City-scale solar PV potential estimation on 3D buildings using multi-source RS data: A case study in Wuhan, China

Zhe Chen, Bisheng Yang, Rui Zhu and Zhen Dong

Applied Energy, 2024, vol. 359, issue C, No S030626192400103X

Abstract: Assessing the solar photovoltaic (PV) potential on buildings is essential for environmental protection and sustainable development. However, currently, the high costs of data acquisition and labor required to obtain 3D building models limit the scalability of such estimations extending to a large scale. To overcome the limitations, this study proposes a method of using freely available multi-source Remote Sensing (RS) data to estimate the solar PV potential on buildings at the city scale without any labeling. Firstly, Unsupervised Domain Adaptation (UDA) is introduced to transfer the building extraction knowledge learned by Deep Semantic Segmentation Networks (DSSN) from public datasets to available satellite images in a label-free manner. In addition, the coarse-grained land cover product is utilized to provide prior knowledge for reducing negative transfer. Secondly, the building heights are derived from the global open Digital Surface Model (DSM) using morphological operations. The building information obtained from the above two aspects supports the subsequent estimation. In the case study of Wuhan, China, the solar PV potential on all buildings throughout the city is estimated without any data acquisition cost or human labeling cost through the proposed method. In 2021, the estimated solar irradiation received by buildings in Wuhan is 289737.58 GWh. Taking into account the current technical conditions, the corresponding solar PV potential is 43460.64 GWh, which can meet the electricity demands of residents. The code and test data for building information extraction are available at https://github.com/WHU-USI3DV/3DBIE-SolarPV.

Keywords: Sustainable development goals; Multi-source remote sensing data; Building solar photovoltaic potential; Deep learning; Unsupervised domain adaptation (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (2)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S030626192400103X
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:appene:v:359:y:2024:i:c:s030626192400103x

Ordering information: This journal article can be ordered from
http://www.elsevier.com/wps/find/journaldescription.cws_home/405891/bibliographic
http://www.elsevier. ... 405891/bibliographic

DOI: 10.1016/j.apenergy.2024.122720

Access Statistics for this article

Applied Energy is currently edited by J. Yan

More articles in Applied Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().