Remote Sensing for Monitoring Photovoltaic Solar Plants in Brazil Using Deep Semantic Segmentation
Brazil is a tropical country with continental dimensions and abundant solar resources that are still underutilized. However, solar energy is one of the most promising renewable sources in the country. The proper inspection of Photovoltaic (PV) solar plants is an issue of great interest for the Brazi...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-05-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/14/10/2960 |
| _version_ | 1797533363234406400 |
|---|---|
| author | Marcus Vinícius Coelho Vieira da Costa Osmar Luiz Ferreira de Carvalho Alex Gois Orlandi Issao Hirata Anesmar Olino de Albuquerque Felipe Vilarinho e Silva Renato Fontes Guimarães Roberto Arnaldo Trancoso Gomes Osmar Abílio de Carvalho Júnior |
| author_facet | Marcus Vinícius Coelho Vieira da Costa Osmar Luiz Ferreira de Carvalho Alex Gois Orlandi Issao Hirata Anesmar Olino de Albuquerque Felipe Vilarinho e Silva Renato Fontes Guimarães Roberto Arnaldo Trancoso Gomes Osmar Abílio de Carvalho Júnior |
| author_sort | Marcus Vinícius Coelho Vieira da Costa |
| collection | DOAJ |
| description | Brazil is a tropical country with continental dimensions and abundant solar resources that are still underutilized. However, solar energy is one of the most promising renewable sources in the country. The proper inspection of Photovoltaic (PV) solar plants is an issue of great interest for the Brazilian territory’s energy management agency, and advances in computer vision and deep learning allow automatic, periodic, and low-cost monitoring. The present research aims to identify PV solar plants in Brazil using semantic segmentation and a mosaicking approach for large image classification. We compared four architectures (U-net, DeepLabv3+, Pyramid Scene Parsing Network, and Feature Pyramid Network) with four backbones (Efficient-net-b0, Efficient-net-b7, ResNet-50, and ResNet-101). For mosaicking, we evaluated a sliding window with overlapping pixels using different stride values (8, 16, 32, 64, 128, and 256). We found that: (1) the models presented similar results, showing that the most relevant approach is to acquire high-quality labels rather than models in many scenarios; (2) U-net presented slightly better metrics, and the best configuration was U-net with the Efficient-net-b7 encoder (98% overall accuracy, 91% IoU, and 95% F-score); (3) mosaicking progressively increases results (precision-recall and receiver operating characteristic area under the curve) when decreasing the stride value, at the cost of a higher computational cost. The high trends of solar energy growth in Brazil require rapid mapping, and the proposed study provides a promising approach. |
| first_indexed | 2024-03-10T11:14:26Z |
| format | Article |
| id | doaj.art-a8b0469d15fd457aad3078a4ae292d0c |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-10T11:14:26Z |
| publishDate | 2021-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-a8b0469d15fd457aad3078a4ae292d0c2023-11-21T20:34:41ZengMDPI AGEnergies1996-10732021-05-011410296010.3390/en14102960Remote Sensing for Monitoring Photovoltaic Solar Plants in Brazil Using Deep Semantic SegmentationMarcus Vinícius Coelho Vieira da Costa0Osmar Luiz Ferreira de Carvalho1Alex Gois Orlandi2Issao Hirata3Anesmar Olino de Albuquerque4Felipe Vilarinho e Silva5Renato Fontes Guimarães6Roberto Arnaldo Trancoso Gomes7Osmar Abílio de Carvalho Júnior8Superintendency of Information Technology, Brazilian Electricity Regulatory Agency, Brasília 70.910-900, BrazilDepartment of Computer Science, University of Brasília, Brasília 70.910-900, BrazilSuperintendency of Information Technology, Brazilian Electricity Regulatory Agency, Brasília 70.910-900, BrazilSuperintendency of Information Technology, Brazilian Electricity Regulatory Agency, Brasília 70.910-900, BrazilDepartment of Geography, University of Brasília, Brasília 70.910-900, BrazilSuperintendency of Information Technology, Brazilian Electricity Regulatory Agency, Brasília 70.910-900, BrazilDepartment of Geography, University of Brasília, Brasília 70.910-900, BrazilDepartment of Geography, University of Brasília, Brasília 70.910-900, BrazilDepartment of Geography, University of Brasília, Brasília 70.910-900, BrazilBrazil is a tropical country with continental dimensions and abundant solar resources that are still underutilized. However, solar energy is one of the most promising renewable sources in the country. The proper inspection of Photovoltaic (PV) solar plants is an issue of great interest for the Brazilian territory’s energy management agency, and advances in computer vision and deep learning allow automatic, periodic, and low-cost monitoring. The present research aims to identify PV solar plants in Brazil using semantic segmentation and a mosaicking approach for large image classification. We compared four architectures (U-net, DeepLabv3+, Pyramid Scene Parsing Network, and Feature Pyramid Network) with four backbones (Efficient-net-b0, Efficient-net-b7, ResNet-50, and ResNet-101). For mosaicking, we evaluated a sliding window with overlapping pixels using different stride values (8, 16, 32, 64, 128, and 256). We found that: (1) the models presented similar results, showing that the most relevant approach is to acquire high-quality labels rather than models in many scenarios; (2) U-net presented slightly better metrics, and the best configuration was U-net with the Efficient-net-b7 encoder (98% overall accuracy, 91% IoU, and 95% F-score); (3) mosaicking progressively increases results (precision-recall and receiver operating characteristic area under the curve) when decreasing the stride value, at the cost of a higher computational cost. The high trends of solar energy growth in Brazil require rapid mapping, and the proposed study provides a promising approach.https://www.mdpi.com/1996-1073/14/10/2960solar paneldeep learningsemantic segmentation |
| spellingShingle | Marcus Vinícius Coelho Vieira da Costa Osmar Luiz Ferreira de Carvalho Alex Gois Orlandi Issao Hirata Anesmar Olino de Albuquerque Felipe Vilarinho e Silva Renato Fontes Guimarães Roberto Arnaldo Trancoso Gomes Osmar Abílio de Carvalho Júnior Remote Sensing for Monitoring Photovoltaic Solar Plants in Brazil Using Deep Semantic Segmentation Energies solar panel deep learning semantic segmentation |
| title | Remote Sensing for Monitoring Photovoltaic Solar Plants in Brazil Using Deep Semantic Segmentation |
| title_full | Remote Sensing for Monitoring Photovoltaic Solar Plants in Brazil Using Deep Semantic Segmentation |
| title_fullStr | Remote Sensing for Monitoring Photovoltaic Solar Plants in Brazil Using Deep Semantic Segmentation |
| title_full_unstemmed | Remote Sensing for Monitoring Photovoltaic Solar Plants in Brazil Using Deep Semantic Segmentation |
| title_short | Remote Sensing for Monitoring Photovoltaic Solar Plants in Brazil Using Deep Semantic Segmentation |
| title_sort | remote sensing for monitoring photovoltaic solar plants in brazil using deep semantic segmentation |
| topic | solar panel deep learning semantic segmentation |
| url | https://www.mdpi.com/1996-1073/14/10/2960 |
| work_keys_str_mv | AT marcusviniciuscoelhovieiradacosta remotesensingformonitoringphotovoltaicsolarplantsinbrazilusingdeepsemanticsegmentation AT osmarluizferreiradecarvalho remotesensingformonitoringphotovoltaicsolarplantsinbrazilusingdeepsemanticsegmentation AT alexgoisorlandi remotesensingformonitoringphotovoltaicsolarplantsinbrazilusingdeepsemanticsegmentation AT issaohirata remotesensingformonitoringphotovoltaicsolarplantsinbrazilusingdeepsemanticsegmentation AT anesmarolinodealbuquerque remotesensingformonitoringphotovoltaicsolarplantsinbrazilusingdeepsemanticsegmentation AT felipevilarinhoesilva remotesensingformonitoringphotovoltaicsolarplantsinbrazilusingdeepsemanticsegmentation AT renatofontesguimaraes remotesensingformonitoringphotovoltaicsolarplantsinbrazilusingdeepsemanticsegmentation AT robertoarnaldotrancosogomes remotesensingformonitoringphotovoltaicsolarplantsinbrazilusingdeepsemanticsegmentation AT osmarabiliodecarvalhojunior remotesensingformonitoringphotovoltaicsolarplantsinbrazilusingdeepsemanticsegmentation |