Surveying Nearshore Bathymetry Using Multispectral and Hyperspectral Satellite Imagery and Machine Learning
Nearshore bathymetric data are essential for assessing coastal hazards, studying benthic habitats and for coastal engineering. Traditional bathymetry mapping techniques of ship-sounding and airborne LiDAR are laborious, expensive and not always efficient. Multispectral and hyperspectral remote sensi...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/17/2/291 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832587574914318336 |
|---|---|
| author | David Hartmann Mathieu Gravey Timothy David Price Wiebe Nijland Steven Michael de Jong |
| author_facet | David Hartmann Mathieu Gravey Timothy David Price Wiebe Nijland Steven Michael de Jong |
| author_sort | David Hartmann |
| collection | DOAJ |
| description | Nearshore bathymetric data are essential for assessing coastal hazards, studying benthic habitats and for coastal engineering. Traditional bathymetry mapping techniques of ship-sounding and airborne LiDAR are laborious, expensive and not always efficient. Multispectral and hyperspectral remote sensing, in combination with machine learning techniques, are gaining interest. Here, the nearshore bathymetry of southwest Puerto Rico is estimated with multispectral Sentinel-2 and hyperspectral PRISMA imagery using conventional spectral band ratio models and more advanced XGBoost models and convolutional neural networks. The U-Net, trained on 49 Sentinel-2 images, and the 2D-3D CNN, trained on PRISMA imagery, had a Mean Absolute Error (MAE) of approximately 1 m for depths up to 20 m and were superior to band ratio models by ~40%. Problems with underprediction remain for turbid waters. Sentinel-2 showed higher performance than PRISMA up to 20 m (~18% lower MAE), attributed to training with a larger number of images and employing an ensemble prediction, while PRISMA outperformed Sentinel-2 for depths between 25 m and 30 m (~19% lower MAE). Sentinel-2 imagery is recommended over PRISMA imagery for estimating shallow bathymetry given its similar performance, much higher image availability and easier handling. Future studies are recommended to train neural networks with images from various regions to increase generalization and method portability. Models are preferably trained by area-segregated splits to ensure independence between the training and testing set. Using a random train test split for bathymetry is not recommended due to spatial autocorrelation of sea depth, resulting in data leakage. This study demonstrates the high potential of machine learning models for assessing the bathymetry of optically shallow waters using optical satellite imagery. |
| format | Article |
| id | doaj-art-6d4debc799c441af87177d4ad64da9d2 |
| institution | Kabale University |
| issn | 2072-4292 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj-art-6d4debc799c441af87177d4ad64da9d22025-01-24T13:48:01ZengMDPI AGRemote Sensing2072-42922025-01-0117229110.3390/rs17020291Surveying Nearshore Bathymetry Using Multispectral and Hyperspectral Satellite Imagery and Machine LearningDavid Hartmann0Mathieu Gravey1Timothy David Price2Wiebe Nijland3Steven Michael de Jong4Royal Netherlands Aerospace Centre (NLR), Anthony Fokkerweg 2, 1059 CM Amsterdam, The NetherlandsInstitute for Interdisciplinary Mountain Research, Austrian Academy of Sciences, 6020 Innsbruck, AustriaFaculty of Geosciences, Utrecht University, Princetonlaan 8A, 3584 CW Utrecht, The NetherlandsFaculty of Geosciences, Utrecht University, Princetonlaan 8A, 3584 CW Utrecht, The NetherlandsFaculty of Geosciences, Utrecht University, Princetonlaan 8A, 3584 CW Utrecht, The NetherlandsNearshore bathymetric data are essential for assessing coastal hazards, studying benthic habitats and for coastal engineering. Traditional bathymetry mapping techniques of ship-sounding and airborne LiDAR are laborious, expensive and not always efficient. Multispectral and hyperspectral remote sensing, in combination with machine learning techniques, are gaining interest. Here, the nearshore bathymetry of southwest Puerto Rico is estimated with multispectral Sentinel-2 and hyperspectral PRISMA imagery using conventional spectral band ratio models and more advanced XGBoost models and convolutional neural networks. The U-Net, trained on 49 Sentinel-2 images, and the 2D-3D CNN, trained on PRISMA imagery, had a Mean Absolute Error (MAE) of approximately 1 m for depths up to 20 m and were superior to band ratio models by ~40%. Problems with underprediction remain for turbid waters. Sentinel-2 showed higher performance than PRISMA up to 20 m (~18% lower MAE), attributed to training with a larger number of images and employing an ensemble prediction, while PRISMA outperformed Sentinel-2 for depths between 25 m and 30 m (~19% lower MAE). Sentinel-2 imagery is recommended over PRISMA imagery for estimating shallow bathymetry given its similar performance, much higher image availability and easier handling. Future studies are recommended to train neural networks with images from various regions to increase generalization and method portability. Models are preferably trained by area-segregated splits to ensure independence between the training and testing set. Using a random train test split for bathymetry is not recommended due to spatial autocorrelation of sea depth, resulting in data leakage. This study demonstrates the high potential of machine learning models for assessing the bathymetry of optically shallow waters using optical satellite imagery.https://www.mdpi.com/2072-4292/17/2/291satellite-derived bathymetryhyperspectral PRISMAmultispectral Sentinel-2machine learningconvolution neural networks |
| spellingShingle | David Hartmann Mathieu Gravey Timothy David Price Wiebe Nijland Steven Michael de Jong Surveying Nearshore Bathymetry Using Multispectral and Hyperspectral Satellite Imagery and Machine Learning Remote Sensing satellite-derived bathymetry hyperspectral PRISMA multispectral Sentinel-2 machine learning convolution neural networks |
| title | Surveying Nearshore Bathymetry Using Multispectral and Hyperspectral Satellite Imagery and Machine Learning |
| title_full | Surveying Nearshore Bathymetry Using Multispectral and Hyperspectral Satellite Imagery and Machine Learning |
| title_fullStr | Surveying Nearshore Bathymetry Using Multispectral and Hyperspectral Satellite Imagery and Machine Learning |
| title_full_unstemmed | Surveying Nearshore Bathymetry Using Multispectral and Hyperspectral Satellite Imagery and Machine Learning |
| title_short | Surveying Nearshore Bathymetry Using Multispectral and Hyperspectral Satellite Imagery and Machine Learning |
| title_sort | surveying nearshore bathymetry using multispectral and hyperspectral satellite imagery and machine learning |
| topic | satellite-derived bathymetry hyperspectral PRISMA multispectral Sentinel-2 machine learning convolution neural networks |
| url | https://www.mdpi.com/2072-4292/17/2/291 |
| work_keys_str_mv | AT davidhartmann surveyingnearshorebathymetryusingmultispectralandhyperspectralsatelliteimageryandmachinelearning AT mathieugravey surveyingnearshorebathymetryusingmultispectralandhyperspectralsatelliteimageryandmachinelearning AT timothydavidprice surveyingnearshorebathymetryusingmultispectralandhyperspectralsatelliteimageryandmachinelearning AT wiebenijland surveyingnearshorebathymetryusingmultispectralandhyperspectralsatelliteimageryandmachinelearning AT stevenmichaeldejong surveyingnearshorebathymetryusingmultispectralandhyperspectralsatelliteimageryandmachinelearning |