Facade Segmentation for Solar Photovoltaic Suitability

2025-11-24

AI Summary

Automated, high-fidelity assessment of building-integrated photovoltaic (BIPV) potential on urban façades remains limited due to oversimplified geometric or radiometric assumptions. Method: This paper proposes an end-to-end analytical framework that incorporates fine-grained façade structural semantics. It fine-tunes the SegFormer-B5 model on the CMP Facades dataset for semantic façade segmentation and integrates photovoltaic module dimensions and installation spacing constraints to generate engineering-feasible, façade-level solar suitability masks. Contribution/Results: The approach explicitly models architectural details—including window-to-wall ratio and shading elements—within BIPV suitability analysis for the first time. Evaluated on 373 real-world façades across ten cities, it yields installable PV potential averaging 42.6% lower than theoretical (unconstrained) estimates, substantially enhancing the reliability and practical implementability of city-scale BIPV planning.

Technology Category

• Computer Vision: Segmentation
• Humans and AI: AI for Accessibility
• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Security and Privacy: Large-scale security measurements
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Building integrated photovoltaic (BIPV) facades represent a promising pathway towards urban decarbonization, especially where roof areas are insufficient and ground-mounted arrays are infeasible. Although machine learning-based approaches to support photovoltaic (PV) planning on rooftops are well researched, automated approaches for facades still remain scarce and oversimplified. This paper therefore presents a pipeline that integrates detailed information on the architectural composition of the facade to automatically identify suitable surfaces for PV application and estimate the solar energy potential. The pipeline fine-tunes SegFormer-B5 on the CMP Facades dataset and converts semantic predictions into facade-level PV suitability masks and PV panel layouts considering module sizes and clearances. Applied to a dataset of 373 facades with known dimensions from ten cities, the results show that installable BIPV potential is significantly lower than theoretical potential, thus providing valuable insights for reliable urban energy planning. With the growing availability of facade imagery, the proposed pipeline can be scaled to support BIPV planning in cities worldwide.

Problem

• Automated facade segmentation for photovoltaic suitability assessment
• Estimating solar energy potential on building facades
• Addressing scarcity of automated approaches for facade PV planning

Innovation

• Fine-tunes SegFormer-B5 for facade segmentation
• Converts semantic predictions into PV suitability masks
• Generates panel layouts considering module sizes and clearances