Accurate elevation information is essential for many applications such as navigation and defense systems. However, real world elevation often comes from sensors that provide sparse, non-uniform, or incomplete measurements. Under these conditions, classical methods may fail to produce reliable elevation maps. This project evaluates whether a decoder-only Transformer-based model can outperform classical spatial interpolation, when the known neighborhood is sparse and limited. While the Transformer reduced the average error by 11% across the test set, its performance varied by location. In some regions, classical methods remained more effective and vice versa. Importantly, analysis of the results suggests that the Transformer can provide substantial corrections in difficult cases, indicating that deep learning can serve as a complementary tool for elevation mapping.