر الکترومغناطیس به­عنوان جایگزینی برای روش سنتی جهت ارزیابی سریع شوری خاک می­باشد. به­منظور واسنجی داده­های دستگاه القاگر الکترومغناطیس از روش­های مختلفی استفاده می­شود. این پژوهش به واسنجی دستگاه القاگر الکترومغناطیس مدل EM38 در یکی از باغات پسته در حاشیه شهرستان اردکان با استفاده از روش­های رگرسیون خطی چندگانه، شبکه عصبی مصنوعی و مدل نروفازی پرداخته است. نتایج نشان داد که مناسب­ترین روش برای واسنجی داده‌های قابلیت هدایت­الکتریکی این دستگاه، به­کارگیری مدل نروفازی برای تخمین شوری خاک در 9 عمق به­ترتیب از عمق اول تا عمق نهم با ضریب تبیین 06/0، 11/0، 30/0، 59/0، 69/0، 64/0، 70/0، 74/0 و 74/0  و با میانگین ریشه مربعات خطا به­ترتیب 09/4، 66/3، 87/2، 22/2، 26/2، 62/2، 46/2، 38/2 و 50/2 بود، که دقت آن نسبت به دو مدل دیگر در تخمین مقادیر شوری خاک و واسنجی دستگاه بالاتر بود.

کلیدواژه‌ها


عنوان مقاله [English]

Calibration of Electromagnetic Induction Device (EM38) in Order to Estimate Vertical Variation of Soil Salinity Using Machine Learning Techniques

نویسندگان [English]

  • Roh Allah Taghizadeh-Mehrjardi 1
  • Somayeh Asemani 2
  • Feridon Sarmadian 3
  • Mehdi Tazeh 4
  • Mohammad Hasan Rahimian 5
چکیده [English]

Soil salinity is a serious environmental problem especially in arid and semiarid areas. Therefore, it is vital to generate and update soil salinity maps in order to determine early stage of salinization. Electromagnetic induction instrument is an alternative to traditional methods for assessing soil salinity. Different methods have been used to calibrate electromagnetic induction instrument. At present research, an attempt was made to calibrate EM38 in pistachio orchard located in Ardakan city using multi-linear regression (MLR), artificial neural network (ANN) and neuro-fuzzy (ANFIS). To calibrate and predict soil salinity in nine standard depths, the best result was obtained by ANFIS model with R2 of 0.06, 0.11, 0.30, 0.59, 0.69, 0.64, 0.70, 0.74 and 0.74; and RMSE of 4.09, 3.66, 2.87, 2.22, 2.26, 2.62, 2.46, 2.38 and 2.50, respectively; which showed the accuracy of ANFIS was higher than other models (ANN and MLR) to predict soil salinity and calibrate EM38. 

کلیدواژه‌ها [English]

  • multi-linear regression
  • Apparent electrical conductivity
  • artificial neural network
  • neuro-fuzzy
References

Aali K., Parsinejan M., and Rahmani, B. 2009. Estimation of saturation percentage of soil using multiple regression, ANN, and ANFIS techniques. Computer and Information Science, 2: 127-136.

Amini M., Afyuni M., Fathianpour N., Khademi H., and Fluchler, H. 2005. Continuous soil pollution mapping using fuzzy logic and spatial interpolation. Geoderma, 124: 223-233.

Chio J., Teresa A., Bahia M., and Hussain, U. 2004. Pavement roughness modeling using back-propagation neural networks. Computer-Aided Civil and Infrastructure Engineering, 19: 295-303.

Drake J. 2000. Communications phase synchronization using the adaptive network fuzzy inference system. PhD. dissertation, New Mexico State University, Las Cruces, New Mexico, USA. 168p.

Feng Q., Zhu A., Harrower M., and Brut J.E. 2006. Fuzzy soil mapping based on prototype category theory. Geoderma, 136: 774-787.

Firat M., and Gungor M. 2007. River flow estimation using adaptive neuro-fuzzy inference system. Mathematics and Computers in Simulation, 75:87-96.

Jang J., Sun C. and Mizutani E. 1997. Neuro-fuzzy and soft computing: A computational approach to learning and machine intelligence. Prentice Hall, Upper Saddle River, New Jersey, USA. 640p.

Kisi O. 2005. Suspended sediment estimation using neuro-fuzzy and neural network approaches. Hydrological Sciences-Journal-des Sciences Hydrologiques, 50: 683-696.

Kosko B. 1992. Neural networks and fuzzy systems: Dynamical approach to machine intelligence. Prentice Hall, Englewood Cliffs, NJ. 449p.

Lesch S., Strauss D.J. and Rhoades J.D. 1995. Spatial prediction of soil salinity using electromagnetic induction techniques 1. Statistical prediction models. A comparison of multiple linear regression and cokriging. Water Resources Research, 31: 373-386.

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.

MATLAB User's Guide. 2006. Fuzzy logic Toolbox, by the math works Inc. 235p.

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: 85– 113.

Minansny B., McBratney A.B., and Bristow K.L. 1999. Comparison of different approaches to the development of pedotransfer functions for water retention curves. Geoderma, 93: 225-253.

Minasny B., and McBratney A.B. 2006. A conditioned Latin hypercube method for sampling in the presence of ancillary information. Geology, 32: 1378-1388.

Mohammadi J., and Taheri M. 2005. Estimation of pedotransfer function using fuzzy regression. Journal of Agriculture Science & Technology, 2: 51-60. (In Persian)

Mohammadi J. 2007. Testing an artificial neural network for predicting soil water retention characteristics from soil physical and chemical properties. 17th World Congress of Soil Science, Thailand, Paper No 221.

Nava P., and Taylor J. 1996. The optimization of neural network performance through incorporation of fuzzy theory. In: Proceedings of the Eleventh International Conference on Systems Engineering, 897-901.

Navabian M., Liaghat A., and Homaee M. 2003. Determination of soil saturated hydraulic conductivity using pedotransfer function. Agriculture Engineering, Research Journal, 4: 1-12. (In Persian)

Padhi J., and Misra R.K. 2011. Sensitivity of EM38 in determining soil water distribution in an irrigated wheat field. Soil and Tillage Research, 117: 93-102.

Rahimian M.H. and Hasheminejhad Y. 2010. Calibration of electromagnetic induction device (EM38) for soil salinity assessment. Journal of Water and Soil Sciences, 3: 243-252. (In Persian)

Rahimian M.H., Hasheminejhad Y., Meshkat M.A., and Qaeminia A.M. 2014. Monitoring of soil salinity using electromagnetic induction device, EM38 (Instructions for use, calibration method and relevant software). National Salinity Research Center, technical manual, 49p. (In Persian)

Rahimian M.H., Noori M.R., Hasheminejhad Y., Tabatabaei S.H., and Neshat, E. 2014. Determination of leaching fraction in Ardakan pistachio orchards through Integration of Wetting Front Detector and Electromagnetic Induction Devices. Journal of Water and Soil Sciences, 28: 163-173. (In Persian)

Rhoades J.D., and Corwin D.L. 1981. Determination soil electrical conductivity-depth relations using an inductive electromagnetic soil conductivity meter. Journal of Soil Science Society of American, 40: 651-655.

Rhoades J.D., Leach S.M., LeMert R.D., and Alves, W.J. 1997. Assessing irrigation/drainage/salinity management using spatially referenced salinity measurements. Agricultural Water Management, 35: 147-165.

Saey T., Van Meirvenne M., Vermeersch H., Ameloot N., and Cockx L. 2009. A pedotransfer function to evaluate the soil profile textural heterogeneity using proximally sensed apparent electrical conductivity. Geoderma, 150: 389-395.

Schaap M.G., Leij F.J., and Van Genuchten M.T. 1998. Neural network analysis for hierarchical prediction of soil hydraulic properties. Journal of Soil Science Society of America, 62: 847-855.

Slavich P.G. 1990. Determining EC, depth profiles from electromagnetic induction measurements. Australian Journal of Soil Research, 28: 443-452.

Slavich P.G., and Petterson G.H. 1990. Estimating average rootzone salinity from electromagnetic induction (EM38) measurements. Australian Journal of Soil Research, 28: 453-463.

Sommer M., Wehrhan M., Zipprich M., Castell Z.W., Weller U., Castell W., Ehrich S., Tandler B. and Selige T. 2003. Hierarchical data fusion for mapping soil units at field scale. Geoderma, 112: 179-196.

Srinivasan K., and Fisher D. 1995. Machine learning approaches to estimating software development effort. IEEE Transactions on Software Engineering, 21: 126-137.

Sudduth K., Drummond S., and Kitchen N. 2002. Accuracy issues in electromagnetic induction sensing of soil electrical conductivity for precision agriculture. Computers and Electronics in Agriculture, 31: 239-264.

Taghizadeh Mehrjardi R., Sarmadian F., Omid M., Savaghebi G.R., Rousta M.G., and Rahimian M.H. 2012. Zoning soil salinity use the techniques geostatistice and EM in Ardakan. Journal of Water and Soil Sciences, 26: 369-380. (In Persian)

Taghizadeh Mehrjardi R., Sarmadian F., Savaghebi G.R., Omid M., Tomanian N., Rousta M.G., and Rahimian M.H. 2013. Comparison of fuzzy techniques, genetic algorithms, neural networks and multivariate regression prediction of soil salinity (Case study: Ardekan city). Journal of Range and Watershed Management, 66: 207-222. (In Persian)

Taghizadeh Mehrjardi R., Minasny B., Sarmadian F., and Malone P.B. 2014. Digital mapping of soil salinity in Ardakan region, central Iran. Geoderma, 213: 15-28.

Tamari S., Wosten J.H.M., and Ruz-suarez J.C. 1996. Testing an artificial neural network for predicting soil hydraulic conductivity. Journal of Soil Science Society of America, 60: 1732-1741.

Triantafilis J., and Buchanan S.M. 2010. Mapping the spatial distribution of subsurface saline material in the Darling River valley. Journal of Applied Geophysics, 70:  144-160.

Wollenhaupt N.C., Richardson J.L., Foss J.E., and Doll E.C. 1986. A rapid method for estimating weighted soil salinity from apparent soil electrical conductivity measured with an above ground electromagnetic induction meter. Journal of Soil Science Society of America, 66: 315-321.