SolarSAM: Building-scale Photovoltaic Potential Assessment Based on Segment Anything Model (SAM) and Remote Sensing for Emerging City

TL;DR

SolarSAM is a novel deep learning-based method that assesses building-integrated photovoltaic potential in emerging cities using remote sensing and semantic segmentation, revealing significant solar power potential surpassing city electricity needs.

Contribution

The paper introduces SolarSAM, a new approach combining remote sensing and deep learning for detailed BIPV potential assessment in cities lacking street-level data.

Findings

BIPV potential exceeds city electricity consumption by 2.5 times.

Model accurately segments rooftops and evaluates PV systems.

Economic and environmental benefits are demonstrated.

Abstract

Driven by advancements in photovoltaic (PV) technology, solar energy has emerged as a promising renewable energy source, due to its ease of integration onto building rooftops, facades, and windows. For the emerging cities, the lack of detailed street-level data presents a challenge for effectively assessing the potential of building-integrated photovoltaic (BIPV). To address this, this study introduces SolarSAM, a novel BIPV evaluation method that leverages remote sensing imagery and deep learning techniques, and an emerging city in northern China is utilized to validate the model performance. During the process, SolarSAM segmented various building rooftops using text prompt guided semantic segmentation. Separate PV models were then developed for Rooftop PV, Facade-integrated PV, and PV windows systems, using this segmented data and local climate information. The potential for BIPV installation, solar power generation, and city-wide power self-sufficiency were assessed, revealing that the annual BIPV power generation potential surpassed the city's total electricity consumption by a factor of 2.5. Economic and environmental analysis were also conducted, including levelized cost of electricity and carbon reduction calculations, comparing different BIPV systems across various building categories. These findings demonstrated the model's performance and reveled the potential of BIPV power generation in the future.