Temperature forecasting is deemed one of the most significant elements that contribute in assessing the impacts of climate change. This paper presents a comprehensive analysis of temperature prediction in the state of Qatar using a combination of traditional statistical models and advanced machine learning techniques. The dataset comprises the monthly average of minimum and maximum temperatures in Qatar from January 2011 to February 2024. We employ Autoregressive Integrated Moving Average (ARIMA), Seasonal Autoregressive Integrated Moving Average (SARIMA), and Random Forest (RF) models to forecast minimum and maximum temperatures, aiming to assess the impact of climate change in the region. The study compares the forecasting accuracy of each model, evaluated through Root Mean Square Error (RMSE) and Mean Absolute Error (MAE). The results show that while traditional models like ARIMA and SARIMA provide baseline forecasts, they fail to capture the complex patterns inherent in the temperature data. Random Forest Algorithm demonstrates a much better performance than the previous models in predicting temperature and effectively capturing temperature variations. The results emphasize the importance of applying machine learning approaches in climate modeling to achieve more accurate and reliable forecasts. This work reveals that advanced modeling methodologies is central to the efforts of evaluating the effects of climate change in Qatar.