Equatorial Guinea is a small country in West Africa that experiences significant climate variability due to its equatorial location. Understanding and predicting climate conditions are crucial for effective adaptation planning, particularly in sectors like agriculture and water management. The methodology involves collecting historical climate data from multiple sources, including satellite observations and ground weather stations, which will be used as input features for our machine learning models. We employ a Random Forest model to predict temperature and precipitation changes over time. Our preliminary analysis shows that the Random Forest model achieves an accuracy of approximately 78% in predicting future climate conditions based on historical data trends. The findings suggest that machine learning models, such as Random Forest, can be effectively utilised for climate prediction and adaptation planning in Equatorial Guinea. This research contributes to a more robust understanding of climate dynamics in tropical regions. Future studies should focus on validating these models across different seasons and geographical areas within Equatorial Guinea, and integrate them into existing climate change adaptation plans. Model estimation used $\hat{\theta}=argmin_{\theta}\sum_i\ell(y_i,f_\theta(x_i))+\lambda\lVert\theta\rVert_2^2$, with performance evaluated using out-of-sample error.