Cape Verde is an archipelago in the Atlantic Ocean with limited terrestrial resources, making effective land use management crucial for sustainable development. The study utilised Sentinel-2 satellite imagery acquired over two years, processed through a Convolutional Neural Network (CNN) model with an accuracy threshold set at 95%. A significant proportion of the analysed land (73%) was found to be dedicated to agriculture and forestry, highlighting the importance of these sectors for Cape Verde’s economy. AI-powered satellite imagery has proven effective in delineating land use patterns with high accuracy, supporting sustainable resource management strategies. Further research should explore inter-seasonal variations and incorporate user feedback into the model to enhance its practical utility. 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.