Wildfires caused by power-grid infrastructure—especially in poorly maintained sections of the network—are a major safety and economic risk. The increasing availability of high-resolution aerial and satellite imagery enables large-area, repeatable monitoring of grid assets, providing the basis for systematic mapping and, ultimately, anomaly detection. This thesis investigates automatic mapping of overhead high-voltage transmission infrastructure in Switzerland from 10,cm aerial orthophotos (SWISSIMAGE). A geospatial data pipeline is developed to align orthophotos with a national reference layer of electrical installations within a common coordinate system, rasterize tower and cable annotations into pixel-wise supervision masks, and construct a largescale dataset using 1km × 1km tiles and 1024×1024 image patches.