TITLE:
A Hybrid Methodology for Short Term Temperature Forecasting
AUTHORS:
Wissam Abdallah, Nassib Abdallah, Jean-Marie Marion, Mohamad Oueidat, Pierre Chauvet
KEYWORDS:
Time Series Analysis, ARIMA Auto Regressive Integrated Moving Average, Weather Forecasting Model, Multiprocessing
JOURNAL NAME:
International Journal of Intelligence Science,
Vol.10 No.3,
June
12,
2020
ABSTRACT: Developing a reliable
weather forecasting model is a complicated task, as it requires heavy IT
resources as well as heavy investments beyond the financial capabilities of
most countries. In Lebanon, the prediction model used by the civil aviation
weather service at Rafic Hariri International Airport in Beirut (BRHIA) is the
ARPEGE model, (0.5) developed by the weather service in France. Unfortunately,
forecasts provided by ARPEGE have been erroneous and biased by several factors
such as the chaotic character of the physical modeling equations of some
atmospheric phenomena (advection, convection, etc.) and the nature of the
Lebanese topography. In this paper, we proposed the time series method ARIMA
(Auto Regressive Integrated Moving Average) to forecast the minimum daily
temperature and compared its result with ARPEGE. As a result, ARIMA method
shows better mean accuracy (91%) over the numerical model ARPEGE (68%), for the
prediction of five days in January 2017. Moreover, back to five months ago, in
order to validate the accuracy of the proposed model, a simulation has been
applied on the first five days of August 2016. Results have shown that the time
series ARIMA method has offered better mean accuracy (98%) over the numerical
model ARPEGE (89%) for the prediction of five days of August 2016. This paper
discusses a multiprocessing approach applied to ARIMA in order to enhance the
efficiency of ARIMA in terms of complexity and resources.