Automated Rooftop Solar Panel Detection Through Convolutional Neural Networks

Transforming the global energy sector from fossil-fuel based to renewable energy sources is crucial to limiting global warming and achieving climate neutrality. The decentralized nature of the renewable energy system allows private households to deploy photovoltaic systems on their rooftops. However...

Full description

Saved in:
Bibliographic Details
Main Authors: Simon Pena Pereira, Azarakhsh Rafiee, Stef Lhermitte
Format: Article
Language:English
Published: Taylor & Francis Group 2024-12-01
Series:Canadian Journal of Remote Sensing
Online Access:http://dx.doi.org/10.1080/07038992.2024.2363236
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846095206557941760
author Simon Pena Pereira
Azarakhsh Rafiee
Stef Lhermitte
author_facet Simon Pena Pereira
Azarakhsh Rafiee
Stef Lhermitte
author_sort Simon Pena Pereira
collection DOAJ
description Transforming the global energy sector from fossil-fuel based to renewable energy sources is crucial to limiting global warming and achieving climate neutrality. The decentralized nature of the renewable energy system allows private households to deploy photovoltaic systems on their rooftops. However, inconsistent data on installed photovoltaic (PV) systems complicate planning for an efficient grid expansion. To address this issue, deep-learning techniques, can support collecting data about PV systems from aerial and satellite imagery. Previous research, however, lacks the consideration for ground truth data-specific characteristics of PV panels. This study aims to implement a semantic segmentation model that detects PV systems in aerial imagery to explore the impact of area-specific characteristics in the training data and CNN hyperparameters on the performance of a CNN. Hence, a U-Net architecture is employed to analyze land use types, rooftop colors, and lower-resolution images. Additionally, the impact of near-infrared data on the detection rate of PV panels is analyzed. The results indicate that a U-Net is suitable for classifying PV panels in high-resolution aerial imagery (10 cm) by reaching F1 scores of up to 91.75% while demonstrating the importance of adapting the training data to area-specific ground truth data concerning urban and architectural properties.
format Article
id doaj-art-ddd36a6128d2413f8751f60ba5f4cc90
institution Kabale University
issn 1712-7971
language English
publishDate 2024-12-01
publisher Taylor & Francis Group
record_format Article
series Canadian Journal of Remote Sensing
spelling doaj-art-ddd36a6128d2413f8751f60ba5f4cc902025-01-02T11:34:20ZengTaylor & Francis GroupCanadian Journal of Remote Sensing1712-79712024-12-0150110.1080/07038992.2024.23632362363236Automated Rooftop Solar Panel Detection Through Convolutional Neural NetworksSimon Pena Pereira0Azarakhsh Rafiee1Stef Lhermitte2Geo-Database Management Center, Delft University of TechnologyGeo-Database Management Center, Delft University of TechnologyDepartment Earth & Environmental Sciences, KU LeuvenTransforming the global energy sector from fossil-fuel based to renewable energy sources is crucial to limiting global warming and achieving climate neutrality. The decentralized nature of the renewable energy system allows private households to deploy photovoltaic systems on their rooftops. However, inconsistent data on installed photovoltaic (PV) systems complicate planning for an efficient grid expansion. To address this issue, deep-learning techniques, can support collecting data about PV systems from aerial and satellite imagery. Previous research, however, lacks the consideration for ground truth data-specific characteristics of PV panels. This study aims to implement a semantic segmentation model that detects PV systems in aerial imagery to explore the impact of area-specific characteristics in the training data and CNN hyperparameters on the performance of a CNN. Hence, a U-Net architecture is employed to analyze land use types, rooftop colors, and lower-resolution images. Additionally, the impact of near-infrared data on the detection rate of PV panels is analyzed. The results indicate that a U-Net is suitable for classifying PV panels in high-resolution aerial imagery (10 cm) by reaching F1 scores of up to 91.75% while demonstrating the importance of adapting the training data to area-specific ground truth data concerning urban and architectural properties.http://dx.doi.org/10.1080/07038992.2024.2363236
spellingShingle Simon Pena Pereira
Azarakhsh Rafiee
Stef Lhermitte
Automated Rooftop Solar Panel Detection Through Convolutional Neural Networks
Canadian Journal of Remote Sensing
title Automated Rooftop Solar Panel Detection Through Convolutional Neural Networks
title_full Automated Rooftop Solar Panel Detection Through Convolutional Neural Networks
title_fullStr Automated Rooftop Solar Panel Detection Through Convolutional Neural Networks
title_full_unstemmed Automated Rooftop Solar Panel Detection Through Convolutional Neural Networks
title_short Automated Rooftop Solar Panel Detection Through Convolutional Neural Networks
title_sort automated rooftop solar panel detection through convolutional neural networks
url http://dx.doi.org/10.1080/07038992.2024.2363236
work_keys_str_mv AT simonpenapereira automatedrooftopsolarpaneldetectionthroughconvolutionalneuralnetworks
AT azarakhshrafiee automatedrooftopsolarpaneldetectionthroughconvolutionalneuralnetworks
AT steflhermitte automatedrooftopsolarpaneldetectionthroughconvolutionalneuralnetworks