Improving the resolution of solar energy potential maps derived from global DSMs for rooftop solar panel placement using deep learning
This study focuses on generating high-resolution annual solar energy potential maps (ASMs) using global Digital Elevation Models (DEMs) to aid in solar panel placement, especially in urban areas. A framework was developed to enhance the resolution of these maps. Initially, the accuracy of ASMs deriv...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-01-01
|
| Series: | Heliyon |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2405844024172246 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841526234155057152 |
|---|---|
| author | Maryam Hosseini Hossein Bagheri |
| author_facet | Maryam Hosseini Hossein Bagheri |
| author_sort | Maryam Hosseini |
| collection | DOAJ |
| description | This study focuses on generating high-resolution annual solar energy potential maps (ASMs) using global Digital Elevation Models (DEMs) to aid in solar panel placement, especially in urban areas. A framework was developed to enhance the resolution of these maps. Initially, the accuracy of ASMs derived from various DEMs was compared with LiDAR-derived ASMs. The evaluations indicated that the Copernicus DEM provided a highly accurate ASM. Subsequently, deep learning algorithms were trained to improve the resolution of the LiDAR-derived ASM. The results demonstrated that the Enhanced Deep Super-Resolution (EDSR) Network outperformed the U-Net-based model. The trained EDSR model was then utilized to enhance the resolution of the Copernicus ASM. Comparing the enhanced-resolution map of Copernicus respective to LiDAR showed that the EDSR model provided the necessary generalizability to improve the accuracy and resolution of the Copernicus ASM, particularly in urban areas. The investigations revealed that the improved resolution map with a resolution of 6 m, achieving RMSE of 35.75 MWhm2 and a correlation of 0.87 respective to LiDAR data, was capable of locating solar panels on buildings, whereas the original Copernicus-derived maps with a 30 m resolution had RMSE of 51.26 MWhm2 and a correlation of 0.72 for such placement purposes. |
| format | Article |
| id | doaj-art-df0616830d7a4dc9b668c69de4a733ac |
| institution | Kabale University |
| issn | 2405-8440 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Heliyon |
| spelling | doaj-art-df0616830d7a4dc9b668c69de4a733ac2025-01-17T04:50:28ZengElsevierHeliyon2405-84402025-01-01111e41193Improving the resolution of solar energy potential maps derived from global DSMs for rooftop solar panel placement using deep learningMaryam Hosseini0Hossein Bagheri1Faculty of Civil Engineering and Transportation, University of Isfahan, Isfahan, IranCorresponding author.; Faculty of Civil Engineering and Transportation, University of Isfahan, Isfahan, IranThis study focuses on generating high-resolution annual solar energy potential maps (ASMs) using global Digital Elevation Models (DEMs) to aid in solar panel placement, especially in urban areas. A framework was developed to enhance the resolution of these maps. Initially, the accuracy of ASMs derived from various DEMs was compared with LiDAR-derived ASMs. The evaluations indicated that the Copernicus DEM provided a highly accurate ASM. Subsequently, deep learning algorithms were trained to improve the resolution of the LiDAR-derived ASM. The results demonstrated that the Enhanced Deep Super-Resolution (EDSR) Network outperformed the U-Net-based model. The trained EDSR model was then utilized to enhance the resolution of the Copernicus ASM. Comparing the enhanced-resolution map of Copernicus respective to LiDAR showed that the EDSR model provided the necessary generalizability to improve the accuracy and resolution of the Copernicus ASM, particularly in urban areas. The investigations revealed that the improved resolution map with a resolution of 6 m, achieving RMSE of 35.75 MWhm2 and a correlation of 0.87 respective to LiDAR data, was capable of locating solar panels on buildings, whereas the original Copernicus-derived maps with a 30 m resolution had RMSE of 51.26 MWhm2 and a correlation of 0.72 for such placement purposes.http://www.sciencedirect.com/science/article/pii/S2405844024172246Solar energy mapSuper-resolutionDigital elevation modelDeep learningSolar panel placement |
| spellingShingle | Maryam Hosseini Hossein Bagheri Improving the resolution of solar energy potential maps derived from global DSMs for rooftop solar panel placement using deep learning Heliyon Solar energy map Super-resolution Digital elevation model Deep learning Solar panel placement |
| title | Improving the resolution of solar energy potential maps derived from global DSMs for rooftop solar panel placement using deep learning |
| title_full | Improving the resolution of solar energy potential maps derived from global DSMs for rooftop solar panel placement using deep learning |
| title_fullStr | Improving the resolution of solar energy potential maps derived from global DSMs for rooftop solar panel placement using deep learning |
| title_full_unstemmed | Improving the resolution of solar energy potential maps derived from global DSMs for rooftop solar panel placement using deep learning |
| title_short | Improving the resolution of solar energy potential maps derived from global DSMs for rooftop solar panel placement using deep learning |
| title_sort | improving the resolution of solar energy potential maps derived from global dsms for rooftop solar panel placement using deep learning |
| topic | Solar energy map Super-resolution Digital elevation model Deep learning Solar panel placement |
| url | http://www.sciencedirect.com/science/article/pii/S2405844024172246 |
| work_keys_str_mv | AT maryamhosseini improvingtheresolutionofsolarenergypotentialmapsderivedfromglobaldsmsforrooftopsolarpanelplacementusingdeeplearning AT hosseinbagheri improvingtheresolutionofsolarenergypotentialmapsderivedfromglobaldsmsforrooftopsolarpanelplacementusingdeeplearning |