The use of artificial neural networks for forecasting the monthly mean soil temperatures in Adana, Turkey

The objective of this paper was to develop an artificial neural network (ANN) model in order to predict monthly mean soil temperature for the present month by using various previous monthly mean meteorological variables. For this purpose, the measured soil temperature and other meteorological data between the years of 2000 and 2007 at Adana meteorological station were used. The soil temperatures were measured at depths of 5, 10, 20, 50, and 100 cm below the ground level by the Turkish State Meteorological Service (TSMS). A 3-layer feed-forward artificial neural network structure was constructed and a back-propagation algorithm was used for the training of ANNs. The models consisting of the combination of the input variables were constructed and the best fit input structure was investigated. The performances of ANN models in training and testing procedures were compared with the measured soil temperature values to identify the best fit forecasting model. The results show that the ANN approach is a reliable model for prediction of monthly mean soil temperature.

Anahtar Kelimeler:

Key words: Artificial neural network, meteorological variables, prediction, soil temperature

The use of artificial neural networks for forecasting the monthly mean soil temperatures in Adana, Turkey

Keywords:

Key words: Artificial neural network, meteorological variables, prediction, soil temperature,

PDF

___

Bechrakis DA, Sparis PD (200 ) Correlation of wind speed between neighboring measuring stations. IEEE Transactions on Energy Conversion 19: 00- 06.
Bilgili M, Sahin B (2010) Prediction of long-term monthly temperature and rainfall in Turkey. Energy Sources 32: 60-71.
Bilgili M, Sahin B, Yasar A (2007) Application of artificial neural networks for the wind speed prediction of target station using reference stations data. Renewable Energy 32: 2350-2360.
Droulia F, Lykoudis S, Tsiros I, Alvertos N, Akylas E, Garofalakis I (2009) Ground temperature estimations using simplified analytical and semi-empirical approaches. Solar Energy 83: 211- 219.
Elminir HK, Azzam YA, Younes FI (2007) Prediction of hourly and daily diffuse fraction using neural network, as compared to linear regression models. Energy 32: 1513-1523.
Enrique G, Braud I, Jean-Louis T, Michel V, Pierre B, Jean-Christophe C (1999) Modelling heat and water exchanges of fallow land covered with plant-residue mulch. Agriculture and Forest Meteorology 97: 151-169.
Firat M, Gungor M (2009) Generalized regression neural networks and feed forward neural networks for prediction of scour depth around bridge piers. Advances in Engineering Software 0: 731- 737.
Gao Z, Bian L, Hu Y, Wang L, Fan J (2007) Determination of soil temperature in an arid region. Journal of Arid Environments 71: 157-168.
Gao Z, Horton R, Wang L, Liu H, Wen J (2008) An improved force- restore method for soil temperature prediction. European Journal of Soil Science 59: 972-981.
García-Suárez AM, Butler CJ (2006) Soil temperatures at Armagh observatory, northern Ireland, from 190 to 2002. International Journal of Climatology 26: 1075-1089.
George RK (2001) Prediction of soil temperature by using artificial neural networks algorithms. Nonlinear Analysis 7: 1737-17 8.
Haykin S (199 ) Neural Networks, A Comprehensive Foundation. Prentice-Hall, Inc, New Jersey.
Kalogirou SA (2001) Artificial neural networks in renewable energy systems applications: a review. Renewable and Sustainable Energy Reviews 5: 373- 01.
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. Forest Ecology and Management 136: 173- 18 .
Krauss G, Kindangen JI, Depecker P (1997) Using artificial neural networks to predict interior velocity coefficients. Building and Environment 32: 295-303.
Kisi O (200 ) River flow modeling using artificial neural networks. Journal of Hydrologic Engineering 9: 60-63.
Koçak K, Şaylan L, Eitzinger J (200 ) Nonlinear prediction of near- surface temperature via univariate and multivariate time series embedding. Ecological Modelling 173: 1-7.
Maqsood I, Khan MR, Huang GH, Abdalla R (2005) Application of soft computing models to hourly weather analysis in southern Saskatchewan, Canada. Engineering Applications of Artificial Intelligence 18: 115-125.
Melesse AM, Hanley RS (2005) Artificial neural network application for multi-ecosystem carbon flux simulation. Ecological Modelling 189: 305-31 .
Mihalakakou G (2002) On estimating soil surface temperature profiles. Energy and Buildings 3 : 251-259.
Paul KI, Polglase PJ, Smethurst PJ, O’Connell AM, Carlyle CJ, Khanna PK (200 ) Soil temperature under forests: a simple model for predicting soil temperature under a range of forest types. Agriculture and Forest Meteorology 121: 197-182.
Prangnell J, McGowan G (2009) Soil temperature calculation for burial site analysis. Forensic Science International 191: 10 -109.
Sözen A, Arcaklıoğlu E, Özalp M, Çağlar N (2005) Forecasting based on neural network approach of solar potential in Turkey. Renewable Energy 30: 1075-1090.
Tayfur G (2002) Artificial neural networks for sheet sediment transport. Hydrological Science Journal 7: 879-892.
Tenge AJ, Kagihura FBS, Lal R, Singh BR (1998) Diurnal soil temperature fluctuations for different erosion classes of an oxisol at Mlingano, Tanzania. Soil and Tillage Research 9: 211- 217.
Ustaoglu B, Cigizoglu HK, Karaca M (2008) Forecast of daily mean, maximum and minimum temperature time series by three artificial neural network methods. Meteorological Applications 15: 31- 5.
Yılmaz T, Özbek A, Yılmaz A, Büyükalaca O (2009) Influence of upper layer properties on the ground temperature distribution. Journal of Thermal Science and Technology 29: 3-51.