Ke Liu ¹ Ke Liu ^2* Zheng Wang ^3* Yuanyuan Liu ^3* Bin Bai ^3* Rui Zhao ^3*

• ¹ Shandong Chengxin Engineering Construction & Consulting Co.Ltd, Shandong, China
• ² Shandong Chengxin Engineering Construction & Consulting Co.Ltd,Jinan,Shangdong,250100,China, Jinan, China
• ³ State Grid Ningxia Electric Power Co.Ltd,Eco-tech Research Institute,Yinchuan, Ningxia, China

Climate change is one of the major challenges facing the world today, causing frequent extreme weather events that significantly impact human production, life, and the ecological environment.Traditional climate prediction models largely rely on the simulation of physical processes. While they have achieved some success, these models still face issues such as complexity, high computational cost, and insufficient handling of multivariable nonlinear relationships. In light of this, this paper proposes a hybrid deep learning model based on Transformer-Convolutional Neural Network (CNN)-Long Short-Term Memory (LSTM) to improve the accuracy of climate predictions. Firstly, the Transformer model is introduced to capture the complex patterns in climate data time series through its powerful sequence modeling capabilities. Secondly, CNN is utilized to extract local features and capture short-term changes. Lastly, LSTM is adept at handling long-term dependencies, ensuring the model can remember and utilize information over extended time spans. Experiments conducted on temperature data from Guangdong Province in China validate the performance of the proposed model. Compared to four different climate prediction decomposition methods, the proposed hybrid model with the Transformer method performs the best. The results also show that the Transformer-CNN-LSTM hybrid model outperforms other hybrid models on five evaluation metrics, indicating that the proposed model provides more accurate predictions and more stable fitting results.