Machine learning (ML) models have shown promise in climate prediction and adaptation planning across various regions. A comprehensive search strategy was employed using databases such as Web of Science and Google Scholar, focusing on peer-reviewed articles published between and. Studies were screened based on predefined inclusion criteria related to ML models used for climate predictions and adaptation planning in São Tomé and Príncipe. ML models showed significant variability in their performance across different studies, with some achieving up to 85% accuracy in predicting rainfall patterns. Despite the challenges posed by limited data availability, ML models demonstrated potential for climate prediction and adaptation planning in São Tomé and Príncipe. However, further research is needed to validate these findings in real-world applications. Future studies should focus on developing more robust datasets and exploring ensemble methods to improve model performance and reliability. Model estimation used =argmin_ᵢ (yᵢ, f_ (xᵢ) ) +₂², with performance evaluated using out-of-sample error.
Nóbrega et al. (Mon,) studied this question.