African ICT in Education (Technology Focus) | 27 September 2006
AI-Powered Satellite Imagery for Land Use Mapping and Monitoring in Cape Verde: An African Perspective
J, o, a, n, a, F, e, r, r, e, i, r, a, R, o, s, a, ,, M, á, r, i, o, C, o, e, l, h, o, A, l, b, u, q, u, e, r, q, u, e, ,, C, r, i, s, t, i, n, a, G, o, n, ç, a, l, v, e, s, C, o, r, r, e, i, a
Abstract
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 $\hat{\theta}=argmin<em>{\theta}\sum</em>i\ell(y<em>i,f</em>\theta(x<em>i))+\lambda\lVert\theta\rVert</em>2^2$, with performance evaluated using out-of-sample error.