APPLICATION OF ARTIFICIAL NEURAL NETWORK FORECASTING OF DAILY MAXIMUM TEMPERATURE IN KONYA
Küçük Resim Yok
Tarih
2011
Yazarlar
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
BRNO UNIV TECHNOLOGY VUT PRESS
Erişim Hakkı
info:eu-repo/semantics/closedAccess
Özet
Weather forecast is one of the most effective factors on human beings and other living creatures. Maximum air temperature is one of the most important parameters to be estimated for meteorology, because the maximum and minimum temperature data is the outlook of the institution and the most interesting aspect of weather forecast presentations. Many meteorological variables play an important role in estimating the lowest and highest temperature of the day. Today, numerical models are mainly used in weather forecasting. The incredible success of Artificial Neural Networks (ANN) in classification and estimation makes it necessary to use this approach in the area of meteorology. Apart from known methods, ANN, which is an artificial intelligence technique, was used to forecast maximum temperature, which is the modeling of a non-linear process. In this study, the data for the years 2008 and 2009 was used that were obtained from the Turkish Meteorological Data Archive System and The Directorate of Konya Airfield Meteorology Station, which are the institutions of the General Directorate of Turkish State Meteorological Services. The developed ANN has 6 inputs and 1 output. The six input variables were respectively the temperature at 850 hpa level (t(850)-degrees C), daily average actual pressure (P-mb), daily minimum temperature (t(min)-degrees C), daily mean temperature (t(mean)-degrees C), daily average relative humidity (H-%) and daily sunshine duration (SD-hour). The output parameter value was the daily maximum temperature (t(max)-degrees C). Feed-forward back-propagation ANN model was used in this study. Levenberg-Marquardt (trainlm) training algorithm and Hyperbolic Tangent Sigmoid (tansig) and Logarithmic Sigmoid (logsig) transfer function were tried in the software developed in MATLAB and the results were obtained. The study put forth that accuracy rates and mean absolute error (MSE) obtained from training and test operations can be used in determining the maximum air temperature in the generated model.
Açıklama
17th International Conference on Soft Computing MENDEL 2011 -- JUN 15-17, 2011 -- Brno, CZECH REPUBLIC
Anahtar Kelimeler
Artificial Neural Network, Weather Forecast, Daily Maximum Temperature
Kaynak
MENDEL 2011 - 17TH INTERNATIONAL CONFERENCE ON SOFT COMPUTING
WoS Q Değeri
N/A
Scopus Q Değeri
Q2
