Estimation of mean monthly air temperatures in Turkey

We model monthly temperature values by MLR, ANN and ANFIS models.Input variables are latitude, longitude, altitude and the month numbers.ANFIS model is found to perform better than the ANN and MLR models. One of the most important climatic factors influencing growth, development and yield of crops, which involve a countless number of biochemical reactions, is temperature. It is also one of the most effective explanatory variables of the evapotranspiration estimation models such as Hargreaves, Rich and Thornthwaite needed for irrigation scheduling policies. Using artificial neural networks (ANN), adaptive neuro-fuzzy inference system (ANFIS), and multiple linear regression (MLR) models, means of maximum, minimum, and average monthly temperatures are estimated as a function of geographical coordinates and month number for any location in Turkey. The monthly data measured by the General Directorate of State Meteorological Works at 275 stations having records of at least 20years are used in developing the models. The latitude, longitude, and altitude of the location, and the month number are used as the input variables, and each of the mean monthly maximum, minimum, and average air temperatures is computed as the output variable. The observed values are compared versus those predicted by the ANN, ANFIS, and MLR models by evaluating their errors, and as a result the ANFIS model turns out to be the best.

[1]  Zhu Ruigeng,et al.  An engineering geology evaluation method based on an artificial neural network and its application , 1997 .

[2]  Adnan Parlak,et al.  Application of artificial neural network to predict specific fuel consumption and exhaust temperature for a Diesel engine , 2006 .

[3]  Mirza Hasanuzzaman,et al.  Extreme Temperature Responses, Oxidative Stress and Antioxidant Defense in Plants , 2013 .

[4]  Maher Chaabene,et al.  Neuro-fuzzy dynamic model with Kalman filter to forecast irradiance and temperature for solar energy systems , 2008 .

[5]  Ozgur Kisi,et al.  Suspended sediment estimation using neuro-fuzzy and neural network approaches/Estimation des matières en suspension par des approches neurofloues et à base de réseau de neurones , 2005 .

[6]  Slavisa Trajkovic,et al.  Testing hourly reference evapotranspiration approaches using lysimeter measurements in a semiarid climate. , 2010 .

[7]  R. E. Abdel-Aal,et al.  Hourly temperature forecasting using abductive networks , 2004, Eng. Appl. Artif. Intell..

[8]  Athanasios Sfetsos,et al.  A comparison of various forecasting techniques applied to mean hourly wind speed time series , 2000 .

[9]  Ozgur Kisi,et al.  River Flow Modeling Using Artificial Neural Networks , 2004 .

[10]  Mohamed Mohandes,et al.  Estimation of wind speed profile using adaptive neuro-fuzzy inference system (ANFIS) , 2011 .

[11]  M. Cobaner.  Evapotranspiration estimation by two different neuro-fuzzy inference systems , 2011 .

[12]  Ali Rahimikhoob,et al.  Estimating global solar radiation using artificial neural network and air temperature data in a semi-arid environment , 2010 .

[13]  Mehmet Bilgili,et al.  Prediction of Long-term Monthly Temperature and Rainfall in Turkey , 2009 .

[14]  A. R. Khoob,et al.  Comparative study of Hargreaves’s and artificial neural network’s methodologies in estimating reference evapotranspiration in a semiarid environment , 2008, Irrigation science.

[15]  I. Dimopoulos,et al.  An application of artificial neural network models to estimate air temperature data in areas with sparse network of meteorological stations , 2008, Journal of environmental science and health. Part A, Toxic/hazardous substances & environmental engineering.

[16]  Zsolt Tulassay,et al.  Application of neural networks in medicine - a review , 1998 .

[17]  F. A. Ogbu,et al.  The importance of maximum air temperature in the parameterisation of solar radiation in Nigeria , 1995 .

[18]  Z. Samani,et al.  Estimating Potential Evapotranspiration , 1982 .

[19]  George H. Hargreaves,et al.  Reference Crop Evapotranspiration from Temperature , 1985 .

[20]  Lisa Guan,et al.  Cross-correlations between weather variables in Australia , 2007 .

[21]  Michio Sugeno,et al.  Fuzzy identification of systems and its applications to modeling and control , 1985, IEEE Transactions on Systems, Man, and Cybernetics.

[22]  Sancho Salcedo-Sanz,et al.  Prediction of daily maximum temperature using a support vector regression algorithm , 2011 .

[23]  François Anctil,et al.  Neural network estimation of air temperatures from AVHRR data , 2004 .

[24]  Slavisa Trajkovic,et al.  Comparison of radial basis function networks and empirical equations for converting from pan evaporation to reference evapotranspiration , 2009 .

[25]  Yi-Chin Fang,et al.  Neural network application for thermal image recognition of low-resolution objects , 2007 .

[26]  Paolo Massimo Buscema,et al.  Feedforward networks in financial predictions: the future that modifies the present , 2000, Expert Syst. J. Knowl. Eng..

[27]  Narendra Singh Raghuwanshi,et al.  Estimation of monthly solar radiation from measured air temperature extremes , 2008 .

[28]  Slavisa Trajkovic,et al.  Temperature-based approaches for estimating reference evapotranspiration , 2005 .

[29]  Ali Rahimikhoob,et al.  Estimation of evapotranspiration based on only air temperature data using artificial neural networks for a subtropical climate in Iran , 2010 .

[30]  J. C. Quadrado,et al.  Wind speed prediction using artificial neural networks , 2005 .