This dataset is the final product of research through the projects ANTARES (grant agreement No. 739570) and CYBELE (grant agreement No. 825355). The dataset consists of yield, protein content and selective harvesting soya maps at a resolution of 10 m. These maps were created by satellite images and soil properties data using machine learning algorithms. Maps are located in the Upper Austria region. Files with the name of "map yield" contain information about yield amount per pixel, while files with "map protein" denote parcels with predicted protein content. Also, the same protein map files contain an additional class column. Class 1 indicates pixels where soya have good quality (protein content > 41), while class 2 represents poorer quality.