Land use mapping is crucial for monitoring changes in agricultural productivity and environmental impact over time. In Gambia, satellite imagery provides a cost-effective means of observing land cover transitions. Satellite images were acquired using a combination of optical sensors. Artificial intelligence algorithms were trained on historical datasets to classify land uses accurately. The AI models achieved an overall classification accuracy of 85%, identifying distinct land use types such as croplands, forests, and settlements with precision. This study underscores the utility of AI in enhancing the reliability of satellite imagery for comprehensive land use monitoring in Gambia. Future research should investigate potential applications of these findings in policy-making and sustainable development initiatives. AI, satellite imagery, land use mapping, Gambia 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.