Machine learning (ML) models have shown promise in climate prediction and adaptation planning for various regions, but their application in Eswatini is not well-documented. A comprehensive search strategy was employed across multiple databases including Web of Science, Scopus, and Google Scholar. Studies were screened based on predefined inclusion criteria related to climate prediction and adaptation using ML models. ML models such as Random Forest and Support Vector Machines (SVM) showed significant improvement in forecasting temperature anomalies with an accuracy rate of around 75%, indicating their potential for resource planning and policy-making. The review highlights the suitability of ML techniques for climate prediction, particularly SVM, which outperformed other models across multiple datasets. However, there is a need for more empirical validation and interdisciplinary collaboration to enhance model reliability. Future research should focus on integrating sociological data into climate models and conducting in-depth case studies to validate findings from ML analyses. Model estimation used =argmin_ᵢ (yᵢ, f_ (xᵢ) ) +₂², with performance evaluated using out-of-sample error.
Maseko et al. (Sat,) studied this question.