Globally Scalable, QGIS-Integrated Workflow for Solar Photovoltaic System Segmentation and Capacity Estimation: A Case Study in Algeria

This study presents a deep learning-based approach for the segmentation of Solar Photovoltaic (PV) systems using a ResNet-based DeepLabV3 architecture. The method is seamlessly integrated into the open-source Geographic Information System QGIS environment through the user-friendly Deepness plugin and allows intuitive application on geospatial base maps anywhere in the world. A case study was conducted in the Piat region of Algeria, focusing on seven large PV systems within an autonomous power grid. After segmentation, a power density factor in megawatt-peak (MWp) was used to calculate the capacity of each identified PV system. The calculated capacities were compared with the official values of the operators, showing a mean relative error of 8.5 %. To further refine the capacity estimates, we introduce a locally adjusted factor of 73.5 MWp/km<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup>, which reflects the expected results for the region more precisely. The approach is globally applicable, easily transferable to different geographical contexts and accessible to users without programming knowledge, offering significant potential for renewable energy analysis. The dataset is publicly available for download [1] and can be used interactively [2].