FEPVNet: A Network with Adaptive Strategies for Cross-Scale Mapping of Photovoltaic Panels from Multi-Source Images

Abstract

The world is transitioning to renewable energy, with photovoltaic (PV) solar power being one of the most promising energy sources. Large-scale PV mapping provides the most up-to-date and accurate PV geospatial information, which is crucial for planning and constructing PV power plants, optimizing energy structure, and assessing the ecological impact of PVs. However, previous methods of PV extraction relied on simple models and single data sources, which could not accurately obtain PV geospatial information. Therefore, we propose the Filter-Embedded Network (FEPVNet), which embeds high-pass and low-pass filters and Polarized Self-Attention (PSA) into a High-Resolution Network (HRNet) to improve its noise resistance and adaptive feature extraction capabilities, ultimately enhancing the accuracy of PV extraction. We also introduce three data migration strategies by combining Sentinel-2, Google-14, and Google-16 images in varying proportions and transferring the FEPVNet trained on Sentinel-2 images to Gaofen-2 images, which improves the generalization performance of models trained on a single data source for extracting PVs in images of different scales. Our model improvement experiments demonstrate that the Intersection over Union (IoU) of FEPVNet in segmenting China PVs in Sentinel-2 images reaches 88.68%, a 2.37% increase compared to the HRNet. Furthermore, we use FEPVNet and the optimal migration strategy to extract photovoltaics across scales, achieving a precision of 94.37%. In summary, this study proposes the FEPVNet model with adaptive strategies for extracting PVs from multiple image sources, with significant potential for application in large-scale PV mapping.