Skip to main content
SpringerLink
Log in

Comparison of artificial intelligence techniques for prediction of soil temperatures in Turkey

  • Original Paper
  • Published:
Theoretical and Applied Climatology Aims and scope Submit manuscript

Abstract

Soil temperature is a meteorological data directly affecting the formation and development of plants of all kinds. Soil temperatures are usually estimated with various models including the artificial neural networks (ANNs), adaptive neuro-fuzzy inference system (ANFIS), and multiple linear regression (MLR) models. Soil temperatures along with other climate data are recorded by the Turkish State Meteorological Service (MGM) at specific locations all over Turkey. Soil temperatures are commonly measured at 5-, 10-, 20-, 50-, and 100-cm depths below the soil surface. In this study, the soil temperature data in monthly units measured at 261 stations in Turkey having records of at least 20 years were used to develop relevant models. Different input combinations were tested in the ANN and ANFIS models to estimate soil temperatures, and the best combination of significant explanatory variables turns out to be monthly minimum and maximum air temperatures, calendar month number, depth of soil, and monthly precipitation. Next, three standard error terms (mean absolute error (MAE, °C), root mean squared error (RMSE, °C), and determination coefficient (R 2)) were employed to check the reliability of the test data results obtained through the ANN, ANFIS, and MLR models. ANFIS (RMSE 1.99; MAE 1.09; R 2 0.98) is found to outperform both ANN and MLR (RMSE 5.80, 8.89; MAE 1.89, 2.36; R 2 0.93, 0.91) in estimating soil temperature in Turkey.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4

Similar content being viewed by others

References

  • Ahmad MF, Rasul G (2008) Prediction of soil temperature by air temperature: a case study for Faisalabad. Pakistan Journal of Meteorology 5(9):19–27

    Google Scholar 

  • Bilgili M (2010) Prediction of soil temperature using regression and artificial neural network models. Meteorog Atmos Phys 110:59–70

    Article  Google Scholar 

  • Bilgili M, Sahin B, Sangun L (2013) Estimating soil temperature using neighboring station data via multi-nonlinear regression and artificial neural network models. Environ Monit Assess 185:347–358

    Article  Google Scholar 

  • Brar GS, Steiner JL, Unger PW, Prihar SS (1992) Modeling sorghum seedling establishment from soil wetness and temperature of drying seed zones. Agron J 84:905–910

    Article  Google Scholar 

  • Brooks PD, McKnight D, Elder K (2004) Carbon limitation of soil respiration under winter snowpacks: potential feedbacks between growing season and winter carbon fluxes. Glob Chang Biol 11:231–238

    Article  Google Scholar 

  • Cigizoglu HK (2003) Estimation, forecasting and extrapolation of river flows by artificial neural networks. Hydrol Sci J 48(3):349–361

    Article  Google Scholar 

  • Citakoglu H (2015) Comparison of artificial intelligence techniques via empirical equations for prediction of solar radiation. Comput Electron Agric 118:28–37

    Article  Google Scholar 

  • Cobaner M (2011) Evapotranspiration estimation by two different neuro-fuzzy inference systems. J Hydrol 398(3–4):292–302

    Article  Google Scholar 

  • Cobaner M, Citakoglu H, Kisi O, Haktanir T (2014) Estimation of mean monthly air temperatures in Turkey. Comput Electron Agric 109:71–79

    Article  Google Scholar 

  • Dawson WC, Wilby R (1998) An artificial neural network approach to rainfall-runoff modelling. Hydrol Sci J 43(1):47–66

    Article  Google Scholar 

  • Gao Z, Horton R, Wang L, Liu H, Wen J (2008) An improved force restore method for soil temperature prediction. Eur J Soil Sci 59:972–981

    Article  Google Scholar 

  • García-Suárez AM, Butler CJ (2006) Soil temperatures at Armagh observatory, Northern Ireland, from 1904 to 2002. Int J Climatol 26:1075–1089

    Article  Google Scholar 

  • George RK (2001) Prediction of soil temperature by using artificial neural networks algorithms. Nonlinear Analysis: Theory, Methods & Applications 47:1737–1748

    Article  Google Scholar 

  • Grundmann GL, Renault P, Rosso L, Bardin R (1995) Differential effects of soil water content and temperature on nitrification and aeration. Soil Sci Soc Am J 59:1342–1349

    Article  Google Scholar 

  • Hares MA, Novak MD (1992) Simulation of surface energy balance and soil temperature under strip tillage: I. Model description. Soil Sci Soc Am J 56:22–29

    Article  Google Scholar 

  • Haykin S (1998) Neural networks—a comprehensive foundation, 2nd edn. Prentice-Hall, Upper Saddle River, pp. 26–32

    Google Scholar 

  • Helsel DR, Hirsch RM (2002) Statistical methods in water resources, techniques of water-resources investigations of the United States, book 4, hydrologic analysis and interpretation, chapter A3. http://water.usgs.gov/pubs/twri/twri4a3/

  • Hontoria L, Aguilera J, Zufiria P (2005) An application of the multilayer perceptron: solar radiation maps in Spain. Sol Energy 79(5):523–530

    Article  Google Scholar 

  • Horton B, Corkrey R (2011) A weighted coefficient model for estimation of Australian daily soil temperature at depths of 5 cm to 100 cm based on air temperature and rainfall. Soil Research 49(4):305–314

    Article  Google Scholar 

  • Jang JSR (1993) Anfis adaptive-network-based fuzzy inference system. Systems, Man and Cybernetics, IEEE Transactions on 23:665–685

    Article  Google Scholar 

  • Kang S, Kim S, Oh S, Lee D (2000) Predicting spatial and temporal patterns of soil temperature based on topography, surface cover and air temperature. For Ecol Manag 136:173–184

    Article  Google Scholar 

  • Karunanithi N, Grenney WJ, Whitley D, Bovee K (1994) Neural networks for river flow prediction. J Comp Civ Eng ASCE 8(2):201–220

    Article  Google Scholar 

  • Kemp PR, Cornelius JM, Reynolds JF (1992) A simple model for predicting soil temperatures in desert ecosystems. Soil Sci 153:280–287

    Article  Google Scholar 

  • Kim S, Singh VJ (2014) Modeling daily soil temperature using data driven models and spatial distribution. Theor Appl Climatol 118(3):465–479

    Article  Google Scholar 

  • Kisi O, Tombul M, Kermani MZ (2015) Modeling soil temperatures at different depths by using three different neural computing techniques. Theor Appl Climatol 121(1):377–387

    Article  Google Scholar 

  • Kluender RA, Thompson LC, Steigerwald DM (1993) A conceptual model for predicting soil temperatures. Soil Sci 156:10–19

    Article  Google Scholar 

  • Krishnan A, Rao GGSN (1979) Soil temperature regime in the arid zone of India. Archiv für Meteorologie, Geophysik und Bioklimatologie, Serie B 27(1):15–22

    Article  Google Scholar 

  • Lin JD (1980) On the force-restore method for prediction of ground surface temperature. Journal of Geophysical Research: Oceans 85(C6):3251–3254

    Article  Google Scholar 

  • Lippman R (1987) An introduction to computing with neural nets. IEEE ASSP Mag 4:4–22

    Article  Google Scholar 

  • Mazou E, Alvertos N, Tsiros IX (2012) Soil temperature prediction using time-delay neural networks. In: Helmis CG and Nastos PT (eds) Advances in meteorology, climatology and atmospheric physics. Springer Atmospheric Sciences

  • McCann IR, McFarland MJ, Witz JA (1991) Near-surface bare soil temperature model for biophysical models. Transactions of American Society of Agricultural and Biological Engineers 34:748–755

    Article  Google Scholar 

  • MGM (2016) Turkish state meteorological service, www.mgm.gov.tr

  • Mohandes M, Rehman S, Halawani TO (1998) Estimation of global solar radiation using artificial neural networks. Renew Energy 14(1–4):179–184

    Article  Google Scholar 

  • Montgomery D, Peck E, Vining G (2001) Introduction to linear regression analysis, 3rd edn. John Wiley, New York

    Google Scholar 

  • Negnevitsky M (2005) Artificial intelligence: a guide to intelligent systems. Pearson Education Limited, Harlow, Essex CM20 2JE, England

    Google Scholar 

  • Ozturk M, Salman O, Koc M (2011) Artificial neural network model for estimating 579 the soil temperature. Can J Soil Sci 91:551–562. doi:10.4141/CJSS10073

    Article  Google Scholar 

  • Paul KI, Polglase PJ, Smethurst PJ, O’Connell AM, Carlyle CJ, Khanna PK (2004) Soil temperature under forests: a simple model for predicting soil temperature under a range of forest types. Agric For Meteorol 121:167–182

    Article  Google Scholar 

  • Peters-Lidard CD, Blackburn E, Liang X, Wood EF (1998) The effect of soil thermal conductivity parameterization on surface energy fluxes and temperatures. J Atmos Sci 55:1209–1224

    Article  Google Scholar 

  • Qian B, Gregorich EG, Gameda S, Hopkins DW, Wang XL (2011) Observed soil temperature trends associated with climate change in Canada, Journal of Geophysical Research. Atmosphere 116(D2):1–16

    Google Scholar 

  • Rao V, Rao H (1996) C++ neural networks and fuzzy logic, B-14. Connaught Place: BPB Publications, New Delhi , pp. 380–381110001

    Google Scholar 

  • Rehman S, Mohandes M (2008) Artificial neural network estimation of global solar radiation using air temperature and relative humidity. Energy Policy 36(2):571–576

    Article  Google Scholar 

  • Rounsevell MDA, Bullock P, Haris J (1996) Climate change, soils and sustainability. In: Taylor AG, Gordon JE, Usher MB (eds) Soils and sustainability and the natural heritage. Scottish Natural Heritage. HMSO, London, UK, pp. 121–139

    Google Scholar 

  • Rumelhart DE, Hinton GE, Williams RJ (1986) Learning internal representation by error propagation. In: Rumelhart DE, McClelland JL (eds) Parallel distributed processing. Foundations, vol 1. MIT Press, Cambridge, MA

    Google Scholar 

  • Schimel JP, Bilbrough C, Welker JA (2004) Increased snow depth affects microbial activity and nitrogen mineralization in two Arctic tundra communities. Soil Biol Biochem 36:217–227

    Article  Google Scholar 

  • Seyfried MS, Flerchinger GN, Murdock MD, Hanson CL, Van Vactor S (2001) Long-term soil temperature database, Reynolds Creek experimental watershed, Idaho, United States. Water Resour Res 37:2843–2846

    Article  Google Scholar 

  • Singh VP (1992) Elementary hydrology, vol 973. Prentice-Hall, Englewood Cliffs, NJ

    Google Scholar 

  • Siqueira AN, Tiba C, Fraidenraich N (2010) Generation of daily solar irradiation by means of artificial neural networks. Renew Energy 35(11):2406–2414

    Article  Google Scholar 

  • Sviličić P, Vučetić V, Filić S, Smolić A (2015) Soil temperature regime and vulnerability due to extreme soil temperatures in Croatia. Theor Appl Climatol. doi:10.1007/s00704-015-1558-z

    Google Scholar 

  • Tabari H, Sabziparvar AA, Ahmadi M (2011) Comparison of artificial neural network and multivariate linear regression methods for estimation of daily soil temperature in an arid region. Meteorog Atmos Phys 110:135–142

    Article  Google Scholar 

  • Talaee PH (2014) Daily soil temperature modeling using neuro-fuzzy approach. Theor Appl Climatol 118:481–489

    Article  Google Scholar 

  • Vigil MF, Kissel DE (1995) Rate of nitrogen mineralized from incorporated crop residues as influenced by temperature. Soil Sci Soc Am J 59:1636–1644

    Article  Google Scholar 

  • Walther GR, Post E, Convey P, Menzel A, Parmesan C, Beebee TCJ, Fromentin JM, Hoegh-Guldberg O, Bairlein F (2002) Ecological responses to recent climate change. Nature 416:389–395

    Article  Google Scholar 

  • Wu W, Tang XP, Guo NJ, Yang C, Liu HB, Shang YF (2013) Spatiotemporal modeling of monthly soil temperature using artificial neural networks. Theor Appl Climatol 113:481–494

    Article  Google Scholar 

  • Yilmaz T, Ozbek A, Yilmaz A, Buyukalaca O (2009) Influence of upper layer properties on the ground temperature distribution. J Therm Sci Technol 29:43–51

    Google Scholar 

  • Yin X, Arp PA (1993) Predicting forest soil temperatures from monthly air temperature and precipitation records. Can J For Res 23:2521–2536

    Article  Google Scholar 

Download references

Acknowledgments

The author wishes to thank the General Directorate of Turkish State Meteorological Service for supplying the meteorological data used in the present research.

Author information

Authors and Affiliations

  1. Faculty of Engineering, Civil Engineering Department, Erciyes University, 38039, Kayseri, Turkey

    Hatice Citakoglu

Authors
  1. Hatice Citakoglu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Hatice Citakoglu.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Citakoglu, H. Comparison of artificial intelligence techniques for prediction of soil temperatures in Turkey. Theor Appl Climatol 130, 545–556 (2017). https://doi.org/10.1007/s00704-016-1914-7

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00704-016-1914-7

Keywords

Search

Navigation