Climate change poses an urgent threat to ecosystems, human society, and the global economy. Accurately forecasting future changes to the Earth's climate is critical for informing mitigation and adaptation strategies. However, traditional physics-based climate models have limitations in fully capturing the complexity of the climate system. In recent years, deep learning (DL) has emerged as a powerful tool for modeling complex systems. In this study, we developed a novel DL framework for climate modeling that combines convolutional neural networks (CNNs) and long short-term memory (LSTM) networks. The model was trained on historical climate data from 1950-2020 and evaluated on holdout data from 2001-2020.