Statistical Downscaling of Global Climate Models for Temperature Trend Analysis in Calgary

Climate change, particularly global warming, is a significant environmental issue that has gained widespread attention in recent decades. It poses a significant threat to life on Earth and requires thorough investigation to understand its impact on different regions of the world. Global Climate Models (GCMs) are one of the primary tools used to study the effects of global warming. However, due to regional diversity and variations in weather patterns, it is necessary to downscale these models to a smaller scale using statistical downscaling methods. This study aimed to complement the model for the future by utilizing Global Climate Model (GCM) data and applying shallow-layered Artificial Neural Network (ANN) and deep-based Long Short-Term Memory (LSTM) network to extract the historical temperature trend of the city of Calgary. Mutual Information (MI) was employed for screening purposes to ensure the quality of the input variables. The results of the study showed that the LSTM model, which relied on the data screening method using MI, achieved an RMSE of 0.01°C and a DC of 0.93. The ANN model, on the other hand, relied on the data screening method and using MI, yielded an RMSE of 1.2°C and a DC of 0.78. These findings demonstrate the effectiveness of the LSTM model in extracting the historical temperature trend of the city of Calgary, and the importance of using rigorous statistical methods to ensure the quality of input variables in downscaling models.