Machine Learning Models in Climate Prediction and Adaptation Planning in Nigeria

Recent climate change impacts in Nigeria highlight the necessity for predictive models to support adaptation planning. The research employs a combination of historical climate data and ML algorithms, including Random Forest and Support Vector Machines, for model development and validation. Random Forest demonstrated an accuracy rate of 85% in forecasting temperature variations across key regions of Nigeria, with lower uncertainty levels compared to Support Vector Machines. ML models offer a robust toolset for climate prediction, aiding policymakers in formulating effective adaptation strategies. Adopting ML models in climate research and planning can significantly enhance the reliability and efficiency of future climate predictions. 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.