Applying single-image super-resolution for the enhancement of deep-water bathymetry
We present research using single-image super-resolution (SISR) algorithms to enhance knowledge of the seafloor using the 1-minute GEBCO 2014 grid when 100m grids from high-resolution sonar systems are available for training. We performed numerical experiments of x15 upscaling along three midocean ri...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2019-10-01
|
| Series: | Heliyon |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2405844019362309 |
| _version_ | 1828416444817211392 |
|---|---|
| author | Kristen Nock David Bonanno Paul Elmore Leslie Smith Vicki Ferrini Fred Petry |
| author_facet | Kristen Nock David Bonanno Paul Elmore Leslie Smith Vicki Ferrini Fred Petry |
| author_sort | Kristen Nock |
| collection | DOAJ |
| description | We present research using single-image super-resolution (SISR) algorithms to enhance knowledge of the seafloor using the 1-minute GEBCO 2014 grid when 100m grids from high-resolution sonar systems are available for training. We performed numerical experiments of x15 upscaling along three midocean ridge areas in the Eastern Pacific Ocean. We show that four SISR algorithms can enhance this low-resolution knowledge of bathymetry versus bicubic or Splines-In-Tension algorithms through upscaling under these conditions: 1) rough topography is present in both training and testing areas and 2) the range of depths and features in the training area contains the range of depths in the enhancement area. We quantitatively judged successful SISR enhancement versus bicubic interpolation when Student's hypothesis testing show significant improvement of the root-mean squared error (RMSE) between upscaled bathymetry and 100m gridded ground-truth bathymetry at p < 0.05. In addition, we found evidence that random forest based SISR methods may provide more robust enhancements versus non-forest based SISR algorithms. |
| first_indexed | 2024-12-10T14:04:00Z |
| format | Article |
| id | doaj.art-1445d111db0c4239b6cb208974d0cbb7 |
| institution | Directory Open Access Journal |
| issn | 2405-8440 |
| language | English |
| last_indexed | 2024-12-10T14:04:00Z |
| publishDate | 2019-10-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Heliyon |
| spelling | doaj.art-1445d111db0c4239b6cb208974d0cbb72022-12-22T01:45:42ZengElsevierHeliyon2405-84402019-10-01510e02570Applying single-image super-resolution for the enhancement of deep-water bathymetryKristen Nock0David Bonanno1Paul Elmore2Leslie Smith3Vicki Ferrini4Fred Petry5Naval Research Laboratory, Washington DC, USANaval Research Laboratory, Washington DC, USAJohns Hopkins University, Applied Physics Laboratory, Laurel, MD, USANaval Research Laboratory, Washington DC, USALamont-Doherty Earth Observatory Columbia University, Palisades, NY, USANaval Research Laboratory, Stennis Space Center, MS, USA; Corresponding author.We present research using single-image super-resolution (SISR) algorithms to enhance knowledge of the seafloor using the 1-minute GEBCO 2014 grid when 100m grids from high-resolution sonar systems are available for training. We performed numerical experiments of x15 upscaling along three midocean ridge areas in the Eastern Pacific Ocean. We show that four SISR algorithms can enhance this low-resolution knowledge of bathymetry versus bicubic or Splines-In-Tension algorithms through upscaling under these conditions: 1) rough topography is present in both training and testing areas and 2) the range of depths and features in the training area contains the range of depths in the enhancement area. We quantitatively judged successful SISR enhancement versus bicubic interpolation when Student's hypothesis testing show significant improvement of the root-mean squared error (RMSE) between upscaled bathymetry and 100m gridded ground-truth bathymetry at p < 0.05. In addition, we found evidence that random forest based SISR methods may provide more robust enhancements versus non-forest based SISR algorithms.http://www.sciencedirect.com/science/article/pii/S2405844019362309Computer scienceEarth sciencesSingle-image super-resolutionUpscalingBathymetry |
| spellingShingle | Kristen Nock David Bonanno Paul Elmore Leslie Smith Vicki Ferrini Fred Petry Applying single-image super-resolution for the enhancement of deep-water bathymetry Heliyon Computer science Earth sciences Single-image super-resolution Upscaling Bathymetry |
| title | Applying single-image super-resolution for the enhancement of deep-water bathymetry |
| title_full | Applying single-image super-resolution for the enhancement of deep-water bathymetry |
| title_fullStr | Applying single-image super-resolution for the enhancement of deep-water bathymetry |
| title_full_unstemmed | Applying single-image super-resolution for the enhancement of deep-water bathymetry |
| title_short | Applying single-image super-resolution for the enhancement of deep-water bathymetry |
| title_sort | applying single image super resolution for the enhancement of deep water bathymetry |
| topic | Computer science Earth sciences Single-image super-resolution Upscaling Bathymetry |
| url | http://www.sciencedirect.com/science/article/pii/S2405844019362309 |
| work_keys_str_mv | AT kristennock applyingsingleimagesuperresolutionfortheenhancementofdeepwaterbathymetry AT davidbonanno applyingsingleimagesuperresolutionfortheenhancementofdeepwaterbathymetry AT paulelmore applyingsingleimagesuperresolutionfortheenhancementofdeepwaterbathymetry AT lesliesmith applyingsingleimagesuperresolutionfortheenhancementofdeepwaterbathymetry AT vickiferrini applyingsingleimagesuperresolutionfortheenhancementofdeepwaterbathymetry AT fredpetry applyingsingleimagesuperresolutionfortheenhancementofdeepwaterbathymetry |