This study explores land use classification in Trento using supervised learning techniques combined with call detail records (CDRs) as a proxy for human activity. Located in an alpine environment, Trento presents unique geographic challenges, including varied terrain and sparse network coverage, making it an ideal case for testing the robustness of supervised learning approaches. By analyzing spatiotemporal patterns in CDRs, we trained and evaluated several classification algorithms, including k-nearest neighbors (kNN), support vector machines (SVM), and random forests (RF), to map land use categories, such as home, work, and forest. A comparative analysis highlights the performance of each method, emphasizing the strengths of RF in capturing complex patterns, its good generalization ability, and the usage of kNN with different distance measures. Our supervised machine-learning approach outperforms unsupervised clustering techniques by capturing complex patterns and achieving higher accuracy. Results demonstrate the potential of CDRs for urban planning, offering a cost-effective approach for fine-grained land use monitoring with the particularities of Trento, as its landscape combines urban areas, agricultural fields, and forested regions, reflecting its alpine setting, in contrast with other metropolitan regions.