Downscaling Surface Albedo to Higher Spatial Resolutions With an Image Super-Resolution Approach and PROBA-V Satellite Images
For bifacial solar photovoltaic panels, surface albedo plays a crucial role in estimating the radiant energy. Since land surfaces are heterogeneous, the actual albedo of the surface where the solar photovoltaic panel is placed can vary widely and its temporality and sparsity present a significant ch...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10015024/ |
| _version_ | 1828056060791881728 |
|---|---|
| author | Sagthitharan Karalasingham Ravinesh C. Deo David Casillas-Perez Nawin Raj Sancho Salcedo-Sanz |
| author_facet | Sagthitharan Karalasingham Ravinesh C. Deo David Casillas-Perez Nawin Raj Sancho Salcedo-Sanz |
| author_sort | Sagthitharan Karalasingham |
| collection | DOAJ |
| description | For bifacial solar photovoltaic panels, surface albedo plays a crucial role in estimating the radiant energy. Since land surfaces are heterogeneous, the actual albedo of the surface where the solar photovoltaic panel is placed can vary widely and its temporality and sparsity present a significant challenge for renewable energy engineers. This paper develops a new image super-resolution deep learning model based on convolutional neural network to generate high resolution spatial representations of surface albedo from coarse resolution remote sensing-based data. For selected Australian locations, we generated a higher resolution surface albedo using imagery from PROBA-V/SPOT Earth Observation satellites. We proposed a Deep Downscaling Spectral Model with Attention (DDSA) with the capability of processing 10-day albedo images captured at a relatively low (≈ 1 km) resolution. The proposed DDSA was then applied to downscale observed surface albedo and generate predicted albedo at 500 m, 333 m and 250 m resolutions. The proposed model was benchmarked with alternative deep learning, super-resolution approaches: Super-Resolution Convolution Neural Network (SRCNN), Enhanced Deep Super-Resolution network (EDSR), Efficient Sub-Pixel Convolutional Neural Network (ESPCN) and Residual Dense Network (RDN). The results showed that the proposed DDSA model outperformed all comparative models in terms of the mean square error (MSE) <inline-formula> <tex-math notation="LaTeX">$\approx ~0.0041$ </tex-math></inline-formula>, signal-to-noise ratio (PSNR) <inline-formula> <tex-math notation="LaTeX">$\approx ~39.471$ </tex-math></inline-formula>, Structural Similarity Index (SSIM) <inline-formula> <tex-math notation="LaTeX">$\approx ~0.999$ </tex-math></inline-formula> vs. an MSE <inline-formula> <tex-math notation="LaTeX">$\approx $ </tex-math></inline-formula> [0.0140-0.0387], PSNR <inline-formula> <tex-math notation="LaTeX">$\approx $ </tex-math></inline-formula> [29.761-33.850], SSIM <inline-formula> <tex-math notation="LaTeX">$\approx $ </tex-math></inline-formula> [0.9994-0.999]). We also cross-validated the downscaled images with satellite imagery and ground-based observations, which reaffirmed the proposed DDSA model’s ability to produce high resolution surface albedo maps and its potential applications for granular scale tracking and mapping solar energy where bifacial solar photovoltaic panels are placed. |
| first_indexed | 2024-04-10T20:49:34Z |
| format | Article |
| id | doaj.art-d54d837f645341d8849b9cf404fe960f |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-10T20:49:34Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-d54d837f645341d8849b9cf404fe960f2023-01-24T00:00:29ZengIEEEIEEE Access2169-35362023-01-01115558557710.1109/ACCESS.2023.323625310015024Downscaling Surface Albedo to Higher Spatial Resolutions With an Image Super-Resolution Approach and PROBA-V Satellite ImagesSagthitharan Karalasingham0Ravinesh C. Deo1https://orcid.org/0000-0002-2290-6749David Casillas-Perez2https://orcid.org/0000-0002-5721-1242Nawin Raj3https://orcid.org/0000-0002-8364-2644Sancho Salcedo-Sanz4https://orcid.org/0000-0002-4048-1676School of Mathematics, Physics and Computing, University of Southern Queensland, Springfield Central, QLD, AustraliaSchool of Mathematics, Physics and Computing, University of Southern Queensland, Springfield Central, QLD, AustraliaDepartment of Signal Processing and Communications, Universidad Rey Juan Carlos, Fuenlabrada, Madrid, SpainSchool of Mathematics, Physics and Computing, University of Southern Queensland, Springfield Central, QLD, AustraliaSchool of Mathematics, Physics and Computing, University of Southern Queensland, Springfield Central, QLD, AustraliaFor bifacial solar photovoltaic panels, surface albedo plays a crucial role in estimating the radiant energy. Since land surfaces are heterogeneous, the actual albedo of the surface where the solar photovoltaic panel is placed can vary widely and its temporality and sparsity present a significant challenge for renewable energy engineers. This paper develops a new image super-resolution deep learning model based on convolutional neural network to generate high resolution spatial representations of surface albedo from coarse resolution remote sensing-based data. For selected Australian locations, we generated a higher resolution surface albedo using imagery from PROBA-V/SPOT Earth Observation satellites. We proposed a Deep Downscaling Spectral Model with Attention (DDSA) with the capability of processing 10-day albedo images captured at a relatively low (≈ 1 km) resolution. The proposed DDSA was then applied to downscale observed surface albedo and generate predicted albedo at 500 m, 333 m and 250 m resolutions. The proposed model was benchmarked with alternative deep learning, super-resolution approaches: Super-Resolution Convolution Neural Network (SRCNN), Enhanced Deep Super-Resolution network (EDSR), Efficient Sub-Pixel Convolutional Neural Network (ESPCN) and Residual Dense Network (RDN). The results showed that the proposed DDSA model outperformed all comparative models in terms of the mean square error (MSE) <inline-formula> <tex-math notation="LaTeX">$\approx ~0.0041$ </tex-math></inline-formula>, signal-to-noise ratio (PSNR) <inline-formula> <tex-math notation="LaTeX">$\approx ~39.471$ </tex-math></inline-formula>, Structural Similarity Index (SSIM) <inline-formula> <tex-math notation="LaTeX">$\approx ~0.999$ </tex-math></inline-formula> vs. an MSE <inline-formula> <tex-math notation="LaTeX">$\approx $ </tex-math></inline-formula> [0.0140-0.0387], PSNR <inline-formula> <tex-math notation="LaTeX">$\approx $ </tex-math></inline-formula> [29.761-33.850], SSIM <inline-formula> <tex-math notation="LaTeX">$\approx $ </tex-math></inline-formula> [0.9994-0.999]). We also cross-validated the downscaled images with satellite imagery and ground-based observations, which reaffirmed the proposed DDSA model’s ability to produce high resolution surface albedo maps and its potential applications for granular scale tracking and mapping solar energy where bifacial solar photovoltaic panels are placed.https://ieeexplore.ieee.org/document/10015024/Surface albedo downscalingimage super resolutiondepth-wise separable convolutionbifacial solar photovoltaic system |
| spellingShingle | Sagthitharan Karalasingham Ravinesh C. Deo David Casillas-Perez Nawin Raj Sancho Salcedo-Sanz Downscaling Surface Albedo to Higher Spatial Resolutions With an Image Super-Resolution Approach and PROBA-V Satellite Images IEEE Access Surface albedo downscaling image super resolution depth-wise separable convolution bifacial solar photovoltaic system |
| title | Downscaling Surface Albedo to Higher Spatial Resolutions With an Image Super-Resolution Approach and PROBA-V Satellite Images |
| title_full | Downscaling Surface Albedo to Higher Spatial Resolutions With an Image Super-Resolution Approach and PROBA-V Satellite Images |
| title_fullStr | Downscaling Surface Albedo to Higher Spatial Resolutions With an Image Super-Resolution Approach and PROBA-V Satellite Images |
| title_full_unstemmed | Downscaling Surface Albedo to Higher Spatial Resolutions With an Image Super-Resolution Approach and PROBA-V Satellite Images |
| title_short | Downscaling Surface Albedo to Higher Spatial Resolutions With an Image Super-Resolution Approach and PROBA-V Satellite Images |
| title_sort | downscaling surface albedo to higher spatial resolutions with an image super resolution approach and proba v satellite images |
| topic | Surface albedo downscaling image super resolution depth-wise separable convolution bifacial solar photovoltaic system |
| url | https://ieeexplore.ieee.org/document/10015024/ |
| work_keys_str_mv | AT sagthitharankaralasingham downscalingsurfacealbedotohigherspatialresolutionswithanimagesuperresolutionapproachandprobavsatelliteimages AT ravineshcdeo downscalingsurfacealbedotohigherspatialresolutionswithanimagesuperresolutionapproachandprobavsatelliteimages AT davidcasillasperez downscalingsurfacealbedotohigherspatialresolutionswithanimagesuperresolutionapproachandprobavsatelliteimages AT nawinraj downscalingsurfacealbedotohigherspatialresolutionswithanimagesuperresolutionapproachandprobavsatelliteimages AT sanchosalcedosanz downscalingsurfacealbedotohigherspatialresolutionswithanimagesuperresolutionapproachandprobavsatelliteimages |