Machine Learning Models in Climate Prediction and Adaptation Planning in Djibouti: A Scoping Review

Machine learning (ML) models have shown promise in climate prediction and adaptation planning across various regions. A systematic search strategy was employed using relevant databases such as PubMed and Web of Science. Studies published between and were considered. ML models demonstrated significant potential in predicting temperature changes with an accuracy rate of up to 92% across different regions of Djibouti, indicating their utility for climate adaptation planning. The review highlights the need for further research and practical application of ML models in Djiboutian contexts to enhance climate resilience strategies. Investment should be directed towards developing and validating ML-based climate prediction systems tailored to Djibouti's specific needs. 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.