Forecasting Istanbul monthly temperature by multivariate partial least square

Abstract

Weather forecasting, especially for temperature, has always been a popular subject since it affects our daily life and always includes uncertainty as statistics does. The goals of this study are (a) to forecast monthly mean temperature by benefitting meteorological variables like temperature, humidity and rainfall; and (b) to improve the forecast ability by evaluating the forecasting errors depending upon the parameter changes and local or global forecasting methods. Approximately 100 years of meteorological data from 54 automatic meteorology observation stations of Istanbul that is the mega city of Turkey are analyzed to infer about the meteorological behaviour of the city. A new partial least square (PLS) forecasting technique based on chaotic analysis is also developed by using nonlinear time series and variable selection methods. The proposed model is also compared with artificial neural networks (ANNs), which model nonlinearly the relation between inputs and outputs by working neurons like human brain. Ordinary least square (OLS), PLS and ANN methods are used for nonlinear time series forecasting in this study. Major findings are the chaotic nature of the meteorological data of Istanbul and the best performance values of the proposed PLS model.

Climatic Trends in the Temperature of Çanakkale City, Turkey

“…Particularly, Ejder et al (2016aEjder et al ( , 2016b and Kale et al (2016aKale et al ( , 2016b reported that temperature has a statistically significant upward trend in Çanakkale. On the other hand, seasonal and monthly temperature trends were investigated by several authors (Karabulut et al, 2008;Şimşek et al, 2013;Ertaç et al, 2015;Tatlı & Altunay, 2015). Tatlı & Altunay (2015) investigated possible climate change effects in Turkey using monthly temperature dataset and reported that there were increasing trends for all seasons.…”

“…Tatlı & Altunay (2015) investigated possible climate change effects in Turkey using monthly temperature dataset and reported that there were increasing trends for all seasons. Ertaç et al (2015) forecasted monthly mean temperature for İstanbul (Turkey) and indicated that temperature has increased. Karabulut et al (2008) studied temperature trends in Samsun (Turkey) and found that temperature increased both annually and seasonally.…”

Nonlinear dynamics of monthly temperature data set in the Northwestern (Marmara region) Turkey

“…Monthly temperature, humidity and rainfall of Istanbul meteorological stations in a very large period were used for forecasting approach. The probability of chaos in the observed time series wasn't researchers' main purpose; however they showed the strong evidence of chaos by catching big and positive largest Lyapunov exponents value (Ertaç et al, 2015). Figure 5 shows the autocorrelation function of Bursa (Uludağ) station.…”

Accuracy Rate of Least Square Support Vector Machine Method and Its Various Modifications: A Forecasting Evaluation on Multi-Type Data

“…Utilizing LS in forecasting hourly fluctuations in the Air Quality Index (AQI) achieved an accuracy level of 93.24%, signifying a remarkably high precision [26]. In their study on monthly temperature estimation using the Partial Least Square (PLS) method, Ertaç et al [27] reported an RMSE value of 1.80% and a high accuracy level of 94%. Moreover, the LS method finds application in forecasting endeavors in the United States and Europe, including the USA [28][29][30][31][32], the Netherlands [33,34], Germany [35,36], and Brazil [37].…”