Modeling,Trend Assessing and Prediction of Mean Maximum Temperature in Northwest of Iran

Introduction
Climate change and its consequence impacts on the different phenomena of earth are serious mankind concerns during recent years. Climate change and global warming have very significant negative impacts on different resources including water and ice resources, forests, pastures, agricultural fields, industry and finally human life. Air temperature and precipitation variations are primary effects of climate change on the atmospheric elements. Hence, the assessment of the atmospheric element for an instance temperature has critical importance. Temperature rise caused by climate change have serious negative impacts on agricultural activities through increasing the evaporation and the possibility of droughts. Because climatological elements have nonlinear behavior and they are not function of a certain statistic distribution therefore a tendency for using non-parametric approaches especially Mann-Kendall is growing. The complicated nature of physical processes and lack of adequate knowledge in the climate models have caused creating statistical models and their development for defining these processes. The application of these models for reconstruction of past values and predicting of future values has been called time series. The aim of current research is analyzing the variation trend of mean maximum monthly temperature using Mann-Kendall test, mean maximum monthly temperature with time series method, determining proper pattern and prediction of temperature variations at the Northwest of Iran in the following years.
Methodology
In this research the trend of mean maximum temperature variations in 12 selected stations in Northwest of Iran in a 24 years period was investigated. At first, the trend of variation data series for was tested using Mann-Kendall approach. Then, mean maximum monthly temperature was predicted using time series model. Minitab 17 software was applied in order time series model development and prediction purposes. Total number of data for each set was 285 where 80% of them were considered for calibration and 20% for model validation. The performance of models was investigated based on Model Efficiency Coefficient (CE) and Correlation Coefficient (R) indices. The CE varies between ∞- to 1 and the closer values to 1 indicates more accurate model performance. Finally, temperature predictions were done for following 8 years based on developed models.
Findings
The obtained results of application of Mann-Kendall test for determining mean maximum temperature trend in 12 studied stations in the Northwest of Iran clarified an increasing behavior for all stations. Increasing trends in Ahar and Sarab station were significant at the level of 95% and in the Tabriz, Marageh, Miyaneh, Ardabil, Khalkhal, Urmia, Khoy and Mahabad stations the significance level was 99%. Regarding to the basic assumptions in time series modeling, before starting model creating, the normal and static situation of data series was tested. The obtained results of these tests also showed a linear increasing trend in the investigated stations. Consequently, seasonal and non-seasonal differential process on initial series in the studied stations was conducted to model recognize through ACF and PACF differential series graphs. The temperature variations along different seasons of year in all stations proved more increasing for all stations in the winter in comparison with other seasons.
Considering 12th differential level due to seasonal characteristic of data, ACF and PACF graphs of differential series were plotted and a correlation was observed between data in first lag. To create series model, seasonal model of SARIMA(p,d,q)(P,D,Q)ω was applied. After calibration and validation of final models for studied stations, these models were applied to for predicting 8 following years (2018-2026) and were compared with basic period (1994-2017). According to the predictions, mean maximum temperature in all station shows an increasing in comparison to the basic period. The highest increasing amount is for Jolfa station with 4.39˚C and the lowest value was determined for Parsabad station with 0.69 ˚C. The variations of temperature was assessed in seasonal scale for 8 upcoming years. The comparisons of temperature variation for all stations in the different seasons showed increasing behaviors in all stations in winter in comparisons with other seasons.

Conclusion
Mean maximum temperature in 12 studied stations was modeled by time series. High values for R and CE in these stations proved high accuracy of this method for predicting of air temperature. After model development and selection of the most proper model for studied stations, the prediction of temperature was performed for 8 following years for each station. The temperature variations in this duration were investigated seasonally and the results showed that the maximum temperature increasing for all stations will occur in the winter. Temperature increasing in winter months may cause negative impacts like change in precipitation pattern from snow to rain, early melting of region snow reservoirs, incomplete vernalization of the seeds and early start of growing season with a risk of frost hazard for crops.