Creating a Dataset of Spatial Parameters of Ground-Mounted Photovoltaic Systems Utilising Orthophotos and the Segment Anything Model

Abstract. The rapid expansion of renewable energy sources poses significant challenges in reconciling energy development with competing interests. This underscores the necessity for precise spatial data to facilitate effective balancing, management, or evaluation of compliance with regulatory frameworks. This paper presents a zero-shot approach for extracting parameters of ground-mounted photovoltaic systems in Germany based on digital orthophotos. This allows for the accurate identification and delineation of essential spatial parameters, including the ground coverage ratio of photovoltaic modules, the row spacing between module rows, and their exact orientation. The results of this study are twofold. First, the developed technical pipeline successfully achieves high-quality segmentation of photovoltaic module rows, with over 71 % of the results demonstrating satisfactory to flawless segmentation. Second, the resulting dataset is made available for further analysis and can serve as a starting point for the development of additional AI models aimed at monitoring the dynamics of photovoltaic systems.