Selection for the best ETS (error, trend, seasonal) model to forecast weather in the Aceh Besar District

7th AIC‐ICMR on Sciences and Engineering 2017

自然科学;工业技术

Jofipasi, Chesilia Amora^1 ; Miftahuddin^1 ; Hizir^1

Department of Statistics, Faculty of Mathematics and Science, Syiah Kuala University, Banda Aceh, Indonesia^1

关键词: Air temperature;    Dew points;    Forecasting methods;    Sea level pressure;    Sea surface temperature (SST);    Station pressure;    Univariate;    Wind speed;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/352/1/012055/pdf
DOI  :  10.1088/1757-899X/352/1/012055

来源: IOP

【 摘 要 】

Weather is a phenomenon that occurs in certain areas that indicate a change in natural activity. Weather can be predicted using data in previous periods over a period. The purpose of this study is to get the best ETS model to predict the weather in Aceh Besar. The ETS model is a time series univariate forecasting method; its use focuses on trend and seasonal components. The data used are air temperature, dew point, sea level pressure, station pressure, visibility, wind speed, and sea surface temperature from January 2006 to December 2016. Based on AIC, AICc and BIC the smallest values obtained the conclusion that the ETS (M, N, A) is used to predict air temperature, and sea surface temperature, ETS (A, N, A) is used to predict dew point, sea level pressure and station pressure, ETS (A, A, N) is used to predict visibility, and ETS (A, N, N) is used to predict wind speed.