Satellite-Derived Bathymetry Mapping on Horseshoe Island, Antarctic Peninsula, with Open-Source Satellite Images: Evaluation of Atmospheric Correction Methods and Empirical Models
Satellite-derived bathymetry (SDB) is the process of estimating water depth in shallow coastal and inland waters using satellite imagery. Recent advances in technology and data processing have led to improvements in the accuracy and availability of SDB. The increased availability of free optical sat...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-05-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/10/2568 |
| _version_ | 1797598467119382528 |
|---|---|
| author | Emre Gülher Ugur Alganci |
| author_facet | Emre Gülher Ugur Alganci |
| author_sort | Emre Gülher |
| collection | DOAJ |
| description | Satellite-derived bathymetry (SDB) is the process of estimating water depth in shallow coastal and inland waters using satellite imagery. Recent advances in technology and data processing have led to improvements in the accuracy and availability of SDB. The increased availability of free optical satellite sensors, such as Landsat missions and Sentinel 2 satellites, has increased the quantity and frequency of SDB research and mapping efforts. In addition, machine learning (ML)- and deep learning (DL)-based algorithms, which can learn to identify features that are indicative of water depth, such as color or texture variations, have started to be used for extracting bathymetry information from satellite imagery. This study aims to produce an initial optical image-based SBD map of Horseshoe Island’s shallow coasts and to perform a comprehensive and comparative evaluation with Landsat 8 and Sentinel 2 satellite images. Our research considers the performance of empirical SDB models (classical, ML-based, and DL-based) and the effects of the atmospheric correction methods ACOLITE, iCOR, and ATCOR. For all band combinations and depth intervals, the ML-based random forest and XGBoost models delivered the highest performance and best fitting ability by achieving the lowest error with MAEs smaller than 1 m up to 10 m depth and a maximum correlation of R<sup>2</sup> around 0.80. These models are followed by the DL-based ANN and CNN models. Nonetheless, the non-linearity of the reflectance–depth connection was significantly reduced by the ML-based models. Furthermore, Landsat 8 showed better performance for 10–20 m depth intervals and in the entire range of (0–20 m), while Sentinel 2 was slightly better up to 10 m depth intervals. Lastly, ACOLITE, iCOR, and ATCOR provided reliable and consistent results for SDB, where ACOLITE provided the highest automation. |
| first_indexed | 2024-03-11T03:21:33Z |
| format | Article |
| id | doaj.art-9016430ec487495082c88a18e1ecc01c |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-11T03:21:33Z |
| publishDate | 2023-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-9016430ec487495082c88a18e1ecc01c2023-11-18T03:06:58ZengMDPI AGRemote Sensing2072-42922023-05-011510256810.3390/rs15102568Satellite-Derived Bathymetry Mapping on Horseshoe Island, Antarctic Peninsula, with Open-Source Satellite Images: Evaluation of Atmospheric Correction Methods and Empirical ModelsEmre Gülher0Ugur Alganci1Geomatics Engineering Program, Graduate School, Istanbul Technical University, 34469 Istanbul, TurkeyGeomatics Engineering Department, Civil Engineering Faculty, Istanbul Technical University, 34469 Istanbul, TurkeySatellite-derived bathymetry (SDB) is the process of estimating water depth in shallow coastal and inland waters using satellite imagery. Recent advances in technology and data processing have led to improvements in the accuracy and availability of SDB. The increased availability of free optical satellite sensors, such as Landsat missions and Sentinel 2 satellites, has increased the quantity and frequency of SDB research and mapping efforts. In addition, machine learning (ML)- and deep learning (DL)-based algorithms, which can learn to identify features that are indicative of water depth, such as color or texture variations, have started to be used for extracting bathymetry information from satellite imagery. This study aims to produce an initial optical image-based SBD map of Horseshoe Island’s shallow coasts and to perform a comprehensive and comparative evaluation with Landsat 8 and Sentinel 2 satellite images. Our research considers the performance of empirical SDB models (classical, ML-based, and DL-based) and the effects of the atmospheric correction methods ACOLITE, iCOR, and ATCOR. For all band combinations and depth intervals, the ML-based random forest and XGBoost models delivered the highest performance and best fitting ability by achieving the lowest error with MAEs smaller than 1 m up to 10 m depth and a maximum correlation of R<sup>2</sup> around 0.80. These models are followed by the DL-based ANN and CNN models. Nonetheless, the non-linearity of the reflectance–depth connection was significantly reduced by the ML-based models. Furthermore, Landsat 8 showed better performance for 10–20 m depth intervals and in the entire range of (0–20 m), while Sentinel 2 was slightly better up to 10 m depth intervals. Lastly, ACOLITE, iCOR, and ATCOR provided reliable and consistent results for SDB, where ACOLITE provided the highest automation.https://www.mdpi.com/2072-4292/15/10/2568satellite-derived bathymetryLandsat 8Sentinel 2machine learningdeep learningatmospheric correction |
| spellingShingle | Emre Gülher Ugur Alganci Satellite-Derived Bathymetry Mapping on Horseshoe Island, Antarctic Peninsula, with Open-Source Satellite Images: Evaluation of Atmospheric Correction Methods and Empirical Models Remote Sensing satellite-derived bathymetry Landsat 8 Sentinel 2 machine learning deep learning atmospheric correction |
| title | Satellite-Derived Bathymetry Mapping on Horseshoe Island, Antarctic Peninsula, with Open-Source Satellite Images: Evaluation of Atmospheric Correction Methods and Empirical Models |
| title_full | Satellite-Derived Bathymetry Mapping on Horseshoe Island, Antarctic Peninsula, with Open-Source Satellite Images: Evaluation of Atmospheric Correction Methods and Empirical Models |
| title_fullStr | Satellite-Derived Bathymetry Mapping on Horseshoe Island, Antarctic Peninsula, with Open-Source Satellite Images: Evaluation of Atmospheric Correction Methods and Empirical Models |
| title_full_unstemmed | Satellite-Derived Bathymetry Mapping on Horseshoe Island, Antarctic Peninsula, with Open-Source Satellite Images: Evaluation of Atmospheric Correction Methods and Empirical Models |
| title_short | Satellite-Derived Bathymetry Mapping on Horseshoe Island, Antarctic Peninsula, with Open-Source Satellite Images: Evaluation of Atmospheric Correction Methods and Empirical Models |
| title_sort | satellite derived bathymetry mapping on horseshoe island antarctic peninsula with open source satellite images evaluation of atmospheric correction methods and empirical models |
| topic | satellite-derived bathymetry Landsat 8 Sentinel 2 machine learning deep learning atmospheric correction |
| url | https://www.mdpi.com/2072-4292/15/10/2568 |
| work_keys_str_mv | AT emregulher satellitederivedbathymetrymappingonhorseshoeislandantarcticpeninsulawithopensourcesatelliteimagesevaluationofatmosphericcorrectionmethodsandempiricalmodels AT uguralganci satellitederivedbathymetrymappingonhorseshoeislandantarcticpeninsulawithopensourcesatelliteimagesevaluationofatmosphericcorrectionmethodsandempiricalmodels |