The paper explores the importance of photovoltaic (PV) energy for decarbonization and the role of remote sensing in monitoring rooftop PV installations. It highlights the current limitations of these techniques, including their sensitivity to shifts in acquisition conditions. To enhance reliability, the authors propose the use of the wavelet scale attribution method (WCAM), which assesses the scales on which a PV model rests. This method provides insights to derive methods that improve the robustness to acquisition conditions, thus increasing trust in deep learning systems for the safe integration of clean energy in electric systems.
Publication date: 21 Sep 2023
Project Page: https://arxiv.org/abs/2309.12214v1
Paper: https://arxiv.org/pdf/2309.12214
