Work

Intelligent Segmentation of Urban Building Roofs and Solar Energy Potential Estimation for Photovoltaic Applications

Year: 2025

Type: article

Abstract: To support dual-carbon objectives and enhance the accuracy of rooftop distributed photovoltaic (PV) planning, this study proposes a multidimensional coupled evaluation framework that integrates an improved rooftop segmentation network (CESW-TransUNet), a residual-fusion ensemble, and physics-based shading and performance simulations, thereby correcting the bias of conventional 2-D area-based methods. First, CESW-TransUNet, equipped with convolution-enhanced modules, achieves robust multi-scale rooftop extraction and reaches an IoU of 78.50% on the INRIA benchmark, representing a 2.27 percentage point improvement over TransUNet. Second, the proposed residual fusion strategy adaptively integrates multiple models, including DeepLabV3+ and PSPNet, further improving the IoU to 79.85%. Finally, by coupling Ecotect-based shadow analysis with PVsyst performance modeling, the framework systematically quantifies dynamic inter-building shading, rooftop equipment occupancy, and installation suitability. A case study demonstrates that the method reduces the systematic overestimation of annual generation by 27.7% compared with traditional 2-D assessments. The framework thereby offers a quantitative, end-to-end decision tool for urban rooftop PV planning, enabling more reliable evaluation of generation and carbon-mitigation potential.

Source: Journal of Imaging

DOI: 10.3390/jimaging11100334

Authors: Junsen Zeng, Minglong Yang, Xiujuan Tang, Xiaotong Guan, Tingting Ma

Institution: Kunming University of Science and Technology

Language: English

Topic: Solar Radiation and Photovoltaics

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

SDGs: Sustainable cities and communities, Affordable and clean energy, Climate action, Industry, innovation and infrastructure

Open Access status: gold

Estimated APC paid: $2,172