From roofs to renewables: Deep learning and geographic information systems insights into a comprehensive urban solar photovoltaic assessment for Stonehaven

As urban solar photovoltaic (PV) construction emerges as a leading renewable energy technology, there is a growing focus on its implementation. However, the challenges of scarce, low-resolution, and inaccurate PV-related data sources hinder accurate assessments of urban PV potentials and are not conducive to efficient and rational smart city planning. This study tackles these challenges by introducing a mature, detailed, and accurate assessment process, taking Stonehaven as an example, aimed at leveraging limited data to mine more data and geographic information useful for guiding urban PV planning. Initially, utilise existing Digital Surface Model (DSM) and optical image data, combined with deep learning techniques and a PV potential assessment model, to comprehensively assess the PV power generation potential of the Stonehaven area. Our results demonstrate that integrating DSM significantly enhances the accuracy of roof segmentation. Furthermore, compared with DeeplabV3, U-Net performs better in roof segmentation. Additionally, the solar radiation potential (SRP) map generated by DSM highlights the superior solar radiation receiving capacity of south-facing and flat roofs. We provide a detailed PV power generation potential (PPGP) map of individual building roofs, revealing the substantial potential of this area for generating up to 1.12 × 10^7 kWh of electricity per year. Detailed and fine-grained PPGP can also help to optimise PV siting and electricity resource allocation. Furthermore, our return-on-investment period (ROIP) analysis indicates that most Stonehaven roofs have ROIPs between 8.1 and 11.3 years. The detailed ROIP distribution map can help people make informed PV investment decisions. Future research directions include enhancing data quality, refining segmentation algorithms, and exploring assisted urban energy planning analysis for smarter urban planning.